The Combined Inversion of Surface and AeRosols (CISAR) algorithm for the joint retrieval of surface and aerosol single scattering properties has been further developed in order to extend the retrieval to clouds and overcome the need for an external cloud mask. Pixels located in the transition zone between pure cloud and pure aerosol are often discarded by both aerosol and cloud algorithms, despite being essential for studying aerosol-cloud interactions, which still represent the largest source of uncertainty in climate predictions. The proposed approach aims at filling this gap and deepening the understanding of aerosol properties in cloudy environments. The new CISAR version is applied to Sentinel-3A/SLSTR observations and evaluated against different satellite products and ground measurements. The spatial coverage is greatly improved with respect to algorithms processing only pixels flagged as clear sky by the SLSTR cloud mask. The continuous retrieval of aerosol properties without any safety zone around clouds opens new possibilities for studying aerosol properties in cloudy environments.

Most real-time terrain point cloud rendering techniques do not address the empty space between the points but rather try to minimize it by changing the way how the points are rendered by either rendering them bigger or with more appropriate shapes such as paraboloids. In this work, we propose an alternative approach to point cloud rendering, which addresses the empty space between the points and tries to fill it with appropriate values to achieve the best possible output. The proposed approach runs in real time and outperforms several existing point cloud rendering techniques in terms of speed and render quality.

Cyprus plans to drastically increase the share of renewable energy sources from 13.9% in 2020 to 22.9% in 2030. Solar energy can play a key role in the effort to fulfil this goal. The potential for production of solar energy over the island is much higher than most of European territory because of the low latitude of the island and the nearly cloudless summers. In this study, high quality and fine resolution satellite retrievals of aerosols and dust, from the newly developed MIDAS climatology, as well as information for clouds from CMSAF are used in order to quantify the effects of aerosols, dust, and clouds on the levels of surface solar radiation (SSR) and the corresponding financial loss for different types of installations for production of solar energy. An SSR climatology has been also developed based on the above information. Ground-based measurements were also incorporated to study the contribution of different species to the aerosol mixture and the effects of day-to-day variability of aerosols on SSR. Aerosols attenuate 5 – 10% of annual GHI and 15 – 35% of annual DNI, while clouds attenuate ~25 – 30% and 35 – 50% respectively. Dust is responsible for 30 – 50% of the overall attenuation by aerosols.

This paper aims at tackling with the task of fusion feature from images and its corresponding point clouds for 3D object detection in autonomous driving scenarios basing on AVOD, an Aggregate View Object Detection network. The proposed fusion algorithms fuse features targeted from Bird’s Eye View (BEV) LIDAR point clouds and its corresponding RGB images. Differs in existing fusion methods, which are simply the adoptions of concatenation module, element-wise sum module or element-wise mean module, our proposed fusion algorithms enhance the interaction between BEV feature maps and its corresponding images feature maps by designing a novel structure, where single level feature maps and another utilizes multilevel feature maps. Experiments show that our proposed fusion algorithm produces better results on 3D mAP and AHS with less speed loss comparing to existing fusion method used on the KITTI 3D object detection benchmark.

Polar stratospheric clouds (PSCs) form in polar regions typically between 15 and 25 km, when the local temperature is sufficiently low. PSCs play an important role in the ozone chemistry and the dehydration and denitrification of the stratosphere. Lidars with a depolarization channel may be used to detect and classify different classes of PSCs. The main PSC classes are water ice, nitric acid trihydrate (NAT) and supercooled ternary solutions (STS), the latter being liquid droplets consisting of water, nitric acid and sulphuric acid. PSCs have been observed at the lidar observatory at Concordia Station from 2014 on. The harsh environmental conditions at Concordia during winter render successful lidar operation difficult. In order to facilitate the operation of the observatory several measures have been put in place to achieve an almost complete remote control of the system. PSC occurrence is strongly correlated with local temperatures and is affected by dynamics, as the PSC coverage during the observation season shows.

Urban scene point cloud pose significant challenges for registration due to its large data volume, similar scenarios and dynamic objects. In this paper, we propose PCRMLP, a model for urban scene point cloud registration that achieves comparable registration performance to prior learning-based methods. Compared to previous works which focus on extracting features and estimating correspondence, the model estimates the transformation implicitly from concrete instances. An instance-level urban scene representation method is introduced to extract instance descriptors via semantic segmentation and DBSCAN, which enable the model to obtain robust instance features, filter dynamic objects and estimate transformation in a more logical manner. Then a lightweight network consisting of MLPs is employed to obtain transformation in an encoder-decoder manner. We validate the approach on KITTI dataset. Experimental results demonstrate that PCRMLP can obtain a satisfactory coarse transformation from instance descriptors just in 0.0028s. With a subsequent ICP refinement module, the proposed method achieves higher registration accuracy and computational efficiency than prior learning-based works.

In this paper, we present a framework to study the spatial structure of noctilucent clouds formed by ice particles in the upper atmosphere at mid and high latitude during summer. We study noctilucent cloud activity in optical images taken from three different locations and under different atmospheric conditions. In order to identify and distinguish noctilucent cloud activity from other objects in the scene, we employ linear discriminant analysis (LDA) with feature vectors ranging from simple metrics to higher-order local autocorrelation (HLAC), and histogram of oriented gradients (HOG). Finally, we propose a Convolutional Neural Networks (CNN) based method for the detection of noctilucent clouds. The results clearly indicate that the CNN based approach outperforms LDA based methods used in this article. Furthermore, we outline suggestions for future research directions to establish a framework that can be used for synchronizing the optical observations from ground based camera systems with echoes measured with radar systems like EISCAT in order to obtain independent additional information on the ice clouds.

At an energy flux imbalance of about 1 W m–2, the ocean is storing 90 % of the heat accumulating by global warming. However, neither the causes nor the responsible geophysical processes are sufficiently well understood. More detailed investigations of the different phenomena contributing to the oceanic energy balance are warranted. Here, the role of low-level marine clouds in the air-sea interaction is analysed. TEOS-10, the International Thermodynamic Equation of State of Seawater – 2010, is exploited for a rigorous thermodynamic description of the climatic trend of the Lifted Condensation Level (LCL) of the marine troposphere. Rising Sea-Surface Temperature (SST) at constant Relative Humidity (RH) is elevating marine clouds, cooling the cloud base and reducing the downward thermal radiation. This LCL feedback effect is negative and counteracting ocean warming. At the current global SST of about 292 K, the net radiative heat flux from the ocean surface to the LCL cloud base is estimated to 24 W m–2. Per degree of SST increase, this net flux is expected to be enhanced by almost 0.5 W m–2. The climatic LCL feedback effect is relevant for the ocean’s energy balance and may thermodynamically rigorously be modelled in terms of TEOS-10 equations. LCL height may serve as a remotely measured, sensitive estimate for sea surface relative fugacity, or conventional relative humidity.

This study investigates the possible mechanisms related to the wide range of relative humidity in cirrus clouds (RHi). Under the closed adiabatic assumption, the impacts of vertical motion and ice crystal deposition/sublimation on RHi are investigated through in situ observations and parcel model simulations. Vertical motion is an active external force that changes the RHi, and ice crystal deposition/sublimation plays a role in mitigating the change in RHi. They are the two most important mechanisms involved in controlling the RHi fluctuation during cirrus evolution and could well explain the wide range of RHi in wave-related cirrus clouds. Furthermore, a comparison of cloud statistical characteristics from both observations and simulations shows that a very low value (e.g., 0.001) for the water vapor ice deposition coefficient is highly unlikely.

The development of extremely powerful thunderstorm which took place on August 19, 2015 is discussed in this paper. High depth hail cloud originated on the Black Sea Coast and classified as a supercell as well as several weaker hailstorms passed more than 1000 km over Northern Caucasus of Russia, the Caspian Sea, and then invaded the territory of Kazakhstan. During more than 20 hours of existence this supercell produced heavy hail, rain, intense lightning discharges, gust and tornado which rarely occurs in the region. The study of the structure and characteristics of the thunderstorm during the formation of electrical discharges and their frequency were of particular interest. According to the forecast, development of convective clouds and separate thunderstorms were expected, though the powerful hail process was not expected due to small vertical temperature gradients and the absence of cold fronts. Supercell was tracked by 5 radars located in this area, which showed its right-hand development with clock-wise deviation from the leading stream on 40-50 degrees to the right and the resulting speed of propagation was about 60-85km/h. The maximum reflectivity factor exceeded value 75dBZ, top of the clouds reached 15-16km and the height of the hail core raised on 11.2km. The size of hailstones size on most of the hail path was 2–3cm, and at the peak of cloud development - 4–5cm. Maximum frequencies of cloud-to-ground flashes of negative and positive polarities reached 30-35min-1 and 60-70min-1 correspondingly, while frequency of cloud-to-cloud flashes was significantly higher and amounted up to 300-500min-1 at the peak of the supercell development. An important fact is that the maximum frequency of flashes of different types coincided in time, showing that the reason of all discharges is similar. Total current of the cloud-to-ground flashes of positive and negative polarities was almost identical in magnitude and differed by sign. It was 200-300 kiloampere at the peak of thunderstorm development. The minimum value of radiation temperature, measured by SEVIRI radiometer installed onboard of Meteosat-10 satellite in 10.8 μm channel, was near to -60ºC. The minimum temperature value on the top of the supercell was comparable to coupled radar and sounding data. The most intensive precipitation flux derived from radiometric measurements was about 22000m3/sec; at the same period radars assessments showed precipitation up to 550mm/h (mixed phase precipitation) and size of hail 4.5cm. The combined satellite-radar-lightning data analysis showed that radar derived characteristics of the supercell reached their maximums earlier than maximum in lightning activity. The highest correlation coefficient between radar and lightning characteristics of the supercell storm was found for pair maximum reflectivity and intensity of LF (0.55) and VHF (0.66) discharges. Estimations of relationship between hail size and lightning activity showed that with increasing hail size, thunderstorm activity increases for both cloud-to-ground and intracloud flashes (on the level 0.46 - 0.59). Analysis of doppler-polarimetric data showed strong inflow zone associated with tornado. Tornadic debris signature was manifested by radar reflectivity factor ZH > 60 dBZ, differential reflectivity ZDR > -1 dB, copolar cross-correlation coefficient ρHV < 0.6, and it was collocated with the tornado vortex signature. Doppler velocities in mesocyclone zone reached values -43 and +63 m/s. Prominent radar echo hook was identified in 1.5 km layer above the ground, while ZDR columns was relatively narrow (4–8 km wide) and not very deep (4.5 km).

The paper presents the results of high precision control survey carried out in the underground mining of Oyu Tolgoi project using terrestrial laser scanning technology. The purpose of the measurements is to ensure the heading, total length and volume of the penetration and excavation works are being implementing in accordance with the planned and designed dimensions. We established a network of 18 reference points in the tunnel of the selected underground level which were repeatedly measured 4 times by two round readings of the Trimble S7 tacheometry and processed by using the Trimble Business Center software. All points except the one was within the permissible error. Based on these points the excavation length and volumes were determined using the Trimble SX12 laser scanner. The difference between the planned work quantity provided by the Oyu Tolgoi project and the actual values measured by the laser scanning was calculated using the comparative method. The TLS partial control measurements in the excavations made through the ore bodies revealed the length of 20285.72 m and volume of 441128.80 m3 for underground 7 mine levels while their project values were 16158.26 m length and 422837.50 m3 volume, respectively.

The TROPOMI XCH4 data product requires rigorous cloud filtering to achieve a product accuracy of &lt;1%. To this end, the operational XCH4 data processing has been based on SUOMI-NPP VIIRS cloud observations. However, SUOMI-NPP is nearing at the end of its operational life and has encountered malfunctions in 2022 and 2023. In this study, we introduce a novel machine learning cloud clearing approach based on a random forest classifier (RFC). The RFC is trained on collocated TROPOMI and SUOMI-NPP VIIRS data to emulate VIIRS-like cloud clearing. After training, cloud masking requires only TROPOMI data, and so becomes operationally independent of SUOMI-NPP. We demonstrate the RFC approach by applying cloud clearing to operational TROPOMI XCH4 data for August 2022, a period in which VIIRS was not operational. For validation, we analyze the TROPOMI XCH4 data at 12 TCCON stations. Comparison of cloud clearing using the RFC and the original VIIRS method reveals excellent agreement with a similar station-to-station bias (-7.4 ppb versus -5.6 ppb), a similar standard deviation of the station-to-station bias (11.6 ppb versus 12 ppb), and the same Pearson correlation coefficient of 0.9. Remarkably, the RFC cloud clearing provides a slightly higher volume of data (2182 versus 2035 daily means) and appears to have fewer outliers. Since November 21, 2023, the RFC approach is part of ESA’s operational processing chain. For now the default practice is to utilize SNPP-VIIRS when accessible. Only in cases where VIIRS data is unavailable do we resort to the RFC cloud mask.

Review of the existing bibliography shows that the direction and magnitude of the long-term trends of UV irradiance, and their main drivers, vary significantly throughout Europe. Analysis of total ozone and spectral UV data recorded at four European stations during 1996 – 2017 reveals that long-term changes in UV are mainly driven by changes in aerosols, cloudiness, and surface albedo, while changes in total ozone play a less significant role. The variability of UV irradiance is large throughout Italy due to the complex topography and large latitudinal extension of the country. Analysis of the spectral UV records of the urban site of Rome, and the alpine site of Aosta reveals that differences between the two sites follow the annual cycle of the differences in cloudiness and surface albedo. Comparisons between the noon UV index measured at the ground at the same stations and the corresponding estimates from the DWD forecast model and OMI/Aura observations reveal differences of up to 6 units between individual measurements, which are likely due to the different spatial resolution of the different datasets, and average differences of 0.5 – 1 unit, possibly related to the use of climatological surface albedo and aerosol optical properties in the retrieval algorithms.

Global pose refinement is a significant challenge within Simultaneous Localization and Mapping (SLAM) frameworks. For LIDAR-based SLAM systems, pose refinement is integral to correcting drift caused by the successive registration of 3D point clouds collected by the sensor. A divergence between the actual and calculated platform path characterizes this error. In response to this challenge, we propose a linear, parameter-free model, which uses a closed circuit for global trajectory corrections. Our model maps rotations to quaternions and uses Spherical Linear Interpolation (SLERP) for transitions between them. The intervals are established from the constraint set by the Least Squares (LS) method on rotation closure and are proportional to the circuit's size. Translations are globally adjusted in a distinct linear phase. Additionally, we suggest a coarse-to-fine pairwise registration method, integrating Fast Global Registration and Generalized ICP with multiscale sampling and filtering. The proposed approach is tested on three varied datasets of point clouds, including Mobile Laser Scanners and Terrestrial Laser Scanners. These diverse datasets affirm the model's effectiveness in 3D pose estimation with substantial pose differences and efficient pose optimization in larger circuits.

Object detection is important in many applications, such as autonomous driving. While 2D images are lack of depth information and are sensitive to environmental conditions, 3D point cloud can provide accurate depth information and a more descriptive environment. However, sparsity is always a challenge in single-frame point cloud object detection. This paper introduces a two-stage proposal-based feature fusion method for object detection using multiple frames. The proposed method, called proposal features fusion (PFF), utilizes a cosine-similarity approach to associate proposals from multiple frames and employs an attention weighted fusion module to merge features from these proposals. It allows for feature fusion specific to individual objects and offers lower computational complexity while achieving higher precision. The experimental results on the nuScenes dataset demonstrate the effectiveness of our approach, achieving a mAP of 46.7%, which is 1.3% higher than the state-of-the-art 3D object detection method.

Analysis of the hourly Canadian Prairie data for the past 60 years has transformed our quantitative understanding of land-atmosphere-cloud coupling. The key reason is that trained observers made hourly estimates of opaque cloud fraction that obscures the sun, moon or stars, following the same protocol for 60 years at all stations. These 24 daily estimates of opaque cloud data are of sufficient quality that they can be calibrated against Baseline Surface Radiation Network data to give the climatology of the daily short-wave, longwave and total cloud forcing (SWCF, LWCF and CF). This key radiative forcing has not been available previously for climate datasets. Net cloud radiative forcing reverses sign from negative in the warm season to positive in the cold season, when reflective snow reduces the negative SWCF below the positive LWCF. This in turn leads to a large climate discontinuity with snow cover, with a systematic cooling of 10°C or more with snow cover. In addition, snow cover transforms the coupling between cloud cover and the diurnal range of temperature. In the warm season, maximum temperature increases with decreasing cloud, while minimum temperature barely changes; while in the cold season with snow cover, maximum temperature decreases with decreasing cloud and minimum temperature decreases even more. In the warm season, the diurnal ranges of temperature, relative humidity, equivalent potential temperature and the pressure height of the lifting condensation level are all tightly coupled to opaque cloud cover. Given over 600 station-years of hourly data, we are able to extract, perhaps for the first time, the coupling between cloud forcing and the warm season imbalance of the diurnal cycle; which changes monotonically from a warming and drying under clear skies to a cooling and moistening under cloudy skies with precipitation. Because we have the daily cloud radiative forci, which is large, we are able to show that the memory of water storage anomalies, from precipitation and the snowpack, goes back many months. The spring climatology shows the memory of snowfall back through the entire winter, and the memory in summer goes back to the months of snowmelt. Lagged precipitation anomalies modify the thermodynamic coupling of the diurnal cycle to the cloud forcing, and shift the diurnal cycle of mixing ratio which has a double peak. The seasonal extraction of the surface total water storage is a large damping of the interannual variability of precipitation anomalies in the growing season. The large land-use change from summer fallow to intensive cropping, which peaked in the early 1990s, has led to a coupled climate response that has cooled and moistened the growing season, lowering cloud-base, increasing equivalent potential temperature, and increasing precipitation. We show a simplified energy balance of the Prairies during the growing season and its dependence on reflective cloud.

As the control brain of the petrochemical plant, blast resistant performance requirements of the petrochemical control room should be guaranteed when the vapor cloud explosion occurs in the petrochemical production process. 3D-Kagome truss core sandwich structure is a kind of blast resistant material with high energy absorption. Considering the influence factors of the radius of the truss core rod and thickness of the upper and lower panels, in this paper, blast resistant performance of a real steel petrochemical control room with 3D-Kagome truss core sandwich wall is analyzed. With the optimization goal of plastic deformation energy and panel displacement, the optimal wall thickness and radius of the truss core rode are obtained. The optimized blast resistant wall is assembled, and the dynamic response of the steel petrochemical control room with the 3D-Kagome truss core sandwich blast resistant wall is analyzed. The simulation results show that the truss core layer does not dissipate the blast energy effectively when the radius ratio of the truss core rod is larger than 2.7% of the total thickness of the wall; with the increase of the thickness of the upper and lower panels, the proportion of plastic deformation energy of the truss core layer increases gradually and then tends to be a stable proportion value, that is about 90%; When the thickness ratio of the panel is 6.7% of the total one of the wall and the radius ratio of the truss core rod is 2.7% of the total thickness of the wall, the optimal blast resistant 3D-Kagome sandwich wall is determined.

40 years of cloud observations are available globally from satellites allowing derivation of climate data records (CDRs) for climate change studies. The aim of this study is to investigate how stable these cloud CDRs are and whether they qualify stability requirements recommended by the WMO’s Global Climate Observing System (GCOS). We also investigate robust trends in global total cloud amount (CA) and cloud top temperature (CTT) that are significant and common across all CDRs. The latest versions of four global cloud CDRs, namely CLARA-A3, ESA Cloud CCI, PATMOS-x and ISCCP-HGM, are analysed. This assessment finds that all three AVHRR based cloud CDRs satisfy even the strictest GCOS stability requirements for CA and CTT when averaged globally. While CLARA-A3 is most stable in global averages, PATMOS-x offers the most stable CDR spatially. While we find these results highly encouraging, there however remain large spatial differences in the stability of and across the CDRs. All four CDRs continue to agree on the statistically significant decrease in global cloud amount over the last four decades, although this decrease is now weaker compared to the previous assessments. This decreasing trend is stabilizing or even reversing in the last two decades; the latter is seen also in MODIS-Aqua and CALIPSO GEWEX datasets. Statistically significant trends in CTT are observed in global averages in the AVHRR-based CDRs, but the spatial agreement in the sign and the magnitude of the trends is weaker compared to those in CA. We also present maps of Common Stability Coverage and Common Trend Coverage that could provide a valuable metric to carry out an ensemble-based analysis of the CDRs.

This article presents results of the polarization laser studies of the optical and microphysical characteristics of the high-level clouds (HLC). The high-altitude matrix polarization lidar (HAMPL; Tomsk, Russia) is described. HAMPL measures vertical profiles of all elements of the backscattering phase matrix (BSPM) of the HLC. Based on the joint analysis of lidar and radiosonde observations it is shown that the spatial structure of the HLC containing oriented ice crystals is inhomogeneous in the horizontal wind direction. It includes local areas with oriented particles; the sizes of such areas are estimated together with the most probable meteorological conditions of their formation. The shortcomings of the radiosonde observations performed closest to the location of the HAMPL are described. The applicability of the ERA5 reanalysis data of the European Centre for Medium-Range Weather Forecasts for use as an alternative source of information on the vertical profiles of meteorological quantities for the interpretation of HLC lidar sensing data in Western Siberia was checked.

Digital Twin Cities (DTCs) play a fundamental role in city planning and management. They allow three-dimensional modeling and simulation of cities. 3D semantic segmentation is the foundation for automatically creating enriched DTCs, as well as their updates. Past studies indicate that prior level fusion approaches demonstrate more promising precisions in 3D semantic segmentation compared to point level fusion, features level fusion, and decision level fusion families. In order to improve point cloud enriched semantic segmentation outcomes, this article proposes a new approach for 3D point cloud semantic segmentation through developing and benchmarking three prior level fusion scenarios. A reference approach based on point clouds and aerial images was proposed to compare it with the different developed scenarios. In each scenario, we inject a specific prior knowledge (geometric features,classified images ,etc) and aerial images as attributes of point clouds into the neural network’s learning pipeline. The objective is to find the one that integrates the most significant prior knowledge and enhances neural network knowledge more profoundly, which we have named the "smart fusion approach". The advanced Deep Learning algorithm "RandLaNet" was adopted to implement the different proposed scenarios and the reference approach, due to its excellent performance demonstrated in the literature. The introduction of some significant features associated with the label classes facilitated the learning process and improved the semantic segmentation results that can be achievable with the same neural network alone. Overall, our contribution provides a promising solution for addressing some challenges, in particular more accurate extraction of semantically rich objects from the urban fabric. An assessment of the semantic segmentation results obtained by the different scenarios is performed based on metrics computation and visual investigations. Finally,the smart fusion approach was derived based on the obtained qualitative and quantitative results.

Downward short-wave (SW) solar radiation is the only essential energy source powering the atmospheric dynamics, ocean dynamics, biochemical processes, etc. on our planet. Clouds are the main factor limiting the SW flux over the land and the Ocean. For the accurate meteorological measurements of the SW flux one needs expensive equipment - pyranometers. For some cases where one does not need golden-standard quality of measurements, we propose estimating incoming SW radiation flux using all-sky optical RGB imagery which is assumed to incapsulate the whole information about the SW flux. We used DASIO all-sky imagery dataset with corresponding SW downward radiation flux measurements registered by an accurate pyranometer. The dataset has been collected in various regions of the World Ocean during several marine campaigns from 2014 to 2022, and it will be updated. We demonstrate the capabilities of several machine learning models in this problem, which are multilinear regression, Random Forests, Gradient Boosting and convolutional neural networks (CNN). We also applied the inverse target frequency (ITF) re-weighting of the training subset and the approach of pre-classification in order to raise the SW flux approximation quality. We found that the CNN is capable of approximating downward SW solar radiation with higher accuracy compared to existing empiric parameterizations. We also found that the ITF reweighting of the training subset increases the approximation quality substantially. The estimates of the SW radiation flux using all-sky imagery may be of particular use in case of the need for the fast radiative budgets assessment of a site.

Mapping vegetation species is critical to facilitate related quantitative assessment, and for invasive plants mapping their distribution is important to enhance monitoring and controlling activities. Integrating high resolution multispectral remote sensing (RS) image and lidar (light detection and ranging) point clouds can provide robust features for vegetation mapping. However, using multiple source of high-resolution RS data for vegetation mapping at large spatial scale can be both computationally and sampling intensive. Here we designed a two-step classification workflow to decrease computational cost and sampling effort, and to increase classification accuracy by integrating multispectral and lidar data to derive spectral, textural, and structural features for mapping target vegetation species. We used this workflow to classify kudzu, an aggressive invasive vine, in the entire Knox County (1,362 km2) of Tennessee, the United States. Object-based image analysis was conducted in the workflow. The first-step classification used 320 kudzu samples and extensive coarsely labeled samples (based on national land cover) to generate an overprediction map of kudzu using random forest (RF). For the second step, 350 samples were randomly extracted from the overpredicted kudzu and labeled manually for the final prediction using RF and support vector machine (SVM). Computationally intensive features were only used for the second-step classification. SVM had constantly better accuracy than RF, and the Producer’s Accuracy, User’s Accuracy, and Kappa for the SVM model on kudzu was 0.94, 0.96, and 0.90, respectively. SVM predicted 1010 kudzu patches covering 1.29 km2 in Knox County. We found the sample size of kudzu used for algorithm training impacted the accuracy and number of kudzu predicted. The proposed workflow could also improve sampling efficiency and specificity. Our workflow had much higher accuracy than the traditional method conducted in this research, and could be easily implemented to map kudzu in other regions or other vegetation species.

The World Meteorological Organization (WMO) recommends that the most recent 30-year period, i.e. 1991-2020, shall be used to compute climate normals of geophysical variables. A unique aspect this recent 30-year period is that the satellite-based observations of many different essential climate variables are available during this period, thus opening up new possibilities to provide a robust, global basis for the 30-year reference period in order to allow climate monitoring and climate change studies. Here, using the satellite-based climate data record of cloud and radiation properties, CLARA-A3, for the month of January between 1981 to 2020, we illustrate the difference between climate normal, as defined by guidelines from WMO on calculations of 30-yr climate normals, and climatology. It is shown that this difference is strongly dependent on the climate variable in question. We discuss the impacts of the nature and availability of satellite observations, variable definition, retrieval algorithm and programmatic configuration. It is shown that the satellite-based climate data records show enormous promise in providing climate normal for the recent 30-year period (1991-2020) globally. We finally argue that the holistic perspectives from the global satellite community should be increasingly considered while formulating the future WMO guidelines on computing climate normals.

In the current industrial landscape, increasingly pervaded by technological innovations, the adoption of optimized strategies for asset management is becoming a critical key success factor. Among the various strategies available, the “Prognostics and Health Management” strategy is able to support maintenance management decisions more accurately, through continuous monitoring of equipment health and “Remaining Useful Life” forecasting. In the present study, Convolutional Neural Network-based Deep Neural Network techniques are investigated for the Remaining Useful Life prediction of a punch tool, whose degradation is caused by working surface deformations during the machining process. Surface deformation is determined using a 3D scanning sensor capable of returning point clouds with micrometric accuracy during the operation of the punching machine, avoiding both downtime and human intervention. The 3D point clouds thus obtained are transformed into bidimensional image-type maps, i.e., maps of depths and normal vectors, to fully exploit the potential of convolutional neural networks for extracting features. Such maps are then processed by comparing 15 genetically optimized architectures with the transfer learning of 19 pre-trained models, using a classic machine learning approach, i.e., Support Vector Regression, as a benchmark. The achieved results clearly show that, in this specific case, optimized architectures provide performance far superior (MAPE=0.058) to that of transfer learning which, instead, remains at a lower or slightly higher level (MAPE=0.416) than Support Vector Regression (MAPE=0.857).

The safe and reliable operation of autonomous vehicles in complex and dynamic environments is heavily dependent upon exteroceptive and proprioceptive sensors. A LiDAR system generates accurate 3D point clouds, which are crucial for the detection, classification, and tracking of multiple targets. LiDAR data, however, presents significant challenges due to its density, noise, and varying sampling rates. In this study, various clustering and MTT techniques for LiDAR point clouds will be identified and classified within the context of autonomous driving to assess the state-of-the-art methods’ key challenges and their performances. We have categorized clustering and MTT methods used in AV applications, identified research gaps and challenges and analyzed existing algorithms and their challenges in detail. Researchers and practitioners in the field of autonomous driving will find this review to be a valuable resource.