Abstract: Atmospheric deposition of emerging contaminants, including toxic trace elements, remains a critical environmental and public health concern. Moss biomonitoring offers a sensitive and cost-effective tool for assessing airborne pollutants, yet traditional analyses rely on descriptive statistics and lack predictive and mechanistic insight. Here, we introduce Mosses ML, a machine-learning–enhanced framework that integrates moss biomonitoring with bulk and dry deposition measurements to improve detection, interpretation and risk assessment of atmospheric contaminants. Using Hylocomium splendens transplants exposed for 90 days across industrial, urban and rural sites in Upper Silesia (Poland), we combined trace-element accumulation (Cd, Pb, Zn, Ni, Cr, Fe), relative accumulation factors (RAF), PCA-derived gradients, and site-level metadata with Random Forest and Gradient Boosting models. ML algorithms achieved high predictive performance (R² up to 0.91), accurately estimating moss metal concentrations from deposition metrics and environmental variables. SHAP feature-importance analysis identified dry deposition load and co-occurring metal signals as the dominant predictors of contamination, confirming the primary role of particulate emissions in shaping moss chemistry. Compared with classical threshold-based classification, the ML approach improved high-risk site identification by 24–38%. Mosses ML combines biologically meaningful indicators with modern computational tools, strengthening the role of mosses as early-warning systems for atmospheric pollution. The framework is broadly applicable to bryophyte biomonitoring and supports regulatory decision-making for emerging contaminants.

Abstract: New methods are needed to monitor environmental treaties, like the Montreal Protocol, by reviewing large, complex customs datasets. This paper introduces a framework using unsupervised machine learning to systematically detect suspicious trade patterns and highlight activities for review. Our methodology, applied to 100,000 trade records, combines several ML techniques. Unsupervised Clustering (K-Means) discovers natural trade archetypes based on shipment value and weight. Anomaly Detection (Isolation Forest and IQR) identifies rare "mega-trades" and shipments with commercially unusual price-per-kilogram values. This is supplemented by Heuristic Flagging to find tactics like vague shipment descriptions. These layers are combined into a priority score, which successfully identified 1,351 price outliers and 1,288 high-priority shipments for customs review. A key finding is that high-priority commodities show a different and more valuable value-to-weight ratio than general goods. This was validated using Explainable AI (SHAP), which confirmed vague descriptions and high value as the most significant risk predictors. The model's sensitivity was validated by its detection of a massive spike in "mega-trades" in early 2021, correlating directly with the real-world regulatory impact of the US AIM Act. This work presents a repeatable unsupervised learning pipeline to turn raw trade data into prioritized, usable intelligence for regulatory groups.

Abstract: Sabalan Dam Lake, located at ~4,800 m above sea level in northwestern Iran, serves as a strategic freshwater source for Ardabil Province. Despite its high-altitude and volcanic setting, recent evidence suggests emerging water quality degradation due to a combination of geogenic and anthropogenic stressors. This study presents the first integrated assessment of pollution status, sources, and spatial distribution in the lake and its inflowing rivers during the spring season. Water samples from nine representative stations were analyzed for physicochemical, microbiological, and heavy metal parameters (Pb, Cd, Zn, Cu), and results were evaluated against WHO, EPA, and Iranian national standards. GIS-based spatial interpolation was employed to identify pollution hotspots and link them to potential sources. Findings revealed that while most physicochemical parameters remained within permissible limits, lead (28.85–62.72 µg/L) and cadmium (11–23.94 µg/L) concentrations exceeded WHO and EPA thresholds by 2–8 times across all stations attributed to natural leaching from Sabalan’s andesitic-basaltic formations and anthropogenic inputs from upstream rural settlements. Microbiological contamination was widespread, with total coliforms (260–1,100 MPN/100mL) and fecal coliforms (0–1,150 MPN/100mL) indicating significant fecal intrusion, particularly near villages and livestock areas. The lake has shifted from an oligotrophic to a mesotrophic state (mean TP ≈ 20 µg/L), signaling early eutrophication. Spatial analysis identified three critical hotspots (Stations 2, 6, and 8) where geogenic metal release and rural pollution converge. These results challenge the assumption that high-altitude lakes are inherently pristine and underscore the dual vulnerability of volcanic reservoirs to natural and human-induced pressures. We recommend a dual-track management strategy: (1) geochemical mitigation (e.g., lime softening to reduce metal bioavailability) and (2) source control (e.g., decentralized wastewater systems, livestock exclusion zones). This study provides a replicable framework for assessing data-scarce, high-elevation reservoirs in arid and semi-arid regions globally.

Abstract: Plastic pollution is a global challenge. Despite plastics being complex chemical mixtures, hazard research has focused on particulate forms and the risks of plastics additives, especially for environmental organisms, remain poorly understood. This is a significant knowledge gap considering ubiquitous organismal exposure to plastics and the associated 16 000+ additives. The aim of this study was to provide ecotoxicological characterization of aqueous eluates of foamed plastic consumer products and propose a test battery for toxicity screening. For that, hazard of eluates of six randomly selected foamed plastic products was evaluated using aquatic decomposers, autotrophs and heterotrophs (Vibrio fischeri, Raphidocelis subcapitata, Lemna minor, Thamnocephalus platyurus, Heterocypris incongruens, Daphnia magna). Alarmingly, all plastic eluates affected the organisms, though toxicity varied among materials and species. Results showed that short-term contact may underestimate plastic eluate toxicity. To increase environmental relevance of hazard assessment of foamed plastic eluates, harmonizing leachate preparation, using natural water and avoiding (excessive) filtration of eluates should be considered. OECD/ISO assays with R. subcapitata, H. incongruens and D. magna (96 h) can be recommended as a minimal sensitive battery for effective screening of plastic eluate toxicity.

Abstract:

Wetlands are delicate ecosystems that host diverse species and face ongoing environmental stress. The “Carlos Anwandter” Ramsar Site in Valdivia, Chile, is the world’s main breeding ground for the black-necked swan, which strongly relies on the aquatic plant Egeria densa. This plant has been impacted by deposition of particulate iron (Fe) and zinc (Zn). However, current methodological approaches typically remove particulate matter during sample pre-treatment through washing, following agricultural plant-tissue protocols. This study aimed to evaluate how sample treatments and plant sectioning affect Fe and Zn concentrations in E. densa. Samples were collected from both the Ramsar site (Cruces River) and a control site (Calle-Calle River). Results showed that washing samples (both in the field and lab) significantly reduced reported metal concentrations, underscoring the importance of standardized sampling and pre-treatment protocols. Fe concentrations were notably higher at the Ramsar site (11,155 mg kg^-1) compared to the control (3,783 mg kg^-1). The same is true for Zn (108 mg kg^-1 and 60 mg kg^-1, respectively). Over time, Fe concentrations remained stable, while Zn concentrations declined, suggesting a consistent Fe input and a decreasing Zn trend in the wetland. These findings are crucial for interpreting metal pollution and understanding spatial-temporal variability in aquatic plant contamination.

Abstract: Air quality prediction is critical for public health management and environmental policymaking, as poor air quality contributes to respiratory diseases, cardiovascular conditions, and premature mortality. Previous research has demonstrated that machine learning models can effectively forecast air quality indices by capturing complex relationships between meteorological variables and pollutant concentrations, with ensemble methods consistently outperforming traditional linear approaches. This study aims to develop and evaluate predictive models for daily Air Quality Index (AQI) in Cook County, Illinois, to support proactive environmental health interventions. Daily air quality data spanning from January 2015 to October 2025 were obtained from the EPA Air Quality System, encompassing 20 environmental parameters including PM2.5, ozone, nitrogen dioxide, and meteorological conditions. The dataset was enhanced through feature engineering, creating 50+ features including temporal patterns, lag variables, rolling averages, and interaction terms. Eleven machine learning models were trained and evaluated, ranging from traditional regression algorithms to advanced ensemble methods (XGBoost) and deep learning architectures (MLP, LSTM). XGBoost with hyperparameter tuning emerged as the best-performing model, achieving 88.4% variance explanation (R²=0.8842) with a mean absolute error of 7.28 AQI points. Feature importance analysis revealed that ozone, PM2.5, and nitrogen dioxide were the strongest predictors, with temporal lag features significantly improving model accuracy. These findings enable environmental agencies to implement early warning systems for poor air quality days, optimize sensor deployment strategies across Cook County's 155 monitoring sites, and develop targeted interventions during high-risk periods such as summer months when ozone levels peak.

Abstract: Mesoporous TiO2 microspheres with a large surface area were synthesized via a hydrothermal reaction using titanium glycolate. The samples were subsequently subjected to different vacuum oven treatment times (2, 4, 6, and 8 hours), resulting in Ti³⁺ self-doping. Comprehensive characterization was performed using transmission electron microscopy (TEM), X-ray diffraction (XRD), and X-ray photoelectron spectroscopy (XPS). The synthesized TiO2 microspheres exhibited significantly enhanced photocurrent and efficient photocatalytic activity under visible light irradiation, demonstrating their potential for applications in solar-driven water splitting. The results highlight the influence of Ti³⁺ self-doping on improving the photoactivity and photosensitivity of the material.

Abstract:

The competition for desalination is currently underway. A mere decade ago, nations within the Maghreb region and, rather unexpectedly, European countries, were fortunate enough to evade humanity's primary adversary: drought. However, the unpredictable nature of climate change has since altered this reality. Consequently, an increasing number of countries are contemplating the serious prospect of utilizing desalination to fulfill their potable water requirements from the seas and oceans bordering their coastlines. Regrettably, research and experience have indicated that highly saline water presents a significant threat to marine ecosystems. This scholarly investigation aims to contribute to the discovery of a solution that will enable the continuation of seawater desalination without inflicting harm on the marine flora and fauna, and this work can be considered as a prototype that need to be studied closely, because the results are here and undeniable, plus this is all what we going to need more and more in near future, namely water and energy.

Abstract: Rural and agricultural runoff continues to pose a threat to water quality and human health despite a plethora of research identifying likely causes. Large livestock operations and leaking septic systems have proven to be significant sources of both nutrients and bacteria in the form of algal blooms and antibiotic-resistant Escherichia coli. Many times, these impacts are witnessed on a watershed scale. Implementing remedies are complicated by livestock operations defined as point source facilities under the USA Clean Water Act (CWA) but regulated as non-point source agricultural runoff. Additionally, the State of Michigan is the only state in the USA without a comprehensive rural septic system law. Pollutant assessment of watersheds involves a wide array of sampling parameters that focus primarily on impacts after-the-fact. Non-point source pollution, particularly in rural areas, lacks regulatory teeth; this watershed management approach is not sustainable as evidenced by continual degradation of our rural watersheds. This study lays out a streamlined methodology incorporating focused parameters that can infer pollutant pathways and processes. We illustrate the methodology using data collected in the Pine River watershed (central Michigan) where multiple pollutant inputs were defined as exceeding water quality standards in channels and reservoirs. The results of this work beg for better understanding of what should be defined as sustainable and unsustainable land use/watershed management. Using simplified field and laboratory techniques, it is possible for local communities, educational institutions, and regulatory agencies to identify likely pollutant sources violating water quality standards regardless of point or nonpoint designation.

Abstract: Plastics are accumulating in the environment, and due to their extremely low biodegradability, this issue is expected to persist for centuries. Historically, oceans were used as dumping grounds for waste, leading to the accumulation of long-lasting materials that now cause severe pollution problems. Macro- and microplastic waste pose serious environmental, social, and economic threats, such as injuring or killing marine organisms and entering the food chain, resulting in potential health risks for humans. Microplastics have become one of the most critical global concerns, as they disrupt the balance of terrestrial and marine ecosystems. The growing presence of microplastics in the environment threatens biodiversity and endangers vulnerable marine species. Moreover, their ingestion by marine organisms can impact the entire food chain, affecting both wildlife and human health. Addressing this challenge requires the development of efficient and sustainable solutions for the control and mitigation of microplastics. This study focuses on the advancement of filtration processes and membrane technologies specifically designed to capture and remove microplastics based on their size, quantity, and origin. By evaluating the performance and suitability of various filtration methods, this research seeks to promote effective recovery, control, and final elimination of microplastics while increasing awareness of sustainable environmental management practices.

Abstract: The Eastern Mediterranean is a rapidly warming climate-change hotspot where heat and air pollution increasingly interact to affect human health. This study quantifies the mortality burden attributed to the synergistic effects of thermal stress and air pollution in Thessaloniki, Greece. Daily mortality data (2001–2019) were analyzed together with pollutant concentrations (PM10, NO₂, O₃) and the modified Physiologically Equivalent Temperature (mPET) using a hierarchical Generalized Additive Model with Distributed Lag Non-Linear terms to capture combined, lagged, and age-specific responses. A re-fined, count-independent definition of the Attributable Fraction (AF) was introduced to improve stability in small strata. Results show that heat and pollution act synergistically, explaining on average 20–30% of daily mortality during severe co-occurrence events. Seniors were most affected during hot, polluted summers (AF ≈ 27%), while adults showed higher burdens during cold, polluted winters (AF ≈ 30%). Intra-urban analyses revealed stronger compound effects in the western, more industrial districts, reflecting combined environmental and socioeconomic vulnerability. The findings demonstrate that temperature extremes amplify pollution-related mortality and underline the need to integrate air-quality and bioclimatic indicators into early-warning and adaptation systems in Eastern Mediterranean cities.

Abstract: Microplastics represent an emerging threat to marine ecosystems, human health, and coastal aesthetics, with increasing concern about their accumulation on beaches due to ocean currents, wave action, and accidental spills. Despite their environmental impact, current methods for detecting and quantifying microplastics remain largely manual, time-consuming, and spatially limited. In this study, we propose a deep learning-based approach for the semantic segmentation of microplastics on sandy beaches, enabling pixel-level localization of small particles under real-world conditions. Twelve segmentation models were evaluated, including U-Net and its variants (Attention U-Net, ResUNet), as well as state-of-the-art architectures such as LinkNet, PAN, PSPNet, and YOLOv11 with segmentation heads. Models were trained and tested on augmented data patches, and their performance was assessed using Intersection over Union (IoU) and Dice coefficient metrics. LinkNet achieved the best performance with a Dice coefficient of 80% and an IoU of 72.6% on the test set, showing superior capability in segmenting microplastics even in the presence of visual clutter such as debris or sand variation. Qualitative results support the quantitative findings, highlighting the robustness of the model in complex scenes.

Abstract: Wastewater treatment systems retain a significant proportion of microplastics (MPs) derived from domestic and industrial discharges; however, these emerging pollutants are not completely removed and tend to accumulate in the biological sludge generated during the treatment process. In this study, three biological-type wastewater treatment plants (WWTPs) located in Acapulco, Mexico, were analyzed. The concentrations of MPs in the biological sludge ranged from 830 to 9,300 items per liter. Using differential scanning calorimetry (DSC), the predominant polymers identified were high-density polyethylene (HDPE), polyethylene terephthalate (PET), and polypropylene (PP). It was estimated that the monthly concentrations of MPs in the sludge could reach up to 5.36 × 109 items/liter, while the annual concentrations could rise to 3.55 × 1010 items/liter. These findings highlight the urgent need to review and update the regulatory framework re-lated to the use of residual sludge for agricultural purposes since high loads of MPs and their transfer pose a potential risk to soil quality, ecosystem health, and long-term en-vironmental sustainability.

Abstract: Liepāja Lake, a Natura 2000 protected area and one of the largest coastal freshwater bodies in Latvia, has been historically influenced by urbanization, diffuse agricultural inputs, and legacy contamination from metallurgy and ship-repair industries. Comprehensive, spatially explicit data on its sediment and water chemistry have previously been lacking. This dataset provides an openly accessible record of major and trace element concentrations in surface sediments and surface waters collected during the 2024 field campaign. Sampling sites were distributed across northern, central, and southern zones to capture gradients in anthropogenic pressure and natural variability. Water samples were filtered and acidified following ISO 15587-2:2002, while sediments were homogenized, sieved, and digested following and EPA 3051a. Both matrices were analyzed using Inductively Coupled Plasma Mass Spectrometry (ICP-MS, Agilent 8900 ICP-QQQ) with multi-element calibration traceable to NIST standards. The dataset comprises 31 analytes (Li–Bi) with paired standard deviation values, reported in mg kg⁻¹ (sediments) and µg L⁻¹ (water). Rigorous validation included certified reference materials, duplicates, blanks, and statistical outlier screening. The resulting data form a reliable geochemical baseline for assessing pollution sources, quantifying spatial heterogeneity, and supporting future monitoring, modelling, and restoration efforts in climate-sensitive Baltic coastal lakes.

Abstract: Injectable Permeable Reactive Barriers (IPRBs) represent a promising in-situ technology for groundwater remediation, with sustainable adsorbents like biochar offering an alternative to activated carbon. This study optimized an IPRB process using a colloidal suspension of pinewood biochar stabilized with sodium carboxymethylcellulose (BC@CMC). The research first characterized the suspension stability under varying hydrochemical conditions, finding optimal colloidal stability at neutral to basic pH (6-9.4), while high ionic strength (>50 mM NaCl) and extreme pH values prompted aggregation. To enable effective delivery, pre-filtration through a 64-µm sieve was implemented, preventing column clogging and facilitating successful deep-bed distribution. The BC concentration was optimized to 3 g L⁻¹, maximizing injectable adsorbent mass. Batch adsorption tests demonstrated the biochar's high affinity for toluene (TOL) and tetrachloroethylene (PCE), with performance comparable to commercial activated carbon, particularly for PCE. The complete IPRB process was successfully validated through continuous-flow adsorption tests, where columns containing distributed BC@CMC showed high contaminant retention, with experimental retardation factors (Rₓ) of 144 ± 4 for TOL and 360 ± 6 for PCE. The study confirms that the optimized BC@CMC suspension enables highly efficient IPRB implementation, establishing this approach as a viable and sustainable strategy for field-scale groundwater remediation.

Abstract: Air pollution monitoring systems use distributed sensors to record dynamic environmental conditions, often producing large volumes of heterogeneous and stochastic data. Efficient aggregation of this data is essential for reducing communication overhead while maintaining the quality of information for decision making. In this paper, we propose an AI-based approach for soft clustering of sensors in air pollution monitoring systems. Our method utilizes the Expectation-Maximization algorithm, an unsupervised machine learning method from the family of probabilistic techniques, to cluster sensors into distinct sets corresponding to normal and polluted zones. This clustering is driven by the need for a dynamic data transmission policy: sensors in polluted zones must intensify their operation for detailed monitoring, while sensors in clean zones can reduce reporting rates and transmit condensed data summaries to alleviate network load and conserve energy. The cluster membership probability enables a tunable trade-off between data redundancy and monitoring accuracy. The high efficiency of the proposed AI-based clustering is validated by the simulation results. The presented approach provides a foundation for a wide range of intelligent and adaptive data aggregation protocols.

Abstract: Microplastic pollution in freshwater systems represents a growing environmental concern, yet the dynamics of microplastic distributions in smaller tributaries like canals/creeks remain understudied. This case study presents an investigation of microplastic contamination in a canal-system in upstate New York, USA, examining land use and rainfall that influence microplastic abundance, distribution, and characteristics. Water and sediment samples were collected bi-weekly (June–October 2023) from sites representing runoff from diverse land-use types: agricultural areas, residential zones, academic buildings, and parking lots. The study reveals significant land-use dependent variations in contamination, with mean concentrations of 17 ± 7 items/L in the water column, while suspended sediment and bedload reached 540 ± 230 items/L and 370 ± 80 items/kg, respectively. Upstream water column exhibited the highest loads (27 ± 2 items/L), driven by cumulative agricultural and commercial inputs, while downstream declines highlighted vegetation-mediated sedimentation. Land-use patterns strongly influenced contamination profiles, with parking lots exhibiting tire-wear fragments, artificial turf contributing polyethylene particles, and residential areas contributing 43% textile fibers. Rainfall intensity and antecedent dry days differentially influenced transport mechanisms. Antecedent dry days strongly predicted parking lot runoff fluxes surpassing rainfall intensity effects and underscored impervious surfaces as transient microplastic reservoirs.

Abstract:

This study assessed the spatial distribution and composition of airborne particulate matter within a 10-km long urban green corridor in Zacatecas, Mexico, using magnetic biomonitoring with Tillandsia recurvata and SEM-EDS particle characterization. A total of 44 samples were collected from distinct urban park contexts (e.g., commercial zones, malls, bus stop), revealing mass-specific magnetic susceptibility χ values ranging from 0.87 to 97.0 × 10⁻⁸ m³kg⁻¹. Three compositional groups were identified based on a PCA performed using elemental concentrations from SEM-EDS and magnetic data, which are associated with traffic emissions and industrial inputs. SEM-EDS images confirmed abundant magnetite-like particles (1–8 μm) with hazardous metals including Pb (up to 5.6 wt.%), Ba (up to 67.6 wt.%), and Cr (up to 31.5 wt.%). Wind direction data indicated predominant SSW-NNE transport, correlating with hotspots in central and northeastern park areas. Overall, vegetated zones displayed significantly lower magnetic loads (mean χ = 8.84 × 10⁻⁸ m³kg⁻¹, σ = 6.65 × 10⁻⁸ m³kg⁻¹) compared to traffic-exposed sites (mean χ = 17.27 × 10⁻⁸ m³kg⁻¹, σ = 12.44 × 10⁻⁸ m³kg⁻¹), emphasizing the pollution mitigation role of green barriers. This research highlights the applicability of combined magnetic and microscopic techniques for evaluating the dynamics of airborne pollution in urban parks and supports their use as biofunctional filters in cities facing vehicular air pollution.

Abstract: The systemic toxicities and cellular responses triggered by ethylparaben were evaluated in the roots of cenoura, tomate, and pepino seeds, in the roots of cebola bulbs, and in Eisenia fetida earthworms, at 1, 10, 100, and 1000 ng.L-1. In plants, concentrations significantly altered catalase activity, ascorbate peroxidase, guaiacol peroxidase, and superoxide dismutase. In carrot (10, 100, and 1000 ng.L-1), tomato (1000 ng.L-1), and cucumber (all concentrations) caused lipid peroxidation. Oxidative radicals produced caused a delay in the progression of the cell cycle and cellular changes in the root meristems, significantly inhibiting roots growth in the plants evaluated. In earthworms, ethylparaben caused a dose-dependent pattern of aversion to the treated soil, which at 1000 ng.L-1 was 90%, characterizing high repellency with habitat loss. Earthworms had no mortality after 14 days of an acute exposure to ethylparaben. Catalase, ascorbate peroxidase, and guaiacol peroxidase were significantly inhibited at the 10 ng.L-1 concentration, and all concentrations caused lipid peroxidation, which results in tissue damage and can substantially impact the survival and ecological functions of these organisms. Therefore, recurrent contamination with ethylparaben can negatively affect soil quality, impacting crop productivity and the ecological sustainability of agricultural landscapes.

Abstract: The global trade in electronic and electrical goods is complicated by the challenge of identifying e-waste, which is often misclassified to evade regulations. Traditional analysis methods struggle to discern the underlying patterns of this illicit trade within vast datasets. This research proposes and validates a robust, data-driven framework to segment products and identify goods exhibiting an anomalous "waste signature" a trade pattern defined by a clear 'inverse price-volume'. The core of the framework is an Outlier-Aware Segmentation method, an iterative K-Means approach that first isolates extreme outliers to prevent data skewing and then re-clusters the remaining products to reveal subtle market segments. To quantify risk, a "Waste Score" is developed using a Logistic Regression model that identifies products whose trade signatures are statistically similar to scrap. The findings reveal a consistent four-tier market hierarchy in both Malaysian and global datasets. A key pattern emerged from a comparative analysis: Malaysia's market structure is defined by high-volume bulk commodities, whereas the global market is shaped by high-value capital goods, indicating a unique national specialization. The framework successfully flags finished goods, such as electric generators (HS 8502), that are traded like scrap, providing a targeted list for regulatory scrutiny.