Search Results (2,854)

Accurate and efficient surface water quality monitoring is essential for ecological protection and sustainable development. However, conventional monitoring methods, such as fixed-site observations, often suffer from spatial limitations and overlook crucial auxiliary variables. This study proposes an innovative modeling framework for large-scale river water quality inversion that integrates multi-source data—including Sentinel-2 imagery, meteorological conditions, land use classification, and landscape pattern indices. To improve predictive accuracy, three tree-based machine learning models (Random Forest, XGBoost, and LightGBM) were constructed and further optimized using the Whale Optimization Algorithm (WOA), a nature-inspired metaheuristic technique. Additionally, model interpretability was enhanced using SHAP (Shapley Additive Explanations), enabling a transparent understanding of each variable’s contribution. The framework was applied to the Red River Basin (RRB) to predict six key water quality parameters: dissolved oxygen (DO), ammonia nitrogen (NH₃-N), total phosphorus (TP), total nitrogen (TN), pH, and permanganate index (COD_Mn). Results demonstrate that integrating landscape and meteorological variables significantly improves model performance compared to remote sensing alone. The best-performing models achieved R² values exceeding 0.45 for all parameters (DO: 0.70, NH₃-N: 0.46, TP: 0.59, TN: 0.71, pH: 0.83, COD_Mn: 0.57). Among them, WOA-optimized LightGBM consistently delivered superior performance. The study also confirms the feasibility of applying the models across the entire basin, offering a transferable and interpretable approach to spatiotemporal water quality prediction in other large-scale or data-scarce regions. Full article

Driven by the globalization tide, urbanization and cross-border economic cooperation have intensified challenges to ecological conservation, with border regions increasingly confronting irreversible habitat degradation risks. As a globally recognized biodiversity hotspot, Xishuangbanna acts as a strategic hub for cross-border ecological security between China and Southeast Asia, having long been confronted with dual pressures from economic development and ecological conservation. By analyzing the spatiotemporal evolution of the Remote Sensing Ecological Index (RSEI) during 2003–2023, this study simulates its multi-scenario dynamics, develops the “RSEI-ESP-PLUS” framework, presents a novel assessment mechanism for ecological security patterns (ESP), and provides a scientific basis for regional sustainable development. Results indicate that integrating RSEI improves the accuracy of ecological source identification. Over the past two decades, regional Ecological Environmental Quality has exhibited an overall improvement trend, yet persistent ecological pressures remain—including vegetation degradation and climate warming. Concurrently, high-quality ecological areas have contracted while moderate-quality ones have expanded. In the 2033 simulation, the ecological conservation scenario delivered the most favorable ecological network assessment outcomes, identifying 16 stable and 15 potential ecological sources. Accordingly, this study establishes an ecological security pattern centered on the core structure of the “One Axis, Two Corridors, and Three Zones”, which provides a spatial planning scheme for regional sustainable development. Full article

This paper explores the intersection of digital technologies, sustainable agriculture, and biodiversity conservation within the framework of the European Green Deal. The study investigates how intelligent agricultural practices—enabled by digital tools such as sensors, AI, and IoT—can enhance soil health and conserve agrobiodiversity. A systematic literature review was conducted to map out current research trajectories, identify the taxonomic focus areas in biodiversity monitoring, and assess the integration of digital tools. Results show a significant upward trend in publications linking digitalization and sustainability in agriculture. Findings highlight that pollinators and soil biota dominate monitoring focus, while technologies like remote sensing and AI show increasing adoption. The study concludes that intelligent agriculture offers a path toward ecological and economic resilience in rural landscapes, aligning with the EU’s green transition agenda. Full article

This follow-up study investigates the long-term environmental sustainability and remediation outcomes of the UPPER (‘Urban Productive Parks for Sustainable Urban Regeneration’-UIA04-252) project in Latina, Italy, focusing on Nature-Based Solutions (NbS) applied to urban green infrastructure. By integrating proximal and satellite-based remote sensing methodologies, the research evaluates persistent improvements in vegetation health, soil moisture dynamics, and overall environmental quality over multiple years. Building upon the initial monitoring framework, this case study incorporates updated data and refined techniques to quantify temporal changes and assess the ecological performance of NbS interventions. In more detail, ground-based data from meteo-climatic, air quality stations and remote satellite data from the Sentinel-2 mission are adopted. Ground-based measurements such as temperature, humidity, radiation, rainfall intensity, PM10 and PM2.5 are carried out to monitor the overall environmental quality. Updated satellite imagery from Sentinel-2 is analyzed using advanced band ratio indices, including the Normalized Difference Vegetation Index (NDVI), the Normalized Difference Water Index (NDWI) and the Normalized Difference Moisture Index (NDMI). Comparative temporal analysis revealed consistent enhancements in vegetation health, with NDVI values significantly exceeding baseline levels (NDVI 2022–2024: +0.096, p = 0.024), demonstrating successful vegetation establishment with larger gains in green areas (+27.0%) than parking retrofits (+11.4%, p = 0.041). However, concurrent NDWI decline (−0.066, p = 0.063) indicates increased vegetation water stress despite irrigation infrastructure. NDMI improvements (+0.098, p = 0.016) suggest physiological adaptation through stomatal regulation. Principal Component Analysis (PCA) of meteo-climatic variables reveals temperature as the dominant environmental driver (PC2 loadings > 0.8), with municipality-wide NDVI-temperature correlations of r = −0.87. These multi-scale findings validate sustained NbS effectiveness in enhancing vegetation density and ecosystem services, yet simultaneously expose critical water-limitation trade-offs in Mediterranean semi-arid contexts, necessitating adaptive irrigation management and continued monitoring for long-term urban climate resilience. The integrated monitoring approach underscores the critical role of continuous, multi-scale assessment in ensuring long-term success and adaptive management of NbS-based interventions. Full article

The ongoing advance of urbanization has increased the need for accurate monitoring of urban green space (UGS). However, existing remote-sensing UGS mapping still struggles with inconsistent data quality, diverse urban forms, and limited cross-city generalization. This study focuses on China’s Guangdong-Hong Kong-Macao Greater Bay Area as its research region, establishing a fully automated UGS mapping framework based on Sentinel-2 time-series imagery and standardized OpenStreetMap (OSM) data. This process achieves UGS mapping at 10 m resolution for 16 cities within the metropolitan area through a dynamic standardized OSM tagging system, a Sentinel-2 satellite image sample generation mechanism integrating spectral and textural features, multidimensional sample quality assessment and weighting strategies, as well as balanced cross-city sampling and weighted SVM classification. The results demonstrate that this method exhibits stable performance across multiple urban environments, achieving an average overall accuracy of approximately 0.83 and an average F1 score of approximately 0.82. The highest recorded F1 score reaches 0.96, highlighting the method’s strong generalization capability under diverse urban conditions. The mapping results reveal significant disparities in UGS distribution within the Guangdong-Hong Kong-Macao Greater Bay Area, reflecting the combined effects of varying urban development patterns and ecological contexts. The unified workflow proposed in this study demonstrates strong applicability in handling heterogeneous urban structures and enhancing cross-regional comparability. It provides consistent, transparent, and reusable foundational data for regional eco-urban planning, urban green infrastructure development, and policy evaluation. Full article

Against the backdrop of rapid urbanization and land development, the degradation of regional ecosystem services and the intensification of ecological risks have become prominent challenges. This study takes the Pinglu Canal Economic Belt—a region characterized by the triple pressures of “large-scale engineering disturbance, karst ecological vulnerability, and port economic agglomeration”—as a case study. Based on remote sensing image data from 2000 to 2020, a landscape ecological risk index was constructed, and regional landscape ecological risk levels were assessed using ArcGIS spatial analysis tools. On this basis, ecological sources were identified by combining the InVEST model with morphological spatial pattern analysis (MSPA),and an ecological resistance surface was constructed by integrating factors such as land use type, elevation, slope, distance to roads, distance to water bodies, and NDVI. Furthermore, the circuit theory method was applied to identify ecological corridors, ecological pinch points, and barrier points, ultimately constructing the ecological security pattern of the Pinglu Canal Economic Belt. The main findings are as follows: (1) Ecological risks were primarily at low to medium levels, with high-risk areas concentrated in the southern coastal region. Over the past two decades, an overall optimization trend was observed, shifting from high risk to lower risk levels. (2) A total of 15 ecological sources (total area 1313.71 km²), 31 ecological corridors (total length 1632.42 km), 39 ecological pinch points, and 15 ecological barrier points were identified, clarifying the key spatial components of the ecological network. (3) Based on spatial analysis results, a zoning governance plan encompassing “ecological protected areas, improvement areas, restoration areas, and critical areas” along with targeted strategies was proposed, providing a scientific basis for ecological risk management and pattern optimization in the Pinglu Canal Economic Belt. Full article

Remote sensing building change detection (RSBCD) is critical for land surface monitoring and understanding interactions between human activities and the ecological environment. However, existing deep learning-based RSBCD methods often result in mis-detected pixels concentrated around object boundaries, mainly due to ambiguous object shapes and complex spatial distributions. To address this problem, we propose a new Multiscale Edge-Aware change detection Network (MEANet) that accurately locates edge pixels of changed objects and enhances the separability between changed and unchanged pixels. Specifically, a high-resolution feature fusion network is adopted to preserve spatial details while integrating deep semantic information, and a multi-scale supervised contrastive loss (MSCL) is designed to jointly optimize pixel-level discrimination and embedding space separability. To further improve the handling of difficult samples, hard negative sampling is adopted in the contrastive learning process. We conduct comparative experiments on three benchmark datasets. Both Visual and quantitative results demonstrate that our new MEANet significantly reduces misclassified pixels at object boundaries and achieve superior detection accuracy compared to existing methods. Especially on the GZ-CD dataset, MEANet improves F1-Score and mIoU by more than 2% compared with ChangeFormer, demonstrating strong robustness in complex scenarios. It is worth noting that the performance of MEANet may still be affected by extremely complex edge textures or highly blurred boundaries. Future work will focus on further improving robustness under such challenges and extending the method to broader RSBCD scenarios. Full article

Freshwater ecosystems are increasingly threatened by pollution, hydromorphological alteration, invasive species, and loss of ecological connectivity, complicating the monitoring and conservation of native fish communities. Environmental DNA (eDNA) has emerged as a sensitive, non-invasive, and cost-effective tool for detecting species, including rare or low-abundance taxa, overcoming several limitations of traditional methods. However, its rapid expansion has generated methodological dispersion and heterogeneity in protocols. This systematic review and bibliometric analysis synthesize 131 articles published between 2020 and 2025 on the use of eDNA in freshwater fish conservation. Due to the strong methodological heterogeneity among studies, the evidence was synthesized through a structured qualitative approach under PRISMA standards. Results show rapid growth in scientific output since 2023. eDNA has proven highly effective in identifying key ecological patterns such as migration and spawning, detecting critical habitats, and supporting temporal and spatial assessments. It has also facilitated early detection of invasive species including Oreochromis niloticus, Oncorhynchus gorbuscha, and Chitala ornata, and improved monitoring of threatened native species, reinforcing conservation decision-making. Despite advances, challenges persist, including variability in eDNA persistence and transport, gaps in genetic reference databases, and a lack of methodological standardization. Future perspectives include detecting parasites, advancing trophic analyses, and integrating eDNA with ecological modeling and remote sensing. Full article

In struggling against invasive species ravaging riverscape ecosystems, gaps in dispersal pathway knowledge and fragmented approaches across scales have long stalled effective riparian management worldwide. To reduce these limitations and enhance invasion management strategies, selecting appropriate alien species as models for in-depth pathway analysis is essential. Alternanthera philoxeroides (Mart.) Griseb. (alligator weed) emerges as an exemplary model species, boasting an invasion record of around 120 years spanning five continents worldwide, supported by genetic evidence of repeated introductions. In addition, the clonal reproduction of A. philoxeroides supports swift establishment, while its amphibious versatility allows occupation of varied riparian environments, with spread driven by natural water-mediated dispersal (hydrochory) and human-related vectors at multiple scales. Thus, leveraging A. philoxeroides, this review proposes a comprehensive multi-scale framework, which integrates monitoring with remote sensing, environmental DNA, Internet of Things, and crowdsourcing for real-time detection. Also, the framework can further integrate, e.g., MaxEnt (Maximum Entropy Model) for climatic suitability and mechanistic simulations of hydrodynamics and human-mediated dispersal to forecast invasion risks. Furthermore, decision-support systems developed from the framework can optimize controls like herbicides and biocontrol, managing uncertainties adaptively. At the global scale, the dispersal paradigm can employ AI-driven knowledge graphs for genetic attribution, multilayer networks, and causal inference to trace pathways and identify disruptions. Based on the premise that our multi-scale framework can bridge invasion ecology with riverscape management using A. philoxeroides as a model, we contend that the implementation of the proposed framework tackles core challenges, such as sampling biases, shifting environmental dynamics, eco–evolutionary interactions using stratified sampling, and adaptive online algorithms. This methodology is purposed to offer scalable tools for other aquatic invasives, evolving management from reactive measures to proactive, network-based approaches that effectively interrupt dispersal routes. Full article

Horse flies (Tabanidae) negatively affect livestock by reducing productivity, compromising animal welfare, and serving as mechanical vectors of pathogens. However, the spatial processes shaping their community organization in southern Brazil’s Coastal Plain of Rio Grande do Sul (CPRS) remain poorly understood. To address this, we conducted standardized Malaise-trap surveys and combined them with historical–contemporary comparisons to examine distance–decay patterns in community composition. We evaluated both abundance-based (Bray–Curtis) and presence–absence (Jaccard) dissimilarities using candidate models. Across sites, Tabanus triangulum emerged as the dominant species. Dissimilarity in community structure increased monotonically with geographic distance, with no evidence of abrupt thresholds. The square-root model provided the best fit for abundance-based data, whereas a linear model best described presence–absence patterns, reflecting dispersal limitation and environmental filtering across a heterogeneous coastal landscape. Sites within riparian forests and conservation units displayed higher diversity, emphasizing the ecological role of protected habitats and the importance of maintaining connected corridors. Collectively, these findings establish a process-based framework for surveillance and landscape management strategies to mitigate vector, host contact. Future directions include integrating remote sensing and host distribution, applying predictive validation across temporal scales. Full article

River and lake ice are sensitive indicators of climate change and important components of hydrological and ecological systems in cold regions. In this study, we develop a simple and transferable “surface water + land surface temperature (LST)” framework on Google Earth Engine to map potential winter ice area across China from 1990 to 2020. The framework enables consistent, large-scale, long-term monitoring without relying on complex remote sensing models or region-specific thresholds. Our results show that, despite a pronounced northwestward shift in the freezing-zone boundary, more than 400 km in the Northeast Plain and about 13 km per year along the eastern coast, the total ice-covered area increased by approximately 1.1% per year. At the same time, the average ice season became slightly shorter. This indicates asynchronous spatial and temporal responses of potential winter ice to warming. We identify a persistent “Northwest–Northeast dual-core” spatial pattern with strong positive spatial autocorrelation, characterized by increasing ice cover in Tibet, Qinghai, Xinjiang, Inner Mongolia, and Northeast China, and decreasing ice cover mainly in Beijing and Yunnan, where intense urbanization and low-latitude warming dominate. Random Forest modeling further shows that water area fraction, nighttime lights, built-up area, altitude, and water–heat indices are the main controls on potential winter ice. These findings highlight the combined influence of hydrological and thermal conditions and urbanization in reshaping potential winter ice patterns under climate change. Full article

Coastal wetland vegetation exhibits pronounced spectral mixing, complex mosaic spatial patterns, and small target sizes, posing considerable challenges for fine-grained classification in high-resolution UAV imagery. At present, remote sensing classification of ground objects based on deep learning mainly relies on spectral and structural features, while the frequency domain features of ground objects are not fully considered. To address these issues, this study proposes a vegetation classification model that integrates spatial-domain and frequency-domain features. The model enhances global contextual modeling through a large-kernel convolution branch, while a frequency-domain interaction branch separates and fuses low-frequency structural information with high-frequency details. In addition, a shallow auxiliary supervision module is introduced to improve local detail learning and stabilize training. With a compact parameter scale suitable for real-world deployment, the proposed framework effectively adapts to high-resolution remote sensing scenarios. Experiments on typical coastal wetland vegetation including Reeds, Spartina alterniflora, and Suaeda salsa demonstrate that the proposed method consistently outperforms representative segmentation models such as UNet, DeepLabV3, TransUNet, SegFormer, D-LinkNet, and MCCA across multiple metrics including Accuracy, Recall, F1 Score, and mIoU. Overall, the results show that the proposed model effectively addresses the challenges of subtle spectral differences, pervasive species mixture, and intricate structural details, offering a robust and efficient solution for UAV-based wetland vegetation mapping and ecological monitoring. Full article

Assessing post-fire disturbance in Mediterranean ecosystems is essential for quantifying ecological impacts and guiding restoration strategies. This study evaluates fire severity following an extreme wildfire event (~28,000 ha) in northwestern Spain using vegetation indices (VIs) derived from PRISMA hyperspectral imagery, validated against field-based Composite Burn Index (CBI) measurements at the vegetation, soil, and site levels across three vegetation formations (coniferous forests, broadleaf forests, and shrublands). Hyperspectral VIs were benchmarked against multispectral VIs derived from Sentinel-2. Hyperspectral VIs yielded stronger correlations with CBI values than multispectral VIs. Vegetation-level CBI showed the highest correlations, reflecting the sensitivity of most VIs to canopy structural and compositional changes. Indices incorporating red-edge, near-infrared (NIR), and shortwave infrared (SWIR) bands demonstrated the greatest explanatory power. Among hyperspectral indices, DVIRED, EVI, and especially CAI performed best. For multispectral data, NDRE, CIREDGE, ENDVI, and GNDVI were the most effective. These findings highlight the strong potential of hyperspectral remote sensing for accurate, scalable post-fire severity assessment in heterogeneous Mediterranean ecosystems. Full article

Urban forests and green spaces are increasingly promoted as Nature-Based Solutions (NbS) to mitigate climate risks, enhance human well-being, and support resilient and sustainable cities. Focusing on the theme of optimizing urban green space ecosystem services to foster resilient and sustainable cities, this study systematically analyzes 861 relevant publications indexed in the Web of Science Core Collection from 2005 to 2025. Using bibliometric analysis and scientific knowledge mapping methods, the research examines publication characteristics, spatial distribution patterns, collaboration networks, knowledge bases, research hotspots, and thematic evolution trajectories. The results reveal a rapid upward trend in this field over the past two decades, with the gradual formation of a multidisciplinary knowledge system centered on environmental science and urban research. China, the United States, and several European countries have emerged as key nodes in global knowledge production and collaboration networks. Keyword co-occurrence and cluster analyses indicate that research themes are mainly concentrated in four clusters: (1) ecological foundations and green process orientation, (2) nature-based solutions and blue–green infrastructure configuration, (3) social needs and environmental justice, and (4) macro-level policies and the sustainable development agenda. Overall, the field has evolved from a focus on ecological processes and individual service functions toward a comprehensive transition emphasizing climate resilience, human well-being, and multi-actor governance. Based on these findings, this study constructs a knowledge ecosystem framework encompassing knowledge base, knowledge structure, research hotspots, frontier trends, and future pathways. It further identifies prospective research directions, including climate change adaptation, integrated planning of blue–green infrastructure, refined monitoring driven by remote sensing and spatial big data, and the embedding of urban green space ecosystem services into the Sustainable Development Goals and multi-level governance systems. These insights provide data support and decision-making references for deepening theoretical understanding of Urban Green Space Ecosystem Services (UGSES), improving urban green infrastructure planning, and enhancing urban resilience governance capacity. Full article

Farmland shelterbelts are crucial elements in safeguarding agricultural ecological security and sustainable development, with their precise extraction being vital for regional ecological monitoring and precision agriculture management. However, constrained by their narrow linear distribution, complex farmland backgrounds, and spectral confusion issues, traditional remote sensing methods encounter significant challenges in terms of accuracy and generalization capability. In this study, six representative deep learning semantic segmentation models—U-Net, Attention U-Net (AttU_Net), ResU-Net, U²-Net, SwinUNet, and TransUNet—were systematically evaluated for farmland shelterbelt extraction using high-resolution Gaofen-6 imagery. Model performance was assessed through four-fold cross-validation and independent test set validation. The results indicate that convolutional neural network (CNN)-based models show overall better performance than Transformer-based architectures; on the independent test set, the best-performing CNN model (U-Net) achieved a Dice Similarity Coefficient (DSC) of 91.45%, while the lowest DSC (88.86%) was obtained by the Transformer-based TransUNet model. Among the evaluated models, U-Net demonstrated a favorable balance between accuracy, stability, and computational efficiency. The trained U-Net was applied to large-scale farmland shelterbelt mapping in the study area (Alar City, Xinjiang), achieving a belt-level visual accuracy of 95.58% based on 385 manually interpreted samples. Qualitative demonstrations in Aksu City and Shaya County illustrated model transferability. This study provides empirical guidance for model selection in high-resolution agricultural remote sensing and offers a feasible technical solution for large-scale and precise farmland shelterbelt extraction. Full article