Timely and accurate information on tree species is crucial for the sustainable management of natural resources, forest inventory, biodiversity detection, and carbon stock calculation. The advancement of remote sensing technology and artificial intelligence has facilitated the acquisition and analysis of remote sensing data, resulting in more precise and effective classification of tree species. Multimodal remote sensing data and deep learning seem to be the current tree species classification research mainstream, whether or not. The current review on the remote sensing data and deep learning tree species classification methods perspectives to analyze the unimodal and multimodal remote sensing data and classification methods in this realm is missing. To bridge the gap, we search for major trends in the remote sensing data and tree species classification methods, provide a detailed overview of classic deep learning-based methods for tree species classification, and discuss the limitations.

This paper reviews recent literature on Spatial Data Infrastructure (SDI) for remote sensing, aiming to provide a comprehensive analysis of the state-of-the-art practices, challenges, and future directions. It also tries to find out if current projects and initiatives involving the exploitation of satellite remote sensing are still framed in the SDI concepts.

A large amount of raw data collected by satellites is processed by the production chain to obtain a large amount of product data, of which the secure exchange and storage is of interest to researchers in the field of remote sensing information science. Authentic, secure data is a critical foundation for data analysis and decision-making. And traditional centralized cloud computing systems are vulnerable to attacks, and once the central server is successfully attacked, all data will be lost. Distributed Ledger Technology (DLT) is an innovative computer technology that can ensure information security, traceability and tamper-proof, and can be applied to the field of remote sensing. Although there are many advantages to using DLT in remote sensing applications, there are some obstacles and limitations to its application. Remote sensing data has the characteristics of large data volume, spatiotemporal nature, global and so on, and it is difficult to store and interconnect remote sensing data in the blockchain. To address these issues, this paper proposes a trustworthy and decentralized system using blockchain. The novelty of this paper is to propose a multi-level blockchain architecture in which the system collects remote sensing data and stores it in the Interplanetary File System (IPFS) network, after generating the IPFS hash, the network rehashes the value again and uploads it on the Ethereum chain for public query. Distributed data storage improves data security, supports the secure exchange of information, and improves the efficiency of data management.

Multimodal remote sensing data classification can enhance the model’s ability to distinguish land features through multimodal data fusion. In this context, how to help models understand the relationship between multimodal data and target tasks is the focus of researchers. Inspired by human feedback learning mechanisms, causal reasoning mechanisms, and knowledge induction mechanisms, this paper integrates causal learning, reinforcement learning, and meta learning into a unified remote sensing data classification framework and proposed the causal meta-reinforcement learning (CMRL). First, based on feedback learning mechanisms, we have overcome the limitations of traditional implicit optimization of fusion features and customized a reinforcement learning environment for multimodal remote sensing data classification tasks. Through feedback interactive learning between agents and the environment, we help them understand the complex relationships between multimodal data and labels, thereby achieving full mining of multimodal complementary information. Second, based on the causal inference mechanism we designed causal distribution prediction action, classification reward, and causal intervention reward, capturing pure causal factors in multimodal data and cutting off false statistical associations between non-causal factors and class labels. Finally, based on the knowledge induction mechanism, we designed a bi-layer optimization mechanism based on meta-learning. By constructing a meta training task and meta validation task simulation model in the generalization scenario of unseen data, we helped the model induce cross-task shared knowledge, thereby improving its generalization ability for unseen multimodal data. The experimental results on multiple sets of multimodal datasets show that the proposed method achieved state-of-the-art performance in multimodal remote sensing data classification tasks.

Geologists employ high-spatial-resolution (HR) remote sensing (RS) data for many diverse applications as they effectively reflect detailed geological information, enabling high-quality and efficient geological surveys. Applications of HR RS data to geological and related fields have grown recently. By analyzing these applications, we can better understand the results of previous studies and more effectively use the latest data and methods to efficiently extract key geological information. HR optical remote sensing data are widely used in geological hazard assessment, seismic monitoring, mineral exploitation, glacier monitoring, and mineral information extraction due to high accuracy and clear object features. Compared with optical satellite images, synthetic-aperture radar (SAR) images are stereoscopic and exhibit clear relief, strong performance, and good detection of terrain, landforms, and other information. SAR images have been applied to seismic mechanism research, volcanic monitoring, topographic deformation, and fault analysis. Furthermore, a multi-standard maturity analysis of the geological applications of HR images using literature from the Science Citation Index reveals that optical remote sensing data are superior to radar data for mining, geological disaster, lithologic, and volcanic applications, but inferior for earthquake, glacial, and fault applications. Therefore, geological remote sensing research needs to be truly multidisciplinary or interdisciplinary, ensuring more detailed and efficient surveys through cross-linking with other disciplines. Moreover, the recent application of deep learning technology to remote sensing data extraction has improved automatic processing and data analysis capabilities.

Parametric cyclonic wind fields are widely used worldwide for insurance risk underwriting, coastal planning, or storm surge forecasts. They support high-stakes financial, development, and emergency decisions. Yet, there is still no consensus on the best parametric approach, or relevant guidance to choose among the great variety of published models. The aim of this paper is first and foremost to demonstrate that recent progresses on estimating extreme surface wind speeds from satellite remote sensing now makes it possible to select the best option with greater objectivity. In particular, we show that the Cyclone Global Navigation Satellite System (CYGNSS) mission of NASA is able to capture a substantial part of the tropical cyclones structure, and allows identifying systematic biases in a number of parametric models. Our results also suggest that none of the traditional empirical approaches can be considered as the best option in all cases. Rather, the choice of a parametric model depends on several criteria such as cyclone intensity and/or availability of wind radii information. The benefit of using satellite remote sensing data to better select a parametric model for a specific case study is tested here by simulating hurricane Maria (2017). The significant wave heights computed by a wave-current hydrodynamic coupled model are found to be in good accordance with the predictions given by the remote sensing data in terms of bias. The results and approach presented in this study should shed new light on how to handle parametric cyclonic wind models, and help the scientific community to conduct better wind, waves and surge analysis for tropical cyclones.

Many remote sensing analytical data products are most useful when they are in an appropriate regional or national projection, rather than globally based projections like Universal Transverse Mercator (UTM) or geographic coordinates, i.e., latitude and longitude. Furthermore, leaving data in the global systems can create problems, either due to misprojection of imagery because of UTM zone boundaries, or because said projections are not optimised for local use. We developed the open-source Irish Earth Observation (IEO) Python module to maintain a local remote sensing data library for Ireland. This pure Python module, in conjunction with the IEOtools Python scripts, utilises the Geospatial Data Abstraction Library (GDAL) for its geoprocessing functionality. At present, the module supports only Landsat TM/ETM+/OLI/TIRS data that have been corrected to surface reflectance using the USGS/ESPA LEDAPS/ LaSRC Collection 1 architecture. This module and the IEOtools catalogue available Landsat data from the USGS/EROS archive, and includes functions for the importation of imagery into a defined local projection and calculation of cloud-free vegetation indices. While this module is distributed with default values and data for Ireland, it can be adapted for other regions with simple modifications to the configuration files and geospatial data sets.

This paper introduces the self-supervised pretext task of rare visual token enhancement: given an image, the model is trained to push the rarest visual tokens far from all the others. This pretext task slightly-but-consistently improves baseline performances for both registration and few-shot change detection on OSCD, LEVIR-CD and S2looking.

Surface water distribution extracted from remote sensing data has been used in water resource assessment, coastal management, and environmental change studies. Traditional manual methods for extracting water bodies cannot satisfy the requirements for mass processing of remote sensing data; therefore, accurate automated extraction of such water bodies has remained a challenge. The histogram bimodal method (HBM) is a frequently used objective tool for threshold selection in image segmentation. The threshold is determined by seeking twin peaks, and the valley values between them; however, automatically calculating the threshold is difficult because complex surfaces and image noise which lead to not perfect twin peaks (single or multiple peaks). We developed an operational automated water extraction method, the modified histogram bimodal method (MHBM). The MHBM defines the threshold range of water extraction through mass static data; therefore, it does not require the identification of twin histogram peaks. It then seeks the minimum values in the threshold range to achieve automated threshold. We calibrated the MHBM for many lakes in China using Landsat 8 Operational Land Imager (OLI) images, for which the relative error (RE) and squared correlation coefficient (R2) for threshold accuracy were found to be 2.1% and 0.96, respectively. The RE and root-mean-square error (RMSE) for the area accuracy of MHBM were 0.59% and 7.4 km2. The results show that the MHBM could easily be applied to mass time-series remote sensing data to calculate water thresholds within water index images and successfully extract the spatial distribution of large water bodies automatically.

Remote sensing (RS) is a compulsory component in studying and monitoring ecosystems suffering from the disruption of natural balance, productivity, and degradation. Current study attempted to assess the feasibility of multisource RS for assessing and monitoring mountainous natural grasslands in Armenia. Series of the different spatial resolution RS data (Landsat 8, Sentinel 2, Planet Scope, and multispectral UAV data) were used to obtain various vegetation spectral indices: NDVI, NDWI, GNDVI, GLI, EVI, DVI, SAVI, MSAVI, and GSAVI, and the relationship among the indices were assessed via Spearman correlation method, which shows a significant positive correlation for all cases (p < 0.01). A comparison of all indices shows a significant high correlation between UAV and the PlanetScope imagery. The comparison of UAV, Sentinel and Landsat data show moderate and low significant correlation (p < 0.01) correspondingly. Also, trend analysis was performed to explore their spatial-temporal changes using Mann-Kendall statistical tests (MK, MKKH, MKKY, PW, TFPW), which indicated no significant trend. However, Sen’s slope as second estimator shows decreasing trend. Though the best result received for PlanetScope and Sentinel 2, Sentinel-2 data seem to have better alignment making it a reliable tool for an accurate monitoring of small mountainous grasslands in Armenia.

Satellite imagery has had limited application in the analysis of pre-colonial settlement archaeology in the Caribbean; visible evidence of wooden structures perishes quickly in tropical climates. Only slight topographic modifications remain, typically associated with middens. Nonetheless, surface scatters, as well as the soil characteristics they produce, can serve as quantifiable indicators of an archaeological site, which can be detected by analysis of remote sensing imagery. A variety of data sets were investigated, with the intention to combine multispectral bands to feed a direct detection algorithm, providing a semi-automatic process to cross-correlate the datasets. Sampling was done using locations of known sites, as well as areas with no archaeological evidence. The pre-processed very diverse remote sensing data sets have gone through a process of image registration. The algorithm was applied in the northwestern Dominican Republic on areas that included different types of environments, chosen for having sufficient imagery coverage, and a representative number of known locations of indigenous sites. The resulting maps present quantifiable statistical results of locations with similar pixel value combinations as the identified sites, indicating higher probability of archaeological evidence. The results show the variable potential of this method in diverse environments.

With the rapid development of earth observation, satellite navigation, mobile communication and other technologies, the order of magnitude of the spatial data we acquire and accumulate is increasing, and higher requirements are put forward for the application and storage of spatial data. Under this circumstance, a new form of spatial data organization emerged-the global discrete grid. This form of data management can be used for the efficient storage and application of large-scale global spatial data, which is a digital multi-resolution the geo-reference model that helps to establish a new model of data association and fusion. It is expected to make up for the shortcomings in the organization, processing and application of current spatial data. There are different types of grid system according to the grid division form, including global discrete grids with equal latitude and longitude, global discrete grids with variable latitude and longitude, and global discrete grids based on regular polyhedrons. However, there is no accuracy evaluation index system for remote sensing images expressed on the global discrete grid to solve this problem. This paper is dedicated to finding a suitable way to express remote sensing data on discrete grids, and establishing a suitable accuracy evaluation system for modeling remote sensing data based on hexagonal grids to evaluate modeling accuracy. The results show that this accuracy evaluation method can evaluate and analyze remote sensing data based on hexagonal grids from multiple levels, and the comprehensive similarity coefficient of the images before and after conversion is greater than 98%, which further proves that the availability hexagonal grid-based remote sensing data of remote sensing images. And among the three sampling methods, the image obtained by the nearest interpolation sampling method has the highest correlation with the original image.

Snow parameters have traditionally been retrieved using discontinuous, multi-band sensors; however, continuous hyperspectral sensor are now being developed as an alternative. In this paper we investigate the performance of various sensor configurations using machine learning neural networks trained on a simulated dataset. Our results show improvements in accuracy of retrievals of snow grain size and impurity concentration for continuous hyperspectral channel configurations. Retrieval accuracy of snow albedo was found to be similar for all channel configurations.

Specific emissivity features of swamps and wetlands of Western Siberia were studied for changing seasonal conditions with the use of daily data of satellite microwave sounding. The research technique involved the analysis of brightness temperatures of the underlying surface at the test sites. Variations in seasonal dynamics of brightness temperatures were mainly caused by different rates of seasonal freezing of the upper waterlogged layer of the underlying surface and dielectric characteristics of water containing natural media (water body, soil, vegetation). We analyzed long-term trends in seasonal and annual dynamics of brightness temperatures of the underlying surface and estimated hydrological changes in the Arctic and Subarctic. The findings open up new possibilities for using satellite data in the microwave range for studying natural seasonal dynamic processes and predicting hazardous hydrological phenomena.

Estimating evapotranspiration at field scale is a major component of sustainable water management. Due to the difficulty to assess some major unknowns of the water cycle at that scale, including irrigation amounts, evapotranspiration is often computed as the residual of the instantaneous surface energy budget. One of the Surface Energy Bal-ance components with the largest uncertainties in their quantification over bare soils and sparse vegetation areas is the ground heat flux (G). Over the last decades, the es-timation of G with RS data has been mainly achieved with empirical equations, on the basis of the G and net radiation (Rn) ratio, G/Rn. G/Rn empirical equations generally require vegetation data (Type I empirical equations), in combination with surface tem-perature (Ts) and albedo (Type II empirical equations). In this article we aim to evalu-ate the estimation of G with RS. For the first time, we compare eight G/Rn empirical equations against two types of machine learning (ML) methods: an ensemble ML type, the Random Forest (RF), and the Neural Networks (NN). The comparison of each method is evaluated over dense dataset, including a wide range of climate and land covers, with data of Eddy-Covariance towers extended along the mid-latitude area that encompass the European and African continent. Our results have shown evidence that the driver of G in bare soils and sparse vegetation areas (Fraction of Vegetation, Fv <= 0.25) is Ts, instead of vegetation greenness indexes. On the other hand, the estimation of G with Rn, Ts or Fv decreases at dense vegetation areas (Fv >= 0.50). There are not significant differences between the most accurate type I and II empirical equations. For bare soils and sparse vegetation areas the empirical equation that better estimates G is E8, which combines the Leaf Area Index (LAI) and Ts. In dense vegetation areas (Fv >= 0.25), an exponential empirical equation based on Fv (E4), shows the best performance. However, ML better estimates G than the empirical equations, independently of the Fv ranges. A RF model with Rn, LAI and Ts as predictor variables shows the best accuracy and performance metrics, outperforming the NN model.

Near-surface humidity (Qa) is a key parameter that modulates oceanic evaporation and influences the global water cycle. Remote sensing observations act as feasible sources for long-term and large-scale Qa monitoring. However, existing satellite Qa retrieval models are subject to apparent uncertainties due to model errors and insufficient training data. Based on in situ observations collected over the China Seas over the last two decades, a deep learning approach named Ensemble Mean of Target deep neural networks (EMTnet) was proposed to improve the satellite Qa retrieval over the China Seas for the first time. The EMTnet model outperforms five representative existing models by nearly eliminating the mean bias and significantly reducing the root-mean-square error in satellite Qa retrieval. According to its target deep neural networks selection process, the EMTnet model can obtain more objective learning results when the observational data are divergent. The EMTnet model was subsequently applied to produce a 30-year monthly gridded Qa data over the China Seas. It indicates that the climbing rate of Qa over the China Seas under the background of global warming are probably underestimated by current products.

The global photovoltaic (PV) installed capacity, vital for the electric sector decarbonation, has reached 1,552.3 GWp in 2023. In France, the capacity stood in April 2024 at 19.9 GWp. The growth of the PV installed capacity over a year was nearly 32% worldwide and 15.7% in France. However, integrating PV electricity into grids is hindered by poor knowledge of rooftop PV systems, constituting 20% of France's installed capacity, and the lack of measurements of the production stemming from these systems. This problem of lack of measurements of the rooftop PV power production is referred to as the lack of observability. Using ground truth measurements of individual PV systems, available at an unprecedented temporal and spatial scale, we show that estimating the PV power production of an individual rooftop system by combining solar irradiance and temperature data, the characteristics of the PV system inferred from remote sensing methods and an irradiation-to-electric power conversion model provides accurate estimations of the PV power production. Our study shows that we can improve rooftop PV observability, and thus its integration into the electric grid, using little information on these systems, a simple model of the PV system and weather data.

With the popularity of solar energy in the electricity market, demand arises for data such as precise locations of solar panels for efficient energy planning, management, and distribution. However, this data is not easily accessible and in some cases, information such as precise locations does not exist. Furthermore, existing data sets for training semantic segmentation models of PV installations are limited, and their annotation is time-consuming and labor-intensive. Therefore, for additional remote sensing (RS) data creation, the pix2pix generative adversarial network (GAN) is utilized, enriching the original resampled training data of varying GSDs without compromising its integrity. Experiments done with the DeepLabV3 model, ResNet-50 backbone, and pix2pix GAN architecture were conducted to find the optimal configuration for an accurate RS imagery segmentation model. The result is a fine-tuned solar panel semantic segmentation model, trained using transfer learning and utilizing an optimal amount – 60% of generated RS imagery for additional training data, increasing model accuracy. The findings demonstrate the benefits of using GAN-generated images as additional training data, increasing the size of small data sets, and improving the capabilities of the segmentation model for solar panel detection in RS images.

Masons are often overlooked part of impact basins, but play an important role in revealing the lunar history. Previous study in masons were usually limited to gravity data. Few researches were reported on morphology features and chronology, which hampers the construction of a complete geological interpretation for the evolution of each mascons. We use multi source remote sensing data to identify the details characteristic of mascons. Result of topography, gravity and characteristic are combined to prove that a mason beside Copernicus crater is a buried peak-ring basin which is about 130km and 260km in diameter. The underground structure is of confirmed as 890m thick mare basalts by analyzing the spectral feature of the material in a geological outcrop called Copernicus H. Geology evolution analysis joint crater size-frequency distribution (CSDF) dating demonstrate that the buried basin impact event occurred in 3.6Ga. Then a hawaiian-style eruption in late Imbrian formed Sinus Aestuum Ⅰ Dark Mantling Deposit (DMD). Mare basalts filling in 3.4Ga. After that, ejecta from Copernicus impact event in about 820Ma and weathering processes cause the disappearing from lunar surface of the buried basin.

Globally, seagrass meadows provide critical ecosystem services. However, seagrasses are globally degraded at an accelerated rate. The lack of information on seagrass spatial distribution and seagrass health status seriously hinders seagrass conservation and management. Therefore, this study proposes to combine remote sensing big data with a new hybrid machine learning model (RF-SWOA) to predict potential seagrass habitats. The multivariate remote sensing data is used to train the machine learning model, which can improve the prediction accuracy of the model. This study shows that a hybrid machine learning model (RF-SWOA) can predict potential seagrass habitats more accurately and effectively than traditional models. At the same time, it has been shown that the most important factors influencing the potential habitat of seagrass in the Hainan region were the distance from land (38.2%) and the depth of the ocean (25.9%). This paper provides a more accurate machine learning model approach for predicting the distribution of marine species, which can help develop seagrass conservation strategies to restore healthy seagrass ecosystems.

Accurate estimations of actual evapotranspiration (ETa) are fundamental for various environmental issues. Artificial Intelligence-based models are considered a promising alternative to the most common direct ETa estimation techniques and indirect methods by remote sensing (RS)-based surface energy balance models. Artificial Neural Networks (ANN) are proven to be suitable for predicting reference evapotranspiration and ETa based on RS data. The aim of this study is to develop a methodology based on ANNs for estimating daily ETa values using NDVI and land surface temperature, coupled with limited site-specific climatic variables at a large irrigation catchment. Two scenarios were implemented by the ANN model. Data from only the 38 days of satellite overpass dates was selected in Scenario-I, while the 769-day data included the satellite overpass dates and other days located between two satellite overpass acquisitions in Scenario-II. An irrigation scheme in the Mediterranean region of Turkiye was selected, and a total of 38 Landsat images, and local climatic data were used in 2021 and 2022. Results showed that R2 values in Scenario-I and II were acknowledgeably high for training (0.79 and 0.86), testing (0.75 and 0.81), and the entire dataset (0.76 and 0.84), respectively. Results of the new model in two scenarios showed acceptable agreement with ETa-METRIC values. The proposed ANN model demonstrated the potential of obtaining daily ETa using limited climatic data and RS imagery.

Land use is an embodiment of human socioeconomic activities and represents a bridge between these activities and natural systems. Through social activities, humans transform land use to promote social and economic development and improve production, living conditions, and eco-logical functions of land. Rural residential land represents a space for rural residents to reside in and exhibits spatial characteristics that evolve over time, which is proof of rural socioeconomic development. This paper observes rural residential land in 21 cities on the Grand Canal and analyses its spatial differentiation. Then, it explores the driving factors of this land using spatial grid analysis and the geographic detector model. Lastly, it proposes three different forms of rural residential land based on the results. The study found that: (1) the change of rural residential land in the northern part of the Grand Canal was more volatile than that in the southern part. The change of rural residential land from 1990 to 2020 conformed to the pattern of cultivated land - rural residential land - urban construction land; (2) Based on the driving factors of rural residen-tial land, the land is divided into one-dimensional cities, two-dimensional cities and three-dimensional cities. Circular, linear, and scattered cities of different sizes were affected by socioeconomic factors, transportation accessibility, and the natural environment, respectively; and (3) Finally, according to the spatial differentiation characteristics and the driving factors of rural residential land, the study proposes the construction of three types of villages through the strate-gies of constructing large-scale villages, relocating and reconstructing new villages, and con-structing high-quality villages, respectively. Enhancing the scientific planning of rural residential land and its efficiency can offer the protection of agricultural land and the integration of urban and rural areas in the new era.

This article explores the use of vegetation indices (VIs) in remote sensing for estimating standing wood volume and volume increments in forest ecosystems. The study investigates the correlations between various VIs and wood volume across different forest stand age classes, focusing on the effectiveness of commonly used indices such as Squared Ratio Simple Red Edge (SQSR) and Red-Edge Ratio Vegetation Index (RERVI), as well as other typical indicators including Enhanced Vegetation Index (EVI), Red-Edge EVI (RE-EVI), and Green Normalized Difference Vegetation Index (GNDVI). Additionally, the analysis considers a pair of indicators based on blue and near-infrared channels, resembling the Blue-normalized Difference Vegetation Index (BNDVI). The research reveals that quadratic and power-law models of SQSR and RERVI demonstrate higher correlations (>0.40) with wood volume, especially in younger forest stands (>0.80). Furthermore, the study highlights the potential of NDII and NDWI indices for estimating volume increments in certain classes of forest stands (0.70). However, correlations vary across different forest stand classes, suggesting the need for further investigation into the reliability of VIs for monitoring wood volume and volume increments in forest ecosystems. Overall, this research contributes to the understanding of the applicability of VIs in remote sensing for forest management and ecosystem monitoring.

Power grid reliability is crucial to supporting critical infrastructure, but monitoring and maintenance activities are expensive and sometimes dangerous. Remote sensing enables real time data monitoring and collection related to environmental and industrial processes, like the power grid system. Monitoring the power grid successfully involves diverse sources of data including that inherent to the power operation and ambient atmospheric weather data. Detection methods can identify anomalies like arcing, and climate data in particular is becoming increasingly important in order to maintain power supply. Gaussian processes (GPs) are a well-established Bayesian method for analyzing data. However, the computational complexity of GPs limits their scalability. This is a challenge when dealing with remote sensing datasets, where acquiring a significant amount of data is common. Alternatively, traditional machine learning methods perform quickly and accurately, but lack the generalizability innate to GPs. The focus of this review is burgeoning research that leverages Gaussian processes and machine learning in remote sensing applications.

Inland lake variations are considered sensitive indicators of global climate change. However, human activity is playing as a more and more important role in inland lake area variations. Therefore, it is critical to identify whether anthropogenic activity or natural event is playing as the dominant factor in inland lake surface area change. In this study, we proposed a Douglas-Peucker simplification algorithm and bend simplification algorithm combined method to locate major lake surface area disturbances; these disturbances were then characterized to extract the time series change features according to documented records; and the disturbances were finally classified into anthropogenic or natural. We took the nine lakes in Yunnan Province as test sites, a 31 years long (from 1987 to 2017) time series Landsat TM/OLI images and HJ-1A/1B used as data sources, the official records was used as references to aid the feature extraction and disturbance identification accuracy. Results of our method for both disturbance location and the disturbance identification could be concluded as follows: 1) The method can accurately locate the main lake changing events based on the time series lake surface area curve. The accuracy of this model for segmenting the lake area time series curves in our study area was 95.24%. 2) Our proposed method achieved an overall accuracy of 91.67%, with F-score of 94.67 for anthropogenic disturbances and F-score of 85.71 for natural disturbances. 3) According to our results, lakes in Yunnan Provence, China, have undergone extensive disturbances, and the human-induced disturbances occurred almost twice as often as natural disturbances, indicating intensified disturbances caused by human activities. This inland lake area disturbance identification method is expected to uncover whether a disturbance to inland lake area is human activity-induced or natural event.

Recent advancements in deep learning have spurred the development of numerous novel semantic segmentation models for land cover mapping, showcasing exceptional performance in delineating precise boundaries and producing highly accurate land cover maps. However, to date, no systematic literature review has comprehensively examined semantic segmentation models in the context of land cover mapping. This paper addresses this gap by synthesizing recent advancements in semantic segmentation models for land cover mapping from 2017 to 2023, drawing insights on trends, data sources, model structures, and performance metrics based on a review of 106 extracted articles. Our analysis identifies top journals in the field, including MDPI Remote Sensing, IEEE Journal of Selected Topics in Earth Science, and IEEE Transactions on Geoscience and Remote Sensing, IEEE Geoscience and Remote Sensing Letters, ISPRS Journal Of Photogrammetry And Remote Sensing as the leading journals. We find that research predominantly focuses on land cover, urban areas, precision agriculture, environment, coastal areas, and forests. Geographically, 35.29% of the study areas are located in China, followed by USA (11.76%), France (5.88 %), Spain (4%) and others. Sentinel-2, Sentinel-1, and Landsat satellites emerge as the most commonly used data sources. Benchmark datasets such as ISPRS Vaihingen &amp; Potsdam, LandCover.ai, DeepGlobe, and GID datasets are frequently employed. Model architectures predominantly utilize encoder-decoder, and hybrid convolutional neural network-based structures because of their impressive performances, with limited adoption of transformer-based architectures due to its computational complexity issue, and slow convergence speed. Lastly, this paper highlights existing key research gaps in the field to guide future research directions.

With the rapid development of satellite remote sensing technology, the volume of image datasets in many application areas is growing exponentially and the demand for Land-Cover and Land-Use change remote sensing data is growing rapidly. It is thus becoming hard to efficiently and intelligently retrieve the change information that users need from massive image databases. In this paper, content-based image retrieval is successfully applied to change detection and a content-based remote sensing image change information retrieval model is introduced. First, the construction of a new model framework for change information retrieval in a remote sensing database is described. Then, as the target content cannot be expressed by one kind of feature alone, a multiple-feature integrated retrieval model is proposed. Thirdly, an experimental prototype system that was set up to demonstrate the validity and practicability of the model is described. The proposed model is a new method of acquiring change detection information from remote sensing imagery and so can reduce the need for image pre-processing, deal with problems related toseasonal changes as well as other problems encountered in the field of change detection. Meanwhile, the new model has important implications for improving remote sensing image management and autonomous information retrieval.

Growing agricultural demands for the global population are unlocking the path to developing innovative solutions for efficient water management. Herein, an intelligent variable rate irrigation system (fuzzy-VRI) is proposed for rapid decision-making to achieve optimized irrigation in various delimited zones. The proposed system automatically creates irrigation maps for a center pivot irrigation system for a variable-rate application of water. Primary inputs are spatial imagery on remotely sensed soil moisture (SSM), soil adjusted vegetation index (SAVI), canopy temperature (CT), and nitrogen content (NI). To eliminate localized issues with soil characteristics, we used the crop nitrogen content map to provide a focused insight on issues related to water shortage. The system relates these inputs to set reference values for the rotation speed controllers and individual openings of each central pivot sprinkler valve. The results showed that the system can detect and characterize the spatial variability of the crop and further, the fuzzy logic solved the uncertainties of an irrigation system and defined a control model for high-precision irrigation. The proposed approach is validated through the comparison between the recommended irrigation and actual irrigation at two field sites, and the results showed that the developed approach gives an accurate estimation of irrigation with a reduction in the volume of irrigated water of up to 27% in some cases. Future research should implement the fuzzy-VRI real-time during field trials in order to quantify its effect on irrigation use, yield, and water use efficiency.

This paper proposed a new evaluation model based on analytic hierarchy process to quantitatively evaluate the capability of multi-satellite cooperative remote sensing observation. The analytic hierarchical process model is a combination of qualitative and quantitative analysis of systematic decision analysis method. According to the objective of the remote sensing cooperative observation mission, we decompose the complex problem into several levels and a number of factors, compare and calculate various factors in pairs, and obtain the combination weights of different schemes. The model can be used to evaluate the observation capability of resource satellites. Taking the optical remote sensing satellites such as China’s resource satellite series and GF-4 as examples, this paper verifies and evaluates the model for three typical tasks: point target observation, regional target observation and moving target continuous observation. The results show that the model can provide quantitative reference and model support for comprehensive evaluation of the collaborative observation capability of remote sensing satellites.

Volcanic activity essentially consists of the transfer of heat from the Earth’ interior to the surface. The precise signature of this heat transfer relates directly to the processes underway at and within a particular volcano and this can be observed, at a safe distance, remotely, using infrared sensors that are present on Earth-orbiting satellites. For over 50 years, scientists have perfected this art using sensors intended for other purposes, and they are now in a position to determine the particular sort of activity that characterizes different volcanoes. This review will describe the theoretical basis of the discipline and then discuss the sensors available for the task and the history of their use. Challenges and opportunities for future development in the discipline are then discussed.

Cities exposed their vulnerabilities during COVID-19 pandemic. Unprecedented policies restricted human activities but left an unique opportunity to quantify anthropogenic effects on urban air pollution. This study aimed to address the key questions of urban development behind the restrictions with the goal of supporting sustainable transition. Data from ground stations and Sentinel-5P satellite were used to assess the temporal and spatial anomalies of NO2. Beijing China was selected for a case study because this mega city maintained a “dynamic zero-COVID” policy with adjusted restrictions, allowing us better to track the effects. The time-series decomposition and prediction regression model were employed to estimate the normal NO2 levels in 2020. The anomalies between the observations and predictions as the deviation were identified due to the policy interventions and quantified different effects using spatial stratified heterogeneity statistics. The top three restrictions showing dominant effects were workplace closures, restricted public transport usage, and school closures, accounting for 54.8%, 52.3%, and 46.4% of NO2 anomalies, respectively; and they are directly linked to the mismatch of employment and housing (deter-mining the commuting patterns), educational inequality and the long-term unsolved road con-gestion. Promoting the transformation of urban spatial structure will effectively alleviate air pollution.

Large-scale farms are pivotal sites for the development of the agricultural industry, and the quality of the ecological environment is a significant factor affecting the growth of cereal crops. Consequently, assessing the ecological quality of large-scale farms is of great importance. This paper leverages the advantages of remote sensing imagery for long-term, quantitative, and dynamic monitoring of ecological quality over extensive areas. It develops an ecological assessment procedure suitable for agricultural regions based on an Improved Remote Sensing Ecological Index (IRSEI), which considers the coupling of ecosystem component elements. This procedure introduces a Pan-Salinity Index (PSI) tailored to the characteristics of soil salinization in farming areas and incorporates an ecological greenness index based on the Normalized Difference Vegetation Index (NDVI), an ecological humidity index derived from the K-T transform (WET), an ecological dryness index synthesized from the bare soil index and the built-up index (NDBSI), and an ecological heat index represented by the Land Surface Temperature (LST) calculated from atmospheric parameter models. These five indices are integrated into the ecological assessment system. The experimental results visually demonstrate the development and changes of ecological impact factors in the farm research area over the past decade, as well as the spatiotemporal variations in the quality of the farm's ecological environment. The findings indicate that between 2010 and 2019, the overall trend of IRSEI first declined, then rose, and subsequently experienced a slight decrease. Through differential analysis, regions and areas with declining ecological quality were identified, providing a data reference for the formulation and implementation of future ecological protection and management measures for the farm. The proposed IRSEI method offers a rapid and effective new monitoring approach for agricultural planting areas with a tendency towards soil salinization.

Remote sensing (RS) and Geographic Information Systems (GIS) provide significant opportunities for monitoring and managing natural resources across various temporal, spectral, and spatial resolutions. There is a critical need for natural resource managers to understand the expanding capabilities of image sources, analysis techniques, and in-situ validation methods. This article reviews a range of image analysis tools applicable to natural resource management, including agriculture, water, forests, soil, and natural hazards, and compares their functionalities. Our study highlights that Google Earth Engine (GEE) is favored for wide-area analysis due to its extensive coverage and free access. Global Mapper excels in 3D and light detection and ranging (LIDAR) data, environment for visualizing images (ENVI) specializes in multi- and hyperspectral image processing, ERDAS IMAGINE is optimal for radar data, and eCognition is used for object-based image analysis. The article emphasizes the importance of in-situ validation data, which provides essential ground truth information to calibrate and validate RS models, thereby enhancing accuracy. Understanding these tools and integrating them with in-situ validation techniques enables natural resource managers to improve their monitoring and decision-making processes, facilitating effective collaboration with RS researchers.

This study has been monitored for five years by Sentinel-2 satellite images, at different seasons of the year, of the fluctuations in the water level of the Gallocanta Lake (between the provinces of Teruel and Zaragoza, Aragón, Spain) considered a hypersaline and endorheic wetland, which has characteristics that make it unique in the geographical area in which it is located, as well as for the operation of the system. Rainfall in the area has a wide variation giving the maximums in the months of May and June and the minimums in January and February. There are considerable fluctuations in the water level from the almost total drying of the lagoon to the filling with a depth of approximately 3 meters.

In recent years, research on adversarial attack techniques for remote sensing object detection (RSOD) has made great progress. Still, most of the research nowadays is on end-to-end attacks, which mainly design adversarial perturbations based on the prediction information of the object detectors (ODs) to achieve the attack. These methods do not discover the common vulnerabilities of the ODs and thus the transferability is weak. Based on this, this paper proposes a foreground feature approximation (FFA) method to generate adversarial examples (AEs) that discover the common vulnerabilities of the ODs by changing the feature information carried by the image itself to implement the attack. Specifically, firstly, the high-quality predictions are filtered as attacked objects using the detector, after which a hybrid image without any target is made, and the hybrid foreground is created based on the attacked targets. The images' shallow features are extracted using the backbone network, and the features of the input foreground are approximated towards the hybrid foreground to implement the attack. In contrast, the model predictions are used to assist in realizing the attack. In addition, we have found the effectiveness of FFA for targeted attacks, and replacing the hybrid foreground with the targeted foreground can realize targeted attacks. Extensive experiments with seven rotating ODs on the RSOD datasets DOTA and UCAS-AOD show that FFA achieves both targetless and targeted attacks with a high success rate and transferability.

Snow-covered regions are the main source of reflection of incident shortwave radiation (ISR) on Earth’s surface. The deposition of light-absorbing particles (LAPs) on these regions increases the capacity of snow to absorb ISR and decreases surface snow albedo (SSA), which intensifies the radiative forcing leading to accelerated snowmelt and modifications of the hydrologic cycle. In this work we investigate changes in SSA and radiative forcing (RF) induced by LAPs in the Upper Aconcagua River Basin (Chilean central Andes) using remote sensing satellite data (MODIS), in-situ spectral SSA measurements, and the ISR (Chilean Solar Explorer platform) during the austral-winter months (May to August) for the 2004-2016 period. To estimate the changes in SSA and RF, we define two spectral ranges: i) an enclosed range (Ecr) between 841-876 nm, which isolates effects of Black-Carbon, an important LAP derived from anthropogenic activities, and ii) a broadband range (Bbr) between 300-2500 nm. Our results show that percent variations in SSA in the Ecr are higher than in the Bbr, regardless of the total amount of radiation received, which may be attributed to the presence of LAPs as these particles have a greater impact on SSA at wavelengths in the Ecr band than in the Bbr band.

In this work, we develop a software suite for studies of atmosphere – underlying SNOW- spaceborne optical receiver light TRANsmission calculations (SNOWTRAN) with applications for the solution of forward and inverse radiative transfer problems in polar regions. Assuming that aerosol load is extremely low, the proposed theory does not require the numerical procedures for the solution of the radiative transfer equation and is based on analytical equations for the spectral nadir reflectance and simple approximations for local optical properties of atmosphere and snow. The model developed is validated using EnMAP and PRISMA spaceborne imaging spectroscopy data close to the Concordia research station in Antarctica. A new fast technique for the determination of the snow grain size and assessment of the snowpack vertical inhomogeneity is then proposed and further demonstrated on EnMAP imagery over the Aviator Glacier and in the vicinity of the Concordia research station in Antarctica. The results revealed a large increase in precipitable water vapor at the Concordia research station in February 2023 linked to warming event, and a 4 times larger grain size at Aviator Glacier compared to Dome C.

Remote sensing imagery is of great significance for policy decisions, especially for disaster assessment and disaster relief. To ensure the privacy and inviolability of personal buildings, the information containing these buildings must be anonymized during the remote sensing mapping process. Traditional processing methods for these targets in remote sensing mapping are mainly based on manual retrieval and image editing tools, which are inefficient. Deep learning provides a new direction for target hiding. Although the image inpainting method based on deep learning is faster than the manual method, the cost of training calculation is a disadvantage. And the element-wise product operation used in the model increases the risk of vanished or exploded gradients. We propose a Residual Attention Target Hiding (RATH) model for remote sensing target hiding based on deep learning. RATH uses residual attention modules to replace gated convolutions, reducing parameters and mitigating gradient issues. The residual attention module preserves gated convolution performance but provides an adjustable kernel size. RATH retains gated convolutions for dynamic feature selection and balances model depth and width. Furthermore, this paper modifies the contextual attention layer by adjusting the fusion process to enlarge the fusion patch size. Finally, we extend the edge-guided function to preserve the original target information and confound viewers. Ablation studies on an open dataset prove RATH’s efficiency for image inpainting and target hiding. RATH achieves state-of-the-art results with lower complexity. And it has the highest similarity for edge-guided target hiding. RATH enables robust, efficient target hiding for privacy protection in remote sensing imagery while balancing performance and complexity. Experiments show RATH's superiority over existing methods in hiding arbitrary-shaped targets.

Deep Learning is an extremely important research topic in Earth Observation. Current use-cases range from semantic image segmentation, object detection to more common problems found in computer vision such as object identification. Earth Observation is an excellent source for different types of problems and data for Machine Learning in general and Deep Learning in particular. It can be argued that both Earth Observation and Deep Learning as fields of research will benefit greatly from this recent trend of research. In this paper we take several state of the art Deep Learning network topologies and provide a detailed analysis of their performance for semantic image segmentation for building footprint detection. The dataset used is comprised of high resolution images depicting urban scenes. We focused on single model performance on simple RGB images. In most situations several methods have been applied to increase the accuracy of prediction when using deep learning such as ensembling, alternating between optimisers during training and using pretrained weights to bootstrap new models. These methods although effective, are not indicative of single model performance. Instead, in this paper, we present different topology variations of these state of the art topologies and study how these variations effect both training convergence and out of sample, single model, performance.

Densely urbanized areas, with a low percentage of green vegetation, are highly exposed to Heat Waves (HW) which nowadays are increasing in terms of frequency and intensity also in the middle-latitude regions, due to ongoing Climate Change (CC). Their negative effects may combine with those of the UHI (Urban Heat Island), a local phenomenon where air temperatures in the compact built up cores of towns increase more than those in the surrounding rural areas, with significant impact on the quality of urban environment, on citizens health and energy consumption and transport, as it has occurred in the summer of 2003 on France and Italian central-northern areas. In this context this work aims at designing and developing a methodology based on aero-spatial remote sensing (EO) at medium-high resolution and most recent GIS techniques, for the extensive characterization of the urban fabric response to these climatic impacts related to the temperature within the general framework of supporting local and national strategies and policies of adaptation to CC. Due to its extension and variety of built-up typologies, the municipality of Rome was selected as test area for the methodology development and validation. First of all, we started by operating through photointerpretation of cartography at detailed scale (CTR 1: 5000) on a reference area consisting of a transect of about 5x20 km, extending from the downtown to the suburbs and including all the built-up classes of interest. The reference built-up vulnerability classes found inside the transect were then exploited as training areas to classify the entire territory of Rome municipality. To this end, the satellite EO HR (High Resolution) multispectral data, provided by the Landsat sensors were used within a on purpose developed "supervised" classification procedure, based on data mining and “object-classification” techniques. The classification results were then exploited for implementing a calibration method, based on a typical UHI temperature distribution, derived from MODIS satellite sensor LST (Land Surface Temperature) data of the summer 2003, to obtain an analytical expression of the vulnerability model, previously introduced on a semi-empirical basis.

With the rapid developments that have been made in computer vision and computer technology, semantic segmentation of high-resolution images has emerged as a mainstream and challenging task. The, segmentation of water areas remains a complex task due to the similar features between water areas or between water areas and other land objects. Meanwhile, since coastlines and riverbanks are typically presented in irregular shapes, it is difficult to obtain the categories of pixels at boundaries. This paper proposed the use of a Water-Land Boundary Attention Network (WLBANet) to improve the accuracy of pixels at boundaries between water and land. This network also reinforced the performance of contextual information extraction into distinguishing between water areas and other land objects. To prove the validity of this proposed network, WLBANet was performed on the Water Land Dataset (WLD), which is also by this paper, and which contains water areas and other land objects categories. The results demonstrates that the proposed method has significant effectiveness.

Automatic ice charting can not be achieved using only SAR modalities. It is fundamental to combine information from other remote sensors with different characteristics for more reliable sea ice characterization. In this paper, we employ principal feature analysis (PFA) to select significant information from multimodal remote sensing data. PFA is a simple yet very effective approach that can be applied to several types of data without loss of physical interpretability. Considering that different homogeneous regions require different types of information, we perform the selection patch-wise. Accordingly, by exploiting the spatial information, we increase the robustness and accuracy of PFA.

Given the context of global climate change, a worldwide increase in land surface temperature (LST) is anticipated, leading to the exacerbation and broadening of its impacts. This could jeopardize the environmental conditions in countries with a predominantly hot and harsh climate, such as Bahrain, one of the Cooperation Countries (GCC) nations. Conversely, Bahrain is currently experiencing significant population growth, leading to a surge in demand for land to accommodate the construction of additional residential developments. This circumstance allows investigation of the potential impact of land use and land cover alterations on the variation in Land Surface Temperature (LST). In order to accomplish this objective, a residential development project was executed within the timeframe spanning from 2013 to 2023. Four sets of Landsat 8 OLI/TIRS remote sensing datasets were selected, with each set corresponding to one of the four climate seasons. Each set consisted of two images: one capturing the study area before the commencement of the development process and the other depicting the study area after the completion of the development. The study area was analyzed by extracting the land surface temperature (LST), normalized difference vegetation index (NDVI), and normalized difference built-up index (NDBI) on various dates. Subsequently, correlation and regression analysis were employed to examine the interrelationships among these three variables. The findings demonstrated a notable rise in the mean land surface temperature throughout the spring and autumn seasons following the conclusion of land development activities. The findings indicate a positive and robust association between LST and NDBI across all seasons. Moreover, this relationship strengthened following the completion of development activities in the area. Conversely, there was a negative correlation between LST and NDVI prior to the region's development, which transformed into a positive relationship post-development. These results provide empirical support for the notion that small-scale residential developments contribute to a notable increase in LST, primarily driven by the expansion of impervious surfaces in built-up areas. The findings can potentially contribute to the formulation of localized adaptation strategies for small-scale residential development projects.

Remote sensing image registration plays an important role in military and civilian fields, such as natural disaster damage assessment, military damage assessment and ground targets identification, etc. However, due to the ground relief variations and imaging viewpoint changes, non-rigid geometric distortion occurs between remote sensing images with different viewpoint, which further increases the difficulty of remote sensing image registration. To address the problem, we propose a multi-viewpoint remote sensing image registration method which contains the following contributions. (i) A multiple features based finite mixture model is constructed for dealing with different types of image features. (ii) Three features are combined and substituted into the mixture model to form a feature complementation, i.e., the Euclidean distance and shape context are used to measure the similarity of geometric structure, and the SIFT (scale-invariant feature transform) distance which is endowed with the intensity information is used to measure the scale space extrema. (iii) To prevent the ill-posed problem, a geometric constraint term is introduced into the L2E-based energy function for better behaving the non-rigid transformation. We evaluated the performances of the proposed method by three series of remote sensing images obtained from the unmanned aerial vehicle (UAV) and Google Earth, and compared with five state-of-the-art methods where our method shows the best alignments in most cases.

The practical utility of remote sensing techniques relies on validating them with ground-truth data. Validation requires similar spatial-temporal scales for ground measurements and remote sensing resolution. Evapotranspiration (ET) estimates are commonly compared to weighing lysimeter data, which provide precise but localized measurements. To address this limitation, we propose using superconducting gravimeters (SG) to obtain ground-truth ET data at larger spatial scales. SG measure gravity acceleration with high resolution (tenths of nm/s2) within a few hundred meters. Similar to lysimeters, gravimeters provide direct estimates of water mass changes for determining ET without soil disturbance. To demonstrate the practical applicability of SG data, we conducted a case study in Buenos Aires Province, Argentina (-34.87, -58.14). We estimated cumulative ET values for 8-day and monthly intervals using gravity and precipitation data from the study site. Comparing these values with MODIS-based ET products (MOD16A2), we found a very good agreement at the monthly scale, with an RMSE of 32.6 mm/month (1.1 mm/day). This study represents progress in using SG for hydrogeological applications. The future development of lighter and smaller gravimeters is expected to further expand their use.

Target recognition and fine-grained ship classification in remote sensing face the challenges of high inter-class similarity and sample scarcity. A transfer fusion-based ship image harmonization algorithm is proposed to overcome these challenges. This algorithm designs a feature transfer fusion strategy based on the combination of region aware instantiation and attention mechanism. Implement adversarial learning through image harmony generator and discriminator module to generate realistic remote sensing ship harmony images. Furthermore, the do-main encoder and domain discriminator modules are responsible for extracting feature representations of foreground and background, and further aligning ship foreground with remote sensing ocean background features through feature discrimination. Compared with other advanced image conversion techniques, our algorithm delivers more realistic visuals, improving classification accuracy for six ship types by 3% and twelve types by 2.94%, outperforming Sim2RealNet. Finally, a mixed dataset containing data augmentation and harmonizing samples and real data was proposed for the fine-grained classification task of remote sensing ships. Evaluation experiments were conducted on 8 typical fine-grained classification algorithms, and the accuracy of fine-grained classification for all categories of ships was analyzed. The experimental results show that the mixed dataset proposed in this paper effectively alleviates the long tail problem in real datasets, and the proposed remote sensing ship data augmentation framework performs better than state-of-the-art data augmentation methods in fine-grained ship classification tasks.

In general, remote sensing has proven to be a powerful tool in the overall understanding of natural and anthropogenic phenomena. Satellites have become useful tools for tasks such as characterization, monitoring, and the continuous prospecting of natural resources. This research aims to analyze spatial dynamic and destructive on coral reefs area and correlation between live coral reduction and population on small islands. Landsat MSS, TM, ETM, and OLI-TIRS are used to spatial analyze of coral reef dynamics from 1972 to 2016. The image processing includes gap-filling, atmospheric correction, geometric correction, image composite (true color), water column correction, unsupervised classification, reclassification, accuracy assessment. The statistical analysis identifies the relationship between dynamic population data with a reduction of live coral, namely Principal Component Analysis (PCA) and Multiple Regression Analysis. The effect of the population shows a positive correlation with the reduction in the area of live coral, although it is significant. The fact is the practice of coral destruction on an island; it is usually not only caused or carried out by residents who live on the island but also carried out by other residents of different islands.

Estimating Forest growing stock volume (GSV) is crucial for forest growth and resource management, as it reflects forest productivity. National measurements are laborious and costly, however integrating satellite data such as optical, Synthetic Aperture Radar (SAR), and Airborne Laser Scanning (ALS) with National Forest Inventory (NFI) data and machine learning (ML) methods has transformed forest management. In this study, Random Forest (RF), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost) were used to predict GSV using Estonian NFI data, Sentinel-2 imagery, and ALS point cloud data. Four variable combinations were tested: CO1 (vegetation indices and LiDAR), CO2 (vegetation indices and individual band reflectance), CO3 (LiDAR and individual band reflectance), and CO4 (a combination of vegetation indices, individual band reflectance, and LiDAR). Across Estonia's geographical regions, RF consistently delivered the best performance. In the northwest (NW), RF achieved an R² of 0.63 and an RMSE of 125.39 m³/plot. In the southwest (SW), it achieved an R² of 0.73 and an RMSE of 128.86 m³/plot. In the northeast (NE), RF achieved an R² of 0.64 and an RMSE of 133.77 m³/plot, and an R² of 0.70 and an RMSE of 120.72 m³/plot was achieved in the southeast (SE). These results underscore RF's precision in predicting GSV across diverse environments, though refining variable selection and improving tree species data could further enhance accuracy.

When earthquake damage occurs, it is extremely important to quickly identify the presence or absence of such damage. In this study, we developed and evaluated a new remote sensing index to automatically determine "damage" by image analysis when damage greater than partial destruction of a house by an earthquake or tsunami occurs. The accuracy of the houses estimated as "damaged" was high and sufficient for the initial assessment of damage. The results of this research are expected to be utilized for more rapid damage assessment after a disaster.

Morphological parameters like cotton height, branches, Leaf Area Index and biomass are mainly affected by the vegetation water content (VWC). Periodical assessment of the VWC and crop parameters is required for timely management of the crop for maximizing yield. The study aimed at using both optical and microwave remotely sensed data to assess cotton crop condition based on the above mentioned traits. Vegetation indices (VI) derived from ground based measurements (5 narrow band and 2 broad band VIs) as well as satellite derived reflectance (2 broad band VIs) were assessed. Regression models were derived for estimating LAI, biomass and plant water content using the ground based indices and applied to the satellite derived spectral index (from LISS-III) map to estimate the respective parameters. HH and HV polarization from RISAT-1 were used to derive Radar Vegetation Index (RVI). The coefficient of determination of the model for estimating LAI, biomass and vegetation water content of cotton with optical vegetation index as input parameter were found to be 0.42, 0.51 and 0.52, respectively. The correlation between RVI and plant height, date of planting in terms of the age of the crop and vegetation water content were found to range between 0.4 to 0.6. The fresh biomass from RVI showed spatial variability from 100 gm-2 to 4000 gm-2 while the dry biomass map derived from NDVI showed spatial variability of 50 to 950 g m-2 for the study area. Plant water content in the district varied from 65 to 85%. The correlation between optical vegetation index and RVI was not significant. Hence a multiple linear regression model using both optical index (NDVI and LSWI) and SAR index (RVI) was developed to assess the LAI, biomass and plant water content. The model showed a R2 of 0.5 for LAI estimation but not significant for biomass and water content. This study show cased the use of combined optical and microwave (C band) remote sensing for cotton condition assessment.

Forest fires can occur suddenly and have significant environmental, economic, and social consequences. Timely and accurate evaluation and prediction of their progression, particularly the spread speed in difficult-to-access areas, are essential for emergency management departments to proactively implement prevention strategies and scientifically extinguish fires. This paper provides a comprehensive analysis of advanced technologies for predicting forest fire spread in China and globally. Incorporating remote sensing (RS) technology and forest fire science as the theoretical foundation, and utilizing the Wang Zhengfei forest fire spread model as the technical framework, this study constructs a forest fire spread model based on remote sensing interpretation. The model optimizes the method for acquiring parameters and enhances algorithm accuracy. By considering regional landforms (ridge lines, valley lines, slopes) and vegetation coverage, this paper establishes visual interpretation markers for identifying hotspots within the spread model. Utilizing statistical data from pixels within the fire line zone transforms the methodology for predicting forest fire spread speed, resulting in greater accuracy compared to conventional fixed-point predictions. Finally, the model was applied to the case of a forest fire in Mianning County, Sichuan Province, China and verified using high-time resolution mid-infrared image data and previous research findings. The results demonstrate that the predicted fire spread area from this RS-enabled model is consistent with both high-time resolution geostationary satellite data and previous research outcomes, indicating high reliability. This model can provide crucial fire spread information to relevant emergency departments, enabling effective preemptive measures and scientific firefighting strategies.

Evapotranspiration is a critical component of the hydrological cycle, and it has a decisive impact on the ecosystem balance in arid and semi-arid regions. The Yinchuan Plain, located in the Gobi of Northwest China, has a strong surface ET. In order to assess the ET pattern in this region, we obtained the ETa of Yinchuan Plain between 1987 and 2020 using the GEE platform. We employed the Surface Energy Balance Model (SEBAL), specifically geeSEBAL, to analyze the change pattern of ET over different seasons, years, and land types. The results show that: ① In spring, the daily ETa of the Yinchuan Plain is highest in the central lake wetland area, with a maximum value of 4.32 mm day-1. In summer, it is concentrated around the croplands and water bodies, with a maximum value of 6.90 mm day-1; In Autumn and winter, it is mainly concentrated around the water bodies and impervious areas, with maximum values of 3.93 and 1.56 mm day-1, respectively. ② From 1987 to 2020, the ET of the Yinchuan Plain showed an obvious upward and downward trend in some areas with significant land use changes, but the overall ET of the region remained relatively stable without dramatic fluctuations. ③ The evapotranspiration of different underlying land use types in the Yinchuan Plain region is as follows: water body&gt;cultivated land&gt;impervious&gt;grassland&gt;bare land. Our results showed that geeSEBAL is highly applicable in the Yinchuan Plain area. It allows for the accurate and detailed inversion of ET in the study area, which facilitates the study of regional hydrological cycle and water governance.

To ensure the security of highly sensitive remote sensing images (RSI) during their transmission, it is essential to implement effective content security protection methods. Generally, secure distribution schemes for remote sensing images often employ cryptographic techniques. However, sending encrypted data exposes communication behavior, which poses significant security risks to the distribution of remote sensing images. Therefore, this paper introduces deep information hiding to achieve secure distribution of remote sensing images, which can serve as an effective alternative in certain specific scenarios. Specifically, the Deep Information Hiding for RSI Distribution (hereinafter referred to as DIH4RSID) based on encoder-decoder network architecture with Parallel Attention Mechanisms (PAM) by adversarial training was proposed. Our model is constructed with four main components: a preprocessing network (PN), an embedding network (EN), a revealing network (RN) and a discriminating network (DN). The PN module is primarily based on Inception to capture more details of RSI and targets of different scales. The PAM module obtains features in two spatial directions to realize feature enhancement and context information integration. The experimental results indicate that our proposed algorithm achieves relatively higher visual quality and secure level compared to related methods. Additionally, after extracting the concealed content from hidden images, the average classification accuracy is unaffected.

In data-scarce regions, prudent planning and precise decision-making for sustainable development especially in agriculture remains a challenging task due to the lack of correct information. Remotely sensed satellite images provide a powerful source for assessing land use land cover (LULC) classes and crop identification. Applying Remote Sensing (RS) in conjunction with the Geographical Information System (GIS) and modern tools/ algorithms of artificial intelligence (AI) and deep learning has been proven effective for strategic planning and integrated resources management. The (this)study was conducted in the canal command area of the Lower Chenab Canal system in Punjab, Pakistan. Crop features/ classes were assessed using the Normalized Difference Vegetation Index (NDVI) algorithm. The MODIS (Moderate Resolution Imaging Spectroradiometer) 250 m and Landsat 5 TM (thematic mapper) images were deployed for NDVI time-series analysis with unsupervised classification technique to get LULC classes that helped to discern cropping pattern, crop rotation, and the area of specific crops, which were then used as a key input for agricultural mechanization planning and resources management. The accuracy of the LULC map was 78%, assessed by the error matrix approach. Limitations of high-resolution RS data availability and the accuracy of the results are the concerns observed in this study that could be managed by the availability of good quality local sources and advanced techniques of processing, which will make it more useful and applicable for regional agriculture and environmental management.

Machine learning (ML) is a subdivision of artificial intelligence in which the machine learns from machine-readable data and information. It uses data, learns the pattern and predicts the new outcomes. Its popularity is growing because it helps to understand the trend and provides a solution that can be either a model or a product. Applications of ML algorithms have increased drastically in G.I.S. and remote sensing in recent years. It has a broad range of applications, from developing energy-based models to assessing soil liquefaction to creating a relation between air quality and mortality. Here, in this paper, we discuss the most popular supervised ML models (classification and regression) in G.I.S. and remote sensing. The motivation for writing this paper is that ML models produce higher accuracy than traditional parametric classifiers, especially for complex data with many predictor variables. This paper provides a general overview of some popular supervised non-parametric ML models that can be used in most of the G.I.S. and remote sensing-based projects. We discuss classification (Naïve Bayes (NB), Support Vector Machine (SVM), Random Forest (RF), Decision Trees (DT)) and regression models (Random Forest (RF), Support Vector Machine (SVM), Linear and Non-Linear) here. Therefore, the article can be a guide to those interested in using ML models in their G.I.S. and remote sensing-based projects

In this review, we summarize the current state-of-the-art in the utilization of close-range sensing in forest monitoring. We include technologies, such as terrestrial and mobile laser scanning as well as unmanned aerial vehicles, which are mainly used for collecting detailed information from single trees, forest patches or small forested landscapes. Based on the current published scientific literature, the capacity to characterize changes in forest ecosystems using close-range sensing has clearly been recognized. Forest growth has been the most investigated cause for changes and terrestrial laser scanner the most applied sensor for capturing forest structural changes. Unmanned aerial vehicles, on the other hand, have been used to acquire aerial imagery for detecting tree height growth and monitoring forest health. Mobile laser scanning has not yet been used in forest change monitoring except for a few early investigations. Considering the length of the forest growth process, investigated time spans have been rather short, less than 10 years. In addition, data from only two time points have been used in many of the studies, which has further been limiting the capability of understanding dynamics related to forest growth. In general, method development and quantification of changes have been the main interests so far regardless of the driver of change. This shows that the close-range remote sensing community has just started to explore the time dimension and its possibilities for forest characterization.

Passive microwave measurements have been available on satellites dating back to the 1970s on research satellites flown by the National Aeronautics and Space Administration (NASA). Since then, several other sensors have been flown to retrieve hydrological products for both operational weather applications (e.g., the Special Sensor Microwave/Imager–SSM/I; the Advanced Microwave Sounding Unit–AMSU) and climate applications (e.g., the Advanced Microwave Scanning Radiometer–AMSR; the Tropical Rainfall Measurement Mission Microwave Imager–TMI; the Global Precipitation Mission Microwave Imager–GMI). Here the focus is on measurements from the AMSU-A, AMSU-B and Microwave Humidity Sounder (MHS). These sensors have been in operation since 1998 with the launch of NOAA-15, and are also on board NOAA-16, -17, -18, -19 and the MetOp-A and -B satellites. A data set called the “Hydrological Bundle” is a Climate Data Record (CDR) that utilizes brightness temperatures from Fundamental CDRs to generate Thematic CDRs (TCDR). The TCDR’s include: Total Precipitable Water (TPW), Cloud Liquid Water (CLW), Sea-Ice concentration (SIC), Land surface temperature (LST), Land surface emissivity (LSE) for 23, 31, 50 GHz, rain rate (RR), snow cover (SC), ice water path (IWP), and snow water equivalent (SWE). The TCDR’s are shown to be in general good agreement with similar products from other sources such as the Global Precipitation Climatology Project (GPCP) and the Modern-Era Retrospective Analysis for Research and Applications (MERRA-2). Because of the careful intercalibration of the FCDR’s, little bias is found among the different TCDR’s produced from individual NOAA and MetOp satellites, except for normal diurnal cycle differences.

With the development of remote sensing satellite technology for Earth observation, remote sensing stereo images have been used for three-dimensional reconstruction in various fields, such as urban planning and construction. However, remote sensing images often include noise, occluded regions, weakly textured areas and repeated textures, which can lead to reduced accuracy in stereo matching and affect the quality of the 3D reconstruction results. To reduce the impact of complex scenes in remote sensing images on stereo matching and to ensure both speed and accuracy, we propose a new end-to-end stereo matching network based on convolutional neural networks (CNNs). The proposed stereo matching network can learn features at different scales from the original images and construct cost volumes with varying scales to obtain richer scale information. Additionally, when constructing the cost volume, we introduce negative disparity to adapt to the common occurrence of both negative and nonnegative disparities in remote sensing stereo image pairs. For cost aggregation, we employ a 3D convolution-based encoder-decoder structure that allows the network to adaptively aggregate information. Before feature aggregation, we also introduce an attention module to retain more valuable feature information, enhance feature representation, and obtain a higher-quality disparity map. By training on the publicly available US3D dataset, we obtain the accuracy that 1.115 pixel in end-point error (EPE) and 5.32% in the error pixel ratio (D1) on the test dataset, and the inference speed is 92 ms. Comparing our model with existing state-of-the-art models, we achieve higher accuracy, and the network is beneficial for the three-dimensional reconstruction of remote sensing images.

A remote sensing-based evapotranspiration (ET) study was conducted over the Central Arizona Irrigation and Drainage District (CAIDD), an Arizona agricultural region. ET was assessed means for 137 wheat plots, 183 cotton plots, and 225 alfalfa plots. The remote sensing ET models were the Satellite-Based Energy Balance for Mapping Evapotranspiration with Internalized Calibration (METRIC), the Two Source Energy Balance (TSEB), and Vegetation Index ET for the US Southwest (VISW). Remote sensing data were principally Landsat 5, supplemented by Landsat 7, MODIS Terra, MODIS Aqua, and ASTER. The models produced similar daily ET for wheat, with 6–8 mm/d mid-season. For cotton and alfalfa daily ET showed greater differences, where TSEB produced largest daily ET, METRIC the least, and VISW in the midrange. Modeled cotton ET at mid-season ranged from 9.5 mm/d (TSEB), to 8 mm/d (VISW), and 6 mm/d (METRIC). For alfalfa ET, values at peak cover ranged from 8 mm/d (TSEB), 6 mm/d (VISW), and 5 mm/d (METRIC). Model bias ranged −10% to +18%. Relative to potential ET, FAO-56 ET, and USDA-SW gravimetric-ET, model variability ranged from negligible to 35% of annual crop water use. Model averaging was found a useful way to consider and reconcile all ET estimates.

The development of unmanned satellite space technology is increasingly willing, the emergence of medium resolution satellites with sensitivity and spectral variants such as Landsat is very effective in observing environmental changes, while the purpose of this study is to monitor the development of built-in land using image transformation techniques, estimating built-in land changes. The research method uses the NDVI image transformation technique, NDBI and Built Up Index, with Landsat satellite image data obtained from USGS. Accuracy sampling is done by purposive sampling with confusion matrix accuracy test technique. The research results were found. developed land for the period 2004 - 2010 with a percentage of 19.25%, for stages 2010 - 2018 with a percentage of 30.25%. The land development was built based on the area of ​​the highest sub-district in the Kubung area in the early period with a percentage of 7.20% then in the second period with a percentage of 32.23%. The quality of the accuracy of the results of image analysis using confusion matrix technique with an image accuracy level in a field sample of 185 with an image accuracy of 86.04%.

In California, water is a perennial concern. As competition for water resources increases due to growth in population, California’s tree nut farmers are committed to improving the efficiency of water used for food production. There is an imminent need to have reliable methods that provide information about the temporal and spatial variability of crop water requirements, which allow farmers to make irrigation decisions at field scale. This study focuses on estimating the actual evapotranspiration and crop coefficients of an almond and pistachio orchard located in Central Valley (California) during an entire growing season by combining a simple crop evapotranspiration model with remote sensing data. A dataset of the vegetation index NDVI derived from Landsat-8 was used to facilitate the estimation of the basal crop coefficient (Kcb), or potential crop water use. The soil water evaporation coefficient (Ke) was measured from microlysimeters. The water stress coefficient (Ks) was derived from airborne remotely sensed canopy thermal-based methods, using seasonal regressions between the crop water stress index (CWSI) and stem water potential (Ystem). These regressions were statistically-significant for both crops, indicating clear seasonal differences in pistachios, but not in almonds. In almonds, the estimated maximum Kcb values ranged between 1.05 to 0.90, while for pistachios, it ranged between 0.89 to 0.80. The model indicated a difference of 97 mm in transpiration over the season between both crops. Soil evaporation accounted for an average of 16% and 13% of the total actual evapotranspiration for almonds and pistachios, respectively. Verification of the model-based daily crop evapotranspiration estimates was done using eddy-covariance and surface renewal data collected in the same orchards, yielding an r² >= 0.7 and average root mean square errors (RMSE) of 0.74 and 0.91 mm day^-1 for almond and pistachio, respectively. It is concluded that the combination of crop evapotranspiration models with remotely-sensed data is helpful for upscaling irrigation information from plant to field scale and thus may be used by farmers for making day-to-day irrigation management decisions.

In the context of climate change, the need for stakeholders to contribute to achieving SDG2 is no longer in doubt especially in sub-Saharan Africa. In this study of the landscape within 10 km of the Donomadé model farm, southeastern Togo, we sought to assess vegetation health in ecosystems and agrosystems, including their capacity to produce biomass for agroecological practices. Sentinel-2 sensor data from 2015, 2017, 2020, and 2022 were preprocessed and used to calculate normalized vegetation fire ratio index (NBR), vegetation fire severity index (dNBR), and CASA-SEBAL models. From these different analyses, it was found that vegetation stress increased across the landscape depending on the year of the time series. We estimated that 9952.215 ha, 10,397.43 ha, and 9854.90 ha were highly stressed in 2015, 2017, and 2020, respectively. Analysis of the level of interannual severity revealed the existence of highly photosynthetic areas which had experienced stress. These areas, which were likely to have been subjected to agricultural practices, were estimated to be 8704.871 ha (dNBR2017–2015), 8253.17 ha (dNBR2020–2017), and 7513.93 ha (dNBR2022–2020). In 2022, the total available biomass estimated by remote sensing for was 3,741,715 ± 119.26 kgC/ha/y. The annual average was 3401.55 ± 119.26 kgC/ha/y. In contrast, the total area of healthy vegetation was estimated to be 4594.43 ha, 4301.30 ha, and 4320.85 ha, in 2015, 2017, and 2022, respectively. The acceptance threshold of the net primary productivity (NPP) of the study area was 96%. The coefficient of skewness (0.81 ± 0.073) indicated a mosaic landscape. Productive and functional ecosystem components were present, but these were highly dispersed. These findings suggest a great opportunity to promote agroecological practices. Mulching may be an excellent technique for enhancing overall ecosystem services as targeted by the SDGs, by means of reconversion of plant biomass consumed by vegetation fires or slash-and-burn agricultural practices.

Semantic segmentation of high-resolution remote sensing images provides detailed and precise feature information, playing a pivotal role in decision-making and analysis in sectors such as water management, agriculture, military, and environmental protection. However, most methods merely combine features from various branches directly, without a mechanism for spatial location feature screening, and treat all extracted features as equally important. To overcome these limitations, we introduce a novel spatially adaptive interaction network (SAINet) for dynamic interaction across different features in remote sensing semantic segmentation task. Specifically, we propose a spatial refined module that leverages local context information to filter spatial locations and extract salient regions. Following this, we introduce an innovative spatial interaction module that uses a spatial adaptive modulation mechanism to dynamically select and allocate spatial position weights. This facilitates interaction between local salient areas and global information, allowing the network to focus more on relevant regions. This flexible approach enables the network to capture more informative features, thereby enhancing segmentation accuracy. Experiments conducted on the DeepGlobe, Vaihingen, and Potsdam public datasets confirm the effectiveness and capability of SAINet. Our code and models will be publicly available

It is very difficult to accurately divide farmland and woodland in Gaofen 2 (GF-2) remote sensing image, because their single plant coverage is very small, and their spectra are very similar. The ratio of spatial resolution and one plant’s coverage area must be fully taken into account when designing the Convolutional Neural Network structure for extracting them from GF-2 image. We establish a Convolutional Encode Neural Networks model (CENN), The first layer has two sets of convolution kernels to learn the characteristics of farmland and woodland respectively, while the second layer is the encoder to encode the characteristics by transfer function, which can map the results to the corresponding category number. In the training stage, samples of farmland, woodland, and other categories are categorically used to train CENN, as soon as training is accomplished, CENN would acquire enough ability to accurately extract farmland and woodland from remote sensing images. The final extraction result is obtained by implementing per-pixel segmentation of images used to train the CENN. CENN is compared and analyzed with others such as Deep Belief Network (DBN), Full Convolutional Network (FCN), Deeplab Model. The results of experiments show that CENN can more accurately mine the characteristics of farmland and woodland, and it achieves its goal of extracting farmland and woodland with high precision from GF-2 images.

Wetlands are recognized as one of the world’s most valuable natural resources. With the increasing world population, human demands on wetland resources for agricultural expansion and urban development continue to increase. In addition, global climate change has pronounced impacts on wetland ecosystems through alterations in hydrological regimes. To better manage and conserve wetland resources, we need to know the distribution and extent of wetlands and monitor their dynamic changes. Wetland maps and inventories can provide crucial information for wetland conservation, restoration, and management. Geographic Information System (GIS) and remote sensing technologies have proven to be useful for mapping and monitoring wetland resources. Recent advances in geospatial technologies have greatly increased the availability of remotely sensed imagery with better and finer spatial, temporal, and spectral resolution. This chapter presents an introduction to the uses of GIS and remote sensing technologies for wetland mapping and monitoring. A case study is presented to demonstrate the use of high-resolution light detection and ranging (LiDAR) data and aerial photographs for mapping prairie potholes and surface hydrologic flow pathways.

Existing methods enhance mid-low resolution remote sensing ship detection by feeding super-resolved images to the detectors. Although these methods marginally improve the detection accuracy, the correlation between image super-resolution (SR) and ship detection is under-exploited. In this paper, we propose a simple but effective ship detection method called ShipSR-Det, in which both the output image and the intermediate features of the SR module are fed to the detection module. Using the super-resolved feature representation, the potential benefit introduced by image SR can be fully used for ship detection. We apply our method to the SSD and Faster-RCNN detectors and develop ShipSR-SSD and ShipSR-Faster-RCNN, respectively. Extensive ablation studies validate the effectiveness and generality of our method. Moreover, we compare ShipSR-Faster-RCNN with several state-of-the-art ship detection methods. Comparative results on the HRSC2016, DOTA and NWPU VHR-10 datasets demonstrate the superior performance of our proposed method.

This paper investigates the characteristics and impact of a major Saharan dust storm during June 14^th -19^th 2020 to atmospheric radiative and thermodynamics properties over the Atlantic Ocean. The event witnessed the highest ever aerosol optical depth (close to 2 during the peak of the storm) for June since 2002. The satellites and high-resolution model reanalysis products well captured the origin, spread and the effects of the dust storm. The Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) profiles, lower angstrom exponent values (~ 0.12) and higher aerosol index value (> 4) tracked the presence of elevated dust. It was found that the dust AOD was as much as 250-300% higher than their climatology resulting in an atmospheric radiative forcing ~200% larger. As a result, elevated warming ( 8-16 %) was observed, followed by a drop in relative humidity(2-4%) in the atmospheric column, as evidenced by both in-situ and satellite measurements. Quantifications such as these for extreme dust events provide significant insights that may help in understanding their climate effects, including improvements to dust simulations using chemistry-climate models

Malaria is a disease spread by female mosquitos of the Anopheles genus. It is acutely prevalent in Sub-Saharan Africa, where 90% of malaria deaths occur annually. One Sub-Saharan African country historically impacted by malaria is Ethiopia. In the past twenty years, malaria prevalence has decreased throughout Sub-Saharan Africa; yet, anthropogenic environmental changes are changing the landscape of malaria. Scholarly literature has cited a positive relationship between hydroelectric dams and malaria in Sub-Saharan Africa. Ethiopia is currently expanding their hydroelectric infrastructure. The Gilgel Gibe III Dam is located on the Omo River in Southwestern Ethiopia. It began generating electricity in 2015 and its reservoir has a capacity of 14,700 million m3 of water. This research utilized Geographic Information Systems and Remote Sensing to identify populations at an increased risk of malaria due to Gilgel Gibe III Dam. Two different techniques were employed: the proximity approach and the remote sensing approach. The proximity approach was based on distance from the reservoir. It identified all populations living within three kilometers of the reservoir as being at an increased risk. The remote sensing approach evaluated the slope, elevation, water content, and land surface temperature of the study area to create a mosquito breeding habitat risk map. Then, populations living within three kilometers of the two main High-Risk areas were identified. This study suggests that mosquito breeding habitat risk is not equally distributed throughout the Gilgel Gibe III Reservoir. This causes certain populations to be at a heightened risk of malaria.

Oil spills are adverse events that may be very harmful to ecosystems and food chain. In particular, large sea oil spills are very dramatic occurrence often affecting sea and coastal areas. Therefore the sustainability of oil rig infrastructures and oil transportation via oil tankers are linked to law enforcement based on proper monitoring techniques which are also fundamental to mitigate the impact of such pollution. Within this context, in this study a meaningful showcase is analyzed using remotely sensed measurements collected by the Synthetic Aperture Radar (SAR) operated by the COSMO-SkyMed (CSK) constellation. The showcase presented refers to the Deepwater Horizon (DWH) oil incident that occurred in the Gulf of Mexico in 2010. It is one of the world's largest incidental oil pollution event that affected a sea area larger than 10,000 km². In this study we exploit, for the first time, dual co-polarization SAR data collected by the Italian CSK X-band SAR constellation showing the key benefits of HH-VV SAR measurements in observing such a huge oil pollution event, especially in terms of the very dense revisit time offered by the CSK constellation.

Land cover segmentation, a fundamental task within the domain of remote sensing, boasts a broad spectrum of application potential. In this article, we focus on the land cover segmentation tasks and complete the following research work: Firstly, to address the issues of uneven distribution of foreground and background and significant differences in target scales in remote sensing images, we propose a decoder called MDCFD based on multi-dilation rate convolution fusion. The decoder utilizes dilated convolution to expand the receptive field, enhancing the model's ability to capture global features and thus improving the model's ability to distinguish between foreground and background. Meanwhile, we design a multi-dilation rate convolution fusion module (MDCFM), which fuses the outputs of different dilation rate convolution layers. Secondly, aiming at the problems of diverse scenes, significant differences between categories, and many background interferences in remote sensing images, we propose a hybrid attention module called LKSHAM based on large kernel convolution. This module combines spatial attention and channel attention mechanisms and combines the two attention modules in series. By introducing large kernel convolution, the model's ability to extract contextual information is improved. At the same time, we adopt a strategy of decomposing large kernel convolution into multiple depthwise convolutions to reduce computational complexity. The improved network models designed by this paper can achieve an improvement of over 1.1% in the mIoU metric on segmentation tasks on the Potsdam and Vaihingen datasets.

Remote sensing methods have the potential to improve lake water quality monitoring and deci-sion-making in water management. This reviews introduces novel findings in the field of opti-cally active water quality parameters using remote sensing. It summarizes existing retrieval methods (analytical, semi-analytical, empirical, semi-empirical, and artificial intelli-gence/machine learning (AI/ML)), examines measurement methods used to determine concen-tration of specific water quality parameters, summarizes satellite systems that enable temporal data for understanding the state of the lake with focus on water quality parameters, and pro-poses enhancements for future research of lake water quality using remote sensing. As part of this review, eight optically active biological and physical water quality parameters were ana-lyzed, including chlorophyll-α (chl-α), transparency (Secchi disk depth (SDD)), colored dis-solved organic matters (CDOM), turbidity (TUR), electrical conductivity (EC), surface salinity (SS), total suspended matter (TSM), and water temperature (WT). The research proposes a shift from point-based data representation to a more reliable raster representation and encourages optimizing grid selection for in situ measurements by combining hydrodynamic model with re-mote sensing methods. This review presents a comprehensive summary of the bands, band combinations, and band equations per sensor for eight optically active water quality parameters as listed in Tables A1-A8. The review’s findings indicate that use of remotely sensed data is an effective method for estimating water quality parameters in lakes, with a significant increase in global utilization. The review highlights potential solutions and limitations to the challenges of remote sensing water quality determination in lakes.

The rapid advancements in satellite technology have led to a significant increase in high-resolution remote sensing (RS) images, necessitating advanced processing methods. Additionally, a patent analysis revealed a significant increase in deep learning and machine learning applications in remote sensing, highlighting the growing importance of these technologies. Therefore, this paper introduces the Kolmogorov-Arnold Network (KAN) model to remote sensing, aiming to enhance efficiency and performance in RS applications. We conducted several experiments to validate KAN's applicability, starting with the EuroSAT dataset, where we combined the KAN layer with multiple pretrained CNN models. The optimal performance was achieved with ConvNeXt, leading to the development of the KonvNeXt model. KonvNeXt was evaluated on the Optimal-31, AID, and Merced datasets for validation, and it achieved accuracies of 90.59%, 94.1%, and 98.1%, respectively. The model also showed fast processing speed, with the Optimal-31 and Merced datasets completed in 107.63 seconds each, while the bigger and more complicated AID dataset took 545.91 seconds. This result is meaningful since it achieved faster speeds and comparable accuracy compared to the existing study which utilized VIT and proved KonvNeXt's applicability for remote sensing classification tasks. Furthermore, we investigated the model's interpretability by utilizing Occlusion Sensitivity and by displaying the influential regions, it validated its potential use in a variety of domains including medical imaging and weather forecasting. This paper is meaningful in that it is the first use of KAN in remote sensing classification, proving its adaptability and efficiency.

Natural springs, recognized as biodiversity hotspots and keystone ecosystems, exert positive ecological influences beyond their immediate extent, particularly in dryland environments. The water feeding these springs, largely governed by natural climatic conditions, is susceptible to anthropogenic impacts. The objective of this study was to determine the factors that cause fluctuations in water availability to springs of the hyper-arid Arava Valley (Israel/Jordan). Using the Standard Precipitation Index, we statistically classified the historical record of yearly rainfall for the past four decades into clusters of dry and wet sub-periods. We assessed changes in vegetation cover around the springs using the Landsat-derived Normalized Difference Vegetation Index (NDVI) for each sub-period. To assess the anthropogenic effects, we examined the correlations between vegetation cover, water extraction from the aquifer, and the status of adjacent agricultural plots that share a hydrological connection with the springs. Our findings reveal fluctuations between wet and dry sub-periods over the last four decades. We observed high responsiveness of vegetation cover around the springs to these fluctuating sub-periods. Of the 25 studied springs, 12 were directly influenced by anthropogenic factors — seven experienced a decline in vegetation which we attributed to water extraction from the aquifers, while vegetation increase in five springs was attributed to water seepage from agricultural areas upstream. In conclusion, addressing vital habitats such as natural springs in arid drylands requires a holistic approach that integrates long-term climatic, ecological, and anthropogenic observations.

The analysis of the land use dynamics of the Lac Télé Community Reserve (RCLT) using Landsat Thematic Mapper (TM) and (Enhance Thematic Mapper) ETM+ images highlight significant changes in the vegetation cover from 1980 to 2000 and 2018. Thus, the rate of forest area decreased by 21.41% for the entire LTCR in favor of savannahs which increased by 15.23%. The conversion of this forest area to savannah due to the practice of slash and burn agriculture facilitates the opening up of the forest area and contributes to greatly degrading the spawning grounds of fish species from the Likouala aux herbes river. For the mapping of fishing activity in general and the ecological characterization of the 151 identified spawning grounds in particular; the respective mean values of the physical and chemical water parameters; temperature (28.13°C), pH (4.23) and depth (3.34) did not vary significantly from one selected village to another between July and September 2019. The fish diversity unregistered during the study, in the 07 pilot villages would be due to the diversity of the microhabitats noted in the villages of the LTCR, especially from the villages; Botongo, Mossengue and Bouanela where the indices of ichthyological diversity were the highest.

Rapid and accurate detection of road cracks is of great significance for road health monitoring, but currently this work is mainly completed through manual site surveys. Low-altitude UAV remote sensing can obtain images with centimeter or even subcentimeter ground resolution, which provides a new efficient and economical approach for rapid crack detection. Nevertheless, crack detection networks face challenges such as edge blurring and misidentification due to the heterogeneity of road cracks and the complexity of the background. To address these issues, we propose a real-time edge reconstruction crack detection network (ERNet) which adopts multi-level information aggregation to reconstruct crack edges and improve the accuracy of segmentation between the target and background. To capture global dependencies across spatial and channel levels, we propose an efficient bilateral decomposed convolutional attention module (BDAM) that combines depth separable convolution and dilated convolution to capture global dependencies across spatial and channel levels. To enhance the accuracy of crack detection, we use a coordinate-based fusion module that integrates spatial, semantic, and edge reconstruction information. In addition, we propose an automatic measurement of crack information for extracting the crack trunk and its corresponding length and width. Experimental results demonstrate that our network achieves the best balance between accuracy and inference speed.

Detecting rotational objects in remote sensing imagery is a significant challenge. These images typically encompass a broad field of view, featuring diverse and intricate backgrounds, with ground objects of various sizes densely scattered. As a result, identifying objects of interest within these images is a daunting task. While the integration of Convolutional Neural Networks (CNN) and Transformer networks leads to some advancements in rotational object detection, there is still room for improvement, particularly in enhancing the extraction and utilization of information related to smaller objects. To address this, our paper presents a multi-scale feature fusion module and a global feature context aggregation module. Initially, we fuse original, shallow, and deep features to reduce the loss of shallow feature information, thereby improving the detection performance of small objects in complex backgrounds. Subsequently, we compute the correlation of contextual information within feature maps to extract valuable insights. We name the newly proposed model the "Multiscale Feature Context Aggregation Module" (MFCA). We evaluate our proposed methodology on three challenging remote sensing datasets: DIOR-R, HRSC, and MAR20. Comprehensive experimental results show that our approach surpasses baseline models by 2.07\% mAP, 1.02\% mAP, and 1.98\% mAP on the DIOR-R, HRSC2016, and MAR20 datasets, respectively.

The assessment of the number of people exposed to natural hazards, especially in countries with strong urban growth, is difficult to be updated at the same rate as land use develops. This paper presents a remote sensing based procedure for quick updating the assessment of the population exposed to natural hazards. A relationship between satellite nightlights intensity and urbanization density from global available cartography is first assessed when all data are available. This can be used to extrapolate urbanization data at different time steps, updating exposure each time new nightlights intensity maps are available. As reliability test for the proposed methodology, the number of people exposed to riverine flood in Italy is assessed, deriving a probabilistic relationship between DMSP nightlights intensity and urbanization density from GUF database for the year 2011. People exposed to riverine flood are assessed crossing the population distributed on the derived urbanization density with flood hazard zones provided by ISPRA. The validation on reliable exposures derived from ISTAT data shows good agreement. The possibility to update exposure maps with higher refresh rate makes this approach particularly suitable for applications in developing countries, where exposure may change at sub-yearly scale.

Globally, rice is one of the most important staple food crops. The most significant metric for evaluating the rice growth and productivity is the Leaf Area Index (LAI), which can be effectively monitored using remote sensing data. Hyperspectral remote sensing provides contiguous bands at narrow wavelengths for mapping LAI at various rice phenological stages and it is functionally related to canopy spectral reflectance. Hyperspectral signatures for different phases of rice crop growth was recorded using Airborne Visible Near-Infrared Imaging Spectrometer - Next Generation (AVIRIS-NG) along with corresponding ground based observations. Ground based hyperspectral canopy spectral reflectance measurements was recorded with FieldSpec 3 Hi-Res spectroradiometer (ASD Inc., USA; spectral range: 350-2500 nm) and LAI data from 132 farmer’s fields in Southern India. Among 29 hyperspectral vegetation indices tested, eight were found promising for mapping rice LAI at various phenological stages. Among all the growth stages, elongation stage was the most accurately estimated using vegetation indices that exhibited significant correlation with the airborne hyperspectral reflectance. The validation of hyperspectral vegetation indices revealed that the best fit model for estimating rice LAI was mND705 (red-edge, blue and NIR bands) at seedling and elongation, SAVI (red and NIR bands) at tillering and WDRVI (red and NIR bands) at booting stage.

The extent of single- and multi-cropping systems in any region, and potential changes to it, have consequences on food and resource use, raising important policy questions. However, addressing these questions is limited by a lack of reliable data on multi-cropping practices at a high spatial resolution, especially in areas with high crop diversity. In this paper, we describe a relatively low-cost and scalable method to identify double-cropping at the field-scale using satellite (Landsat) imagery. The process combines machine learning methods with expert labeling. We demonstrate the process by measuring double-cropping extent in a portion of Washington State in the Pacific Northwest United States--- a region with significant production of more than 60 distinct types of crops including hay, fruits, vegetables, and grains in irrigated settings. Our results indicate that the current state-of-the-art methods for identifying cropping intensity---that apply simpler rule-based thresholds on vegetation indices---do not work well in regions with a high crop diversity, and likely significantly overestimate double-cropped extent. Multiple machine learning models were able to perform better by capturing nuances that the simple rule-based approaches are unable to. In particular, our (image-based) deep learning model was able to capture nuances in this crop-diverse environment and achieve a high accuracy (96-99% overall accuracy and 83– 93% producer accuracy for the double-cropped class with standard error of less than 2.5%) while also identifying double-cropping in the right crop types and locations based on expert knowledge. Our expert labeling process worked well and has potential as a relatively low-cost, scalable approach for remote sensing applications. The product developed here is valuable to inform several policy questions related to food production and resource use.

This study uses Landsat 8 and Digital Elevation Models (DEM) to show the dominant orientations of digital lineaments and morphotectonic features between measured trends and the tectonic evolution of the Upper Guajira, Colombia, in the northernmost region of the South American plate. Data from Landsat-8 and hillshaded images of three Digital Elevation Model (DEM) images with different resolutions (SRTM: 90m, ASTER-GDEM: 30m and Alos-Palsar: 12.5m), were used for the extraction and mapping of morpholineaments, drainage network and morphological features. Lineaments were analyzed by means of north azimuth frequency, length, density distributions, lithological distributions and geochronological periods. Tectonic control was supported by using the digitized geological map created by the Colombian Geological Service (SGC). Lineaments and faults were analyzed through the interpretation of a Riedel shear model as a result of the transtensional/transpressional tectonic arrangement of the Caribbean and South American plates. The directional trends of lineaments and faults indicate two dominant directions: NE-SW and E-W. The azimuth distribution analysis of measured structures and drainage channels show similar trends, except for some differences in the predominant directions of some drainage channels. The similarity in the orientation of lineaments, faults and drainage system highlights the degree of control exerted by underlying structures on the surface geomorphological features. Drainage channel classification illustrates the morphological and neo-tectonic complexity of the region. The extracted lineaments were divided into five geochronological groups based on the main ages of host rock formations according to the Colombian Geological Service (SGC) geological map. From the Cretaceous onward, the lineament azimuth frequency rotates from a NE-SW trend to a prominent E-W direction, which resembles the translation that Caribbean plate has been undergoing since the Cretaceous. Our results confirm that Remote Sensing techniques are reliable and useful to study the morphotectonic of an area and can be applied to zones of difficult access.

YOLOv8, as an efficient object detection method, can swiftly and precisely identify objects within images. However, traditional algorithms encounter difficulties when detecting small targets in remote sensing images, such as missing information, background noise, and interactions among multiple objects in complex scenes, which may affect performance. To tackle these challenges, we propose an enhanced algorithm optimized for detecting small objects in remote sensing images, named HP-YOLOv8. Firstly, we design the C2f-D-Mixer (C2f-DM) module as a replacement for the original C2f module. This module integrates both local and global information, significantly improving the ability to detect features of small objects. Secondly, we introduce a feature fusion technique based on attention mechanisms, named Bi-Level Routing Attention in Gated Feature Pyramid Network (BGFPN). This technique utilizes an efficient feature aggregation network and reparameterization technology to optimize information interaction between different scale feature maps, and through the Bi-level Routing Attention (BRA) mechanism, it effectively captures critical feature information of small target objects. Finally, we propose the Smooth Mean Perpendicular Distance Intersection over Union (SMPDIoU) loss function. The method comprehensively considers the shape and size of detection boxes, enhances the model's focus on the attributes of detection boxes and provides a more accurate bounding box regression loss calculation method. To demonstrate our approach's efficacy, we conduct comprehensive experiments across the RSOD, NWPU VHR-10, and VisDrone2019 datasets. The experimental results show that the HP-YOLOv8 achieves 95.11%, 93.05%, and 53.49% in the mAP@0.5 metric, and 72.03%, 65.37%, and 38.91% in the more stringent mAP@0.5:0.95 metric, respectively.

The environmental legacy of post-closure mine sites poses a significant risk to the sustainability of mining operations and natural resource development. This study aims to advance the understanding of sustainable mine site reclamation behavior in Canada by using multi-temporal Landsat satellite images to examine the long-term land cover changes at post-closure mine sites. Six representative post-closure mine sites were selected for the evaluation and comparison. The Normalized Difference Vegetation Index (NDVI) analysis, Landsat image classification, post-classification change detection, and Regrowth Index (RI) analysis were conducted to assess the speed and extent of landscape and vegetation recovery at the target mine sites. A significant vegetation recovery was quantified for the mine sites that have experienced active reclamation activities. In contrast, the post-closure mine area undergoing only the passive revegetation typically demonstrated a slow and minor increase in vegetation over time. The actively revegetated mine sites can typically be restored to a level that equals or better than the pre-mining situation. This work confirms that active reclamation and revegetation at post-closure mine sites is critically important in sustainable mining. The quantified mine site reclamation behavior and the relevant sustainable practices would be useful for evidence-based sustainable resource management in Canada.

With the continuous progress of remote sensing image object detection tasks in recent years, researchers in this field have gradually shifted the focus of their research from horizontal object detection to the study of object detection in arbitrary directions. It is worth noting that some properties are different from the horizontal object detection during oriented object detection that researchers have yet to notice much. This article presents the design of a straightforward and efficient arbitrary-oriented detection system, leveraging the inherent properties of the orientation task, including the rotation angle and box aspect ratio. In the detection of low aspect ratio objects, the angle is of little importance to the orientation bounding box, and it is even difficult to define the angle information in extreme categories. Conversely, in the detection of objects with high aspect ratios, the angle information plays a crucial role and can have a decisive impact on the quality of the detection results. By exploiting the aspect ratio of different targets, this letter proposes a ratio-balanced angle loss that allows the model to make a better trade-off between low-aspect ratio objects and high-aspect ratio objects. The rotation angle of each oriented object, which we naturally embed into a two-dimensional Euclidean space for regression, thus avoiding an overly redundant design and preserving the topological properties of the circular space. The performance of the UCAS-AOD, HRSC2016, and DLR-3K datasets show that the proposed model in this paper achieves a leading level in terms of both accuracy and speed. The code is released at https://github.com/minghuicode/Periodic-Pseudo-Domain.

Rapid urbanization has facilitated socioeconomic development but has also exacerbated land use/cover change (LUCC), significantly impacting ecological environments. Timely, objective, and quantitative assessments of ecological quality changes resulting from LUCC are essential for safeguarding the natural environment and managing land resources. However, limited research has explored the potential interrelationships between the spatio-temporal heterogeneity of LUCC and ecological quality during urbanization. This study focuses on Xiong’an New Area, a region experiencing rapid urbanization, utilizing the remote sensing-based ecological index (RSEI) to monitor ecological quality dynamics from 2017 to 2023. To address the computational challenges associated with large-scale regions, a streamlined RSEI construction method was developed using Landsat imagery and implemented via Google Earth Engine (GEE). A geographically weighted regression (GWR) analysis, integrated with Sentinel-2 land use data, was employed to examine the influence of LUCC on ecological quality. The findings reveal the following: (1) Ecological quality in Xiong’an New Area exhibited an overall positive trajectory, with improvements elevating the ecological status to above moderate levels. (2) Urban expansion resulted in a 17% reduction in farmland, primarily converted into construction land, which expanded by approximately 12%. (3) Ecological protection policies have facilitated the conversion of farmland into wetlands and urban green areas, which have emerged as the principal contributors to ecological quality enhancement. (4) A positive correlation was observed between changes in ecological land and ecological quality, while a negative correlation was identified between shifts in construction land and farmland and ecological quality. This research provides valuable scientific insights into ecological conservation and land use management, thereby establishing a foundation for the development of rational land resource planning and sustainable ecological development strategies in the Xiong’an New Area.

Aerosol Optical Thickness (AOT) is one of the critical factors for global atmospheric conditions, climate change, and air pollution. AOT has been exposed as a major component of air pollution in Bangladesh. This paper aims to map the seasonal distribution of AOT from 2002-2022 and to explore the internal relationship between AOT and ten air pollutants using remote sensing and machine learning tools. These ten air pollutants are Particulate matter (PM2.5), Methane (CH4), Carbon monoxide (CO), Nitrogen dioxide (NO2), Formaldehyde (HCHO), Ozone (O3), Sulfur dioxide (SO2), Aerosol Particulate Radius (APR), Nitrogen oxide (NOx) and Black carbon (BC). The results show that the concentrations of AOT were higher in December-January-February (mean value 0.50) and March-April-May (mean value 0.50) seasons, mostly in the central, western, and southern parts of Dhaka, Narayanganj, and Munshiganj districts. AOT was a bit less in June-July-August (mean value 0.33) and September-October-November (mean value 0.37). This paper also revealed that the AOT was correlated positively with PM2.5 (0.60), CH4 (0.80), NO (0.76), and BC (0.83) while correlated negatively with CO (-0.66), HCHO (-0.16), SO2 (-0.41), APR (-0.48), and NOx (-0.20). From the machine learning, the Rational quadratic GPR (RME-0.0024, MAE-0.0015, R2-0.96), Matern 5/2 GPR (RMSE-0.0023, MAE-0.0015, R2-0.96), and Squared Exponential GPR (RMSE-0.0015, MAE-0.0015, R2-0.96) were found good classifiers to predict AOT. UN agencies, government line departments, and local and regional development councils for air pollution mitigation and long-term protective measures may use the paper's key results.

Detecting and monitoring changes in soil salinity through remote sensing provides an opportunity for field assessment in regions where on-site measurements are limited. This investigation, carried out in Siwa Oasis, Egypt, aimed to assess the efficacy of several soil salinity indices derived from Landsat 5 and 7 satellite images. To achieve this, 56 on-site ground measurements were utilized for evaluation purposes. The study aimed to improve the correlation between EC and index values and explore the relationship between salinity and changes in land cover. Eleven spectral indices were calculated for nine scenes captured in different months from August to December. The first approach involved stacking the data to identify the index with the strongest correlation with ground EC values, without the need for complex analysis or EC value ranging. In the second approach, the ground EC measurements were classified into seven different salinity categories, and the correlation coefficient was calculated between each index and each salinity category. The third approach analyzed the data temporally, considering different salinity levels. Lastly, a spatial correlation analysis was conducted between EC and index values in the fourth scenario. The initial approach revealed a weak correlation due to substantial variation in EC values. However, the SI index demonstrated the highest correlation coefficient of 0.38. In the second scenario, the S2 index exhibited the highest correlation of 0.96 for moderate salinity samples. The third scenario showed that the S1 index achieved the highest correlation value of 0.99 for moderately saline areas. In the fourth scenario, the SI index exhibited the strongest correlation among all four ponds with correlation coefficients of 0.23, 0.23, 0.18, and 0.61. Notably, the correlations observed in the second and third scenarios demonstrated higher correlation coefficients compared to both the first and fourth scenarios. The study highlighted significant variations in EC levels related to land cover types and pond elevation. Additionally, remote sensing methods detected a 48% increase in total vegetated area over 17 years, showing the potential of remote sensing techniques in salinity monitoring for expanding agriculture and improving land management.

Detecting rotated objects in remote sensing images poses a substantial challenge. These images usually cover a wide field of view, containing diverse and complex backgrounds with variously sized ground objects densely distributed. Therefore, identifying objects of interest in remote-sensing images is challenging. While integrating Convolutional Neural Networks (CNNs) and Transformer networks has exhibited progress in detecting rotated objects, there is still scope for enhancing feature extraction and fusion. To address this issue, we propose a feature extraction module, a feature context aggregation module, and a multi-scale feature fusion module. Initially, we substitute the Spatial Pyramid Pooling Bottleneck (SPPFBottleneck) with a new module aimed at extracting multi-scale features, thereby enhancing the detection of small objects in complex backgrounds. Next, we develop a novel module for the multi-scale fusion of contextual information within feature maps, extracting valuable information. Finally, we combine the original features with the fused ones to prevent the loss of specific features in the fusion process. We refer to our newly proposed model as the "Multi-scale Feature Context Aggregation Network" (MFCANet). We assess our approach on three challenging remote sensing datasets: MAR20, SRSDD, and HRSC. Comprehensive experimental results show that our method surpasses baseline models by 2.13%, 10.28%, and 1.46% mAP on the MAR20, SRSDD, and HRSC datasets, respectively.

The present work focuses on developing miniaturized, light weight electrochemical sensors for detection of chemical warfare agents (CWAs) like sarin and tabun simulants, i.e., diisopropyl fluorophosphate (DFP), and O,S-diethyl methyl phosphonothioate (O,S-DEMPT). Differential pulse voltammetry (DPV) was employed to examine the redox properties of capturing molecular probe CE2 with the nerve agent stimulants. Coupling of a portable potentiostat with the drone technology could allow on-situ and remote detection of analytes such CWAs to be realized, which can be crucially important to the national and global securities.

Although deep learning has received extensive attention and achieved excellent performances in various of scenarios, it suffers from adversarial examples to some extent. Especially, physical attack poses more threats than digital attack. However, existing researches pay less attention to physical attack of object detection in remote sensing images (RSIs). In this work, we systematically analyze the universal adversarial patch attack for multi-scale objects in the remote sensing field. There are two challenges for adversarial attack in RSIs. On one hand, the number of objects in remote sensing images is more than that of natural images. Therefore, it is difficult for adversarial patch to show adversarial effect on all objects when attacking a detector of RSIs. On the other hand, the wide range of height of photography platform causes that the size of objects diverse a lot, which brings challenges for generating universal adversarial perturbation for multi-scale objects. To this end, we propose an adversarial attack method on object detection for remote sensing data. One of the key ideas of the proposed method is the novel optimization of adversarial patch. We aim to attack as many objects as possible by formulating a joint optimization problem. Besides, we raise a scale factor to generate a universal adversarial patch that adapts to multi-scale objects, which ensures the adversarial patch is valid for multi-scale objects in the real world. Extensive experiments demonstrate the superiority of our method against state-of-the-art methods on YOLO-v3 and YOLO-v5. In addition, we also validate the effectiveness of our method in real-world applications.

Land use and land cover (LULC) datasets for Jinan in 1992, 1998, 2002, 2006, 2011, 2017, and 2022 were developed from Landsat images using the Random Forest (RF) classification approach. The relationships between social-economic, political factors and time-series LULC data were exam-ined for the periods between 1992 and 2022. The results showed the effectiveness of using the RF classification method for LULC classification with time series of Landsat images. Combined with driving forces analysis, our research can effectively explain the detailed LULC change tra-jectories corresponding to different stages and give new insights into Jinan LULC change pat-terns. The results show a significant increase in impervious surface which opposite change to bare land which experienced a huge decline declined by 95%, due to urbanization and rapid in-crease of population. The driving forces behind these changes are related to population growth, economic development, and climate change. Moreover, the present research employed Principal Components Analysis (PCA) methodology in order to understand the relative significance of disparate driving factors. The analysis results prove that the economy (population, GDP) and climate change were the primary factors that have an obvious impact on land use/land cover changes and that the driving factors for impervious surface, bare land, woodland, farmland, and water were distinct. Government policies also have a substantial impact on LULC change as well, such as the Construction of Harmonious Jinan (COHJ). The results were helpful for better understanding the mechanisms of LULC change and can provide useful knowledge for effective land resource management and planning.

This work mainly discusses an innovative teaching platform on Unmanned Aerial Vehicle digital mapping for Remote Sensing (RS) education at Wuhan University, underlining the fast development of RS technology. Firstly, we introduce and discuss the future development of the Virtual Simulation Experiment Teaching Platform for Unmanned Aerial Vehicle (VSETP-UAV). It includes specific topics such as the Systems and function Design, teaching and learning strategies, and experimental methods. This study shows that VSETP-UAV expands the usual content and training methods related to RS education, and creates a good synergy between teaching and research. The results also show that the VSETP-UAV platform is of high teaching quality producing excellent engineers, with high international standards and innovative skills in the RS field. In particular, it develops students' practical skills with technical manipulations of dedicated hardware and software equipment (e.g., UAV) in order to assimilate quickly this particular topic. Therefore, students report that this platform is more accessible from an educational point-of-view than theoretical programs, with a quick way of learning basic concepts of RS. Finally, the proposed VSETP-UAV platform achieves a high social influence, expanding the practical content and training methods of UAV based experiments, and providing a platform for producing high-quality national talents with internationally recognized topics related to emerging engineering education.

Remote sensing datasets are increasingly being used to provide spatially explicit large scale evapotranspiration (ET) estimates. The focus of this study was to estimate and thematically map on a pixel-by-pixel basis, the actual evapotranspiration (ET_a) of the Wonji Shoa Sugarcane Estate using the Surface Energy Balance Algorithm for Land (SEBAL), Simplified Surface Energy Balance (SSEB) and Operational Simplified Surface Energy Balance (SSEBop) algorithms. The results obtained revealed that the ranges of the daily ETa estimated on January 25, February 26, September 06 and October 08, 2002 using SEBAL were 0.0 - 6.85, 0.0 – 9.36, 0.0 – 3.61, 0.0 – 6.83 mm/day; using SSEB 0.0 - 6.78, 0.0 – 7.81, 0.0 – 3.65, 0.0 – 6.46 mm/day, and SSEBop were 0.05 - 8.25, 0.0 – 8.82, 0.2 – 4.0, 0.0 – 7.40 mm/day, respectively. The Root Mean Square Error (RMSE) values between SSEB and SEBAL, SSEBop and SEBAL, and SSEB and SSEBop were 0.548, 0.548, and 0.99 for January 25, 2002; 0.739, 0.753, and 0.994 for February 26, 2002;0.847, 0.846, and 0.999 for September 06, 2002; 0.573, 0.573, and 1.00 for October 08, 2002, respectively. The standard deviation of ET_a over the sugarcane estate showed high spatio-temporal variability perhaps due to soil moisture variability and surface cover. The three algorithm results showed that well watered sugarcane fields in the mid-season growing stage of the crop had higher ET_a values compared with the other dry agricultural fields confirming that they consumptively use more water. Generally during the dry season, ET_a is limited to water surplus areas only and in wet season, ET_a was high throughout the entire sugarcane estate. The evaporation fraction (ETrF) results also followed the same pattern as the daily ET_a over the sugarcane estate. The total crop and irrigation water requirement and effective rainfall estimated using the Cropwat model were 2468.8, 2061.6 and 423.8 mm/yr for January 2001 planted and 2281.9, 1851.0 and 437.8 mm/yr for March 2001 planted sugarcanes, respectively. The mean annual ET_a estimated for the whole estate were 107 Mm³, 140 Mm³, and 178 Mm³ using SEBAL, SSEB, and SSEBop, respectively. Even though the algorithms should be validated through field observation, they have potential to be used for effective estimation of ET in the sugarcane estate.

Relationship between caveman prehistoric life in terms of heat induced food processing and its geological ecosystems have received many attentions. Previous studies have investigated the sources of heat included using Fourier transform infrared spectroscopy and biomarker approaches. Here this study proposes the use of remote sensing to identify the relationship of 9500 year old (9.5 ka) prehistoric mongoloid occupancy with hydrothermal manifestations at Pawon cave of West Java. The hydrothermal manifestations around Pawon cave were identified using Landsat 8 band combinations, land surface temperature, and sedimentary lithology. The results showed the hydrothermal manifestations surrounding Pawon cave were within a distance of 0.5-2 km. The results also showed bones representing 12 animal taxon groups with high abundance of rodents. To conclude this study sheds the light of proximity and preferences of mongoloid prehistoric occupancy towards hydrothermal landscape due to its advantage as heat sources for food processing purposes.

Leakages in the water distribution networks (WDNs) are real problems for utilities and other governmental agencies. Timely leak detection and location identification has been a challenge. In this paper, an integrated approach to geospatial and infrared image processing method was used for robust leak detection. The method combines drops in flow, pressure, and chlorine residuals to determine potential water leakage locations in the WDN using Geographic Information System (GIS) techniques. GIS layers were created from the hourly values of these three parameters for the city of Sharjah provided by Sharjah Electricity, Water and Gas Authority (SEWA). These layers are then analyzed for locations with dropped values of each of the parameters and are overlaid with each other. In the case where there were no overlaying locations between flow and pressure, further water quality analysis was avoided, assuming no potential leak. In the case where there are locations with drops in flow and pressure layers, these overlaying locations are then examined for drops in chlorine values. If overlaying locations are found, then these regions are considered potential leak locations. Once potential leak locations are identified, a specialized remote sensing technique can be used for precise leak location. This study also demonstrated the suitability of using an infrared camera for leak detection in a laboratory-based setup. This paper concludes that the following methodology can help water utility companies in the timely detection of leaks, saving money, time, and effort.

The assessment of ecosystem quality and the maintenance of optimal ecosystem function requires understanding vegetation area dynamics and its relationship with climate variables. This study aims to detect vegetation area changes over a downstream dam and to understand the influence of the dam as well as climatic variables on the region’s vegetation areas. The case study is located in an arid area with an average rainfall amount of 50 to 100 mm/year. An analysis of seasonal changes in vegetation areas was conducted using the Normalized Difference Vegetation Index (NDVI), and supervised image classification was used to evaluate changes in vegetation areas using Landsat imagery. Pearson correlation and multivariate linear regression were used to assess the response of local vegetation areas to both hydrologic changes due to dam construction and climate variability. The NDVI analysis reveals a considerable vegetation decline after the dam construction in the dry season. This is primarily associated with the impoundment of the seasonal water by the dam and the increase in cropland areas due to dam irrigation. A significantly stronger correlation between vegetation changes and precipitation and temperature variations is observed before the dam construction. Furthermore, multivariant linear regression was used to evaluate the variations of equivalent water thickness (EWT), climate data, and NDVI before and after the dam construction. The results suggest that 85 percent of the variability in the mean NDVI was driven by climate variables and EWT before the dam construction. On the other hand, it was found that only 42 percent of the variations in NDVI were driven by climate variables and EWT after the dam construction for both dry and wet seasons.

Understanding the distribution of rock glaciers provides key information for investigating and recognizing the status and changes of the periglacial environment. Deep learning algorithms and red-green-blue (RGB) bands from high-resolution satellite images have been extensively employed to map rock glaciers. However, the near-infrared (NIR) band offers rich spectral information and sharp edge features that could significantly contribute to semantic segmentation tasks, but it is rarely utilized in constructing rock glacier identification models due to the limitation of three input bands for classical semantic segmentation networks, like DeeplabV3+. In this study, a dual-encoder DeeplabV3+ network (DEDNet) was designed to overcome the flaws of classical DeeplabV3+ network (CDNet) when identifying rock glaciers using multispectral remote sensing images by extracting spatial and spectral features from RGB and NIR bands, respectively. This network, trained with manually labeled rock glacier samples from QiLian Mountains, established a model with accuracy, precision, recall, specificity, and mIoU (Mean Intersection over Union) of 0.9131, 0.9130, 0.9270, 0.9195, and 0.8601, respectively. The well-trained model was applied to identify new rock glaciers in a test region, achieving a producer's accuracy of 93.68% and a user's accuracy of 94.18%. Furthermore, the model was employed to two study areas in northern Tien Shan (Kazakhstan) and Daxue Shan (Hengduan Shan, China) with high accuracy, which proved that the DEDNet offers an innovative solution to more accurately map rock glaciers on a larger scale due to its robustness across diverse geographic regions.

Rapidly and accurately extracting tobacco plant information can facilitate tobacco planting man-agement, precise fertilization and yield prediction. In karst plateau of southern China, tobacco plant identification is affected by large ground undulations, fragmented planting areas, complex and diverse habitats and uneven plant growth. This study took a tobacco planting area in Gui-zhou Province as the research object and used DJI UAVs to collect UAV visible light images. Considering plot fragmentation, plant size, presence of weeds and shadow masking, this area was classified into eight habitats. The datasets of different habitats were constructed to train the U-Net model. The results show that (1) the overall precision, recall, F1-score and IOU of tobacco plant information extraction were 0.68, 0.85, 0.75 and 0.60, respectively. (2) The precision was the highest for the subsurface-fragmented and weed-free habitat and the lowest for the smooth-tectonics and weed-infested habitat. (3) The weed-infested habitat with smaller tobacco plants can cause blurred images, reducing the plant identification accuracy. This study verified the feasibility of the U-Net model for tobacco single-plant identification in complex habitats. Decomposing complex habitats to establish the sample set method is a new attempt to improve crop identification in complex habitats in karst mountainous areas.

Seasonal snowpacks, characterized by their snow water equivalent (SWE), play a major role in the hydrological cycle, snow melt contributions to floods and the subsequent availability of water resources downstream. Accurately estimating SWE and understanding its spatial and temporal variations presents a considerable challenge, particularly within mountainous regions characterized by complex terrain and limited observational data. Seeking to enhance the performance of the widely used Soil and Water Assessment Tool (SWAT), we report a new approach characterising snowpack behaviour incorporating both modelled and remotely sensed derived SWE calibration data. We focus on the Chenab River Basin (CRB) a headwater catchment of the Indus Basin, globally significant in terms of human inhabitants and intensifying flood risk due to climate change. We conducted a thorough assessment of five satellite-derived and reanalysis-based precipitation datasets: ERA5-Land, CMORPH, TRMM, APHRODITE, and CPC UPP. This reveals significant levels of uncertainty in global precipitation products when compared to reference data from observed stations as well as in the resulting simulated streamflow from the SWAT model. Subsequently, we expanded the scope of the SWAT model to encompass the spatial and temporal simulation of SWE. This was achieved by incorporating information from remotely sensed and modelled SWE products, manually adjusting snow parameters in R-SWAT for both the main basin and at sub-basin scales. Integrating SWE from reference snow products into the calibration process, alongside streamflow data, substantially enhanced modelling accuracy to simulate SWE compared to the conventional auto-calibration and single-variable approaches reliant solely on streamflow data. This approach results in considerable improvement in SWE predictions and to some extent in streamflow simulation in catchments dominated by snow. This research highlights the potential of remote sensing and modelled SWE parameterisation in the absence of in-situ snowpack data in high-altitude environments. An improved understanding of SWE behaviour is vital for predicting hydrological responses spanning hazards to water resources in the populous downstream regions of the Indus Basin, especially in the face of climate change.

Land cover change detection (LCCD) based on bi-temporal remote sensing images plays an important role in the inventory of land cover change. Due to the benefit of having spatial dependency properties within the image space while using remote sensing images for detecting land cover change, many contextual information based change detection methods have been proposed during past decades. However, there is still a space for improvement in accuracies and usability of LCCD. In this paper, a LCCD method based on adaptive contextual information is proposed. First, an adaptive region is constructed by gradually detecting the spectral similarity surrounding a central pixel. Second, the Euclidean distance between pairwise extended regions is calculated to measure the change magnitude between the pairwise central pixels of bi-temporal images. While the whole bi-temporal images are scanned pixel-by-pixel, the change magnitude image (CMI) can be generated. Then, the Otsu or a manual threshold is employed to acquire the binary change detection map (BCDM). The detection accuracies of the proposed approach are investigated by two land cover change cases with Landsat bi-temporal remote sensing images. In comparison to several widely used change detection methods, the proposed approach can achieve a land cover change inventory map with a competitive accuracy.

This study is aimed at demonstrating application of vegetation spectral techniques for detection and monitoring of impact of oil spills on vegetation. Vegetation spectral reflectance from Landsat 8 data were used in the calculation of five vegetation indices (normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), adjusted resistant vegetation index 2 (ARVI2), green-infrared index (G/NIR) and green-shortwave infrared (G/SWIR) from the spill sites (SS) and non-spill (NSS) sites in 2013 (pre-oil spill), 2014 (oil spill date) and 2015 (post-oil spill) for statistical comparison. The result shows that NDVI, SAVI, ARVI2, G/NIR and G/SWIR indicated certain level difference between vegetation condition at the SS and the NSS were significant with p-value <0.5 in December 2013. In December 2014 vegetation conditions indicated higher level of significant difference between the vegetation at the SS and NSS as follows where NDVI, SAVI and ARVI2 with p-value 0.005, G/NIR - p-value 0.01 and GSWIR p-value 0.05. Similarly, in January 2015 a very significant difference with p-value <0.005. Three indices NDVI, ARVI2 and G/NIR indicated highly significant difference in vegetation conditions with p-value <0.005 between December 2013 and December 2014 at the same sites. Post—spill analysis show that NDVI and ARVI2 indicated low level of significance difference p-value <0.05 suggesting subtle change in vegetation conditions between December 2014 and January 2015. This technique is essential for real time detection, response and monitoring of oil spills from pipelines for mitigation of pollution at the affected sites in the mangrove forest.