Search Results (4,043)

In July 2024, a major rainfall-induced landslide disaster occurred in Zixing county, Hunan Province, triggering more than 4000 landslides with a total area exceeding 21 km². The scale of this hazard underscores a critical need for long-term stability assessment of the affected slopes. While previous studies have primarily used optical remote sensing to map landslide distributions, quantitative evaluation of post-failure movement dynamics remains limited. This study developed an integrated monitoring framework that combines time-series SBAS-InSAR displacement measurements (using Sentinel-1 data from August 2024 to September 2025) with deep learning-based optical interpretation, rainfall analysis, and geological data. Our approach enables the quantitative, region-scale stability assessment of the Zixing landslide cluster one year after the initial event. Experimental results reveal sustained surface displacement with rates ranging from −30 to 30 mm/year, and localized displacements exceeding 40 mm/year. Notably, over 48% of the mapped landslides are classified as active or critically active, indicating widespread, ongoing instability. Correlation analysis further establishes precipitation as a key driver of accelerated movement. Beyond the Zixing case, this work provides a transferable methodology for assessing long-term post-disaster landslide behavior, offering direct value for regional hazard management and early-warning systems. Full article

Oil spills are severe environmental disasters that cause long-lasting damage to marine ecosystems and impose significant economic costs, underscoring the urgent need for efficient detection and monitoring technologies. Conventional field-based observation methods, while valuable, are constrained by limited spatial coverage, high costs, and labor-intensive processes, making them impractical for large-scale or rapid-response applications. To overcome these challenges, satellite remote sensing has been used as an effective alternative for oil spill monitoring. In particular, the advent of Google Earth Engine (GEE), a cloud-based geospatial platform, has transformed oil spill research by enabling scalable management and analysis of large satellite remote sensing datasets. This review synthesizes studies employing GEE for oil spill detection, across marine environments and interconnected aquatic systems, focusing on methodologies based on optical imagery and synthetic aperture radar data and approaches that integrate machine learning techniques. The analysis underscores that GEE enhances oil spill monitoring by facilitating rapid data processing, supporting reproducible workflows, and expanding access to multi-source satellite data. Furthermore, this review highlights the necessity of incorporating very-high-resolution satellite data and achieving tighter integration of external deep learning framework within GEE to improve detection accuracy and the operational applicability in complex marine and coastal contexts. Full article

Urban road collapses are characterized by sudden occurrence and strong spatial heterogeneity, posing substantial challenges for proactive infrastructure management. Susceptibility mapping can provide spatially explicit evidence to support targeted inspection and early-warning strategies. Using Futian District, Shenzhen (China) as a case study, a total of 315 road collapse events recorded during 2019–2023 were compiled to develop an integrated framework for urban road collapse relative susceptibility mapping based on multi-source remote sensing and urban spatial data. First, an indicator-based susceptibility index (SI) was constructed using eight conditioning factors, including PS-InSAR-derived deformation, topographic–hydrological conditions, and distance-based infrastructure variables (distance to underground utilities, metro lines, and roads). Factor weights were determined by coupling the Analytic Hierarchy Process (AHP) with the Entropy Weight Method (EWM), producing a comprehensive SI for historical collapse locations. Subsequently, a set of 17 remote-sensing predictors, including Sentinel-2 spectral bands, Sentinel-2 GLCM texture features, and Sentinel-1 SAR backscatter variables, was used to train a Random Forest model to predict SI and generate continuous susceptibility maps at the urban road-network scale. The influence of neighborhood window size on predictive performance was systematically evaluated. Results show that the Random Forest model performed best at the 5 × 5 window scale (R² = 0.70, RMSE = 0.0172, MAE = 0.0122), outperforming both pixel-based inputs (1 × 1) and larger windows. Uncertainty analysis further indicated that the 5 × 5 RF configuration yielded the most stable and spatially coherent predictions, whereas overly small windows and less robust learners produced more fragmented or higher-uncertainty susceptibility patterns. Spatiotemporal analysis indicates that susceptibility patterns remained broadly stable from 2019 to 2023, with moderate susceptibility accounting for 50.82–57.89% and high susceptibility for 21.94–23.30%, while very high susceptibility consistently remained below 1%. Overall, this study demonstrates that integrating multi-source remote sensing with scale-optimized machine learning provides an effective approach for fine-scale susceptibility mapping of urban road collapses, offering practical guidance for differentiated monitoring and risk prevention along critical road corridors. Full article

The proposed study investigates the key factors influencing UAV adoption and proposes an integrated educational–operational framework to enhance implementation in agricultural practice. A case study in Sibiu County, Romania, combined survey-based empirical analysis (n = 80), strategic environmental assessment and the deployment of a demonstration aerial crop monitoring system for educational purposes (ACMS-E). We integrated the Technology Acceptance Model (TAM) and Theory of Planned Behavior (TPB) to examine adoption intentions, revealing perceived usefulness (β = 0.355, p = 0.021) and positive attitudes (β = 0.382, p = 0.005) as the strongest predictors, explaining 44.1% of variance. Based on these findings, a modular training curriculum was designed, combining theoretical instruction, flight operation exercises, remote sensing techniques, data analytics and farm-management integration. ACMS-E provides hands-on training and promotes capacity-building, bridging the gap between technological availability and real-world adoption. By linking technological capabilities with structured training, ACMS-E bridges the gap between UAV availability and effective implementation, offering a scalable model for precision agriculture. This framework provides a pathway to accelerate UAV adoption, optimize field-level monitoring and support evidence-based, resource-efficient farm management in emerging and developed agricultural contexts. Full article

Against the background of global climate change and intensified human activities, the Black Soil Region of Northeast China (BSRNC)—an ecologically fragile zone and critical grain-producing area—faces mounting pressures on ecosystem stability, productivity sustainability, and black soil conservation. Clarifying the spatiotemporal evolution characteristics of vegetation net primary productivity (NPP) and its associative patterns is crucial for ecological protection and sustainable land management in this region. Based on remote sensing, meteorological, topographic, soil and human activity data, this study employed the improved Carnegie–Ames–Stanford Approach (CASA) model to quantify vegetation NPP—an analytical approach that integrates the CASA model with tree-based machine learning and SHapley Additive exPlanations (SHAP) interpretation. By further combining multiple spatial analysis methods, it characterizes the spatiotemporal dynamics of NPP in the black soil region and innovatively compares seven machine learning algorithms to select the optimal Light Gradient Boosting Machine (LightGBM) model for quantifying the contributions of drivers in this region with high spatial heterogeneity. The results showed that the average annual vegetation NPP in the BSRNC was 301.18 g C·m⁻², exhibiting a fluctuating upward trend at a rate of 1.55 g C·m⁻²·a⁻¹ over the 24-year period. Spatially, NPP displayed significant heterogeneity, climbing gradually from the region’s southwest to its northeast quadrant, with over 90% of the territory showing an upward trajectory. Overall NPP reached a high stability level, though the western and southern regions faced higher degradation risks, and the entire region presented a weak anti-persistent trend. Precipitation was the dominant factor associated with NPP variations, followed by soil moisture, while soil pH had the smallest correlative contribution (0.38). Land-use changes were positively associated with NPP growth, and the interaction of multiple factors showed a significant associative pattern with NPP variations. This study clarifies the spatiotemporal patterns and associative patterns of vegetation NPP in the BSRNC with a 24-year-long time series, and its incremental findings on the coupling of land-use change and multi-factor interaction provide a targeted scientific basis for ecological protection, restoration policies and sustainable management of black soil resources. Full article

This study used bibliometric methods to systematically analyze the development trend, knowledge structure and evolution path of the field of “quantitative research on agricultural soil respiration based on machine learning” from 2021 to 2025, and further explored its implications for agricultural soil carbon sinks. Based on 966 articles included in the core collection of Web of Science, this paper comprehensively uses tools such as Biblioshiny, CiteSpace and VOSviewer to carry out multi-dimensional analysis from the aspects of annual publication trends, international and institutional cooperation networks, keyword clustering and emergent evolution. It is found that this field has shown phased evolution characteristics of “technology-driven mechanism deepening–application expansion” in the past five years. At the beginning of the 5-year period of research, the introduction of machine learning methods and model verification were the core, then gradually expanding to multi-algorithm comparison, environmental factor coupling mechanisms and multi-source data fusion. Recently, the field has focused on regional-scale simulation, uncertainty quantification and model interpretability research. Keyword clustering identifies three thematic clusters—machine learning algorithm and model optimization, environmental driving factors and process mechanism, and remote sensing fusion and regional application—which form a knowledge system of “method–mechanism–application” collaborative evolution. The national cooperation network presents a pattern of “Asia-led, China–US dual-core, and European connectivity”. China dominates in scientific research output, and the United States plays a key role in international cooperation. This study further points out that the development of this field provides important methodological support and a scientific basis for accurate assessment, intelligent management and carbon neutralization decision-making for agricultural soil carbon sinks. Based on the above findings, future research should focus on the development of intelligent models of mechanisms and data fusion, the construction of multi-source data assimilation and uncertainty assessment frameworks, the expansion of global diversified agricultural system cases, and the promotion of an open and shared international scientific research cooperation ecology. This study provides empirical evidence and a direction reference for academic development, scientific research layout, carbon sink management and international collaboration in this field. Full article

Irrigation-driven greening is essential for northwest China’s dryland ecosystems, where vegetation growth depends on key hydrological factors, including precipitation (PRE), evapotranspiration (ET), soil moisture (SM), and irrigation water use (IWU), which affect water availability to a certain extent. To assess greening sustainability, a 1 km IWU dataset was created for 2001–2022 by combining remote sensing and ancillary data using machine learning, overcoming limited irrigation records. By linking IWU with the normalized difference vegetation index (NDVI) and analyzing trends in irrigated areas, we implemented a regional zonation approach to identify specific risk areas and evaluated both greening sustainability and vegetation responses using water balance (WB) and various hydrological variables. The results show that NDVI has increased widely over the past two decades, with sustained positive WB and stable irrigation, indicating improved water availability. However, spatial differences exist: 35.98% of irrigated areas have rising NDVI but falling IWU, especially in the east, where higher NDVI, IWU, WB, PRE, and ΔSM (soil moisture difference between growing season end and start) reflect favorable climate and hydrology; attention should also be directed toward potential deep percolation and saline sinks. In contrast, areas with high IWU often displayed elevated NDVI but declining water availability, suggesting unsustainable greening due to excessive irrigation. In addition, the SCD_IWU-SCD_NDVI class dominates among significant NDVI-IWU trends, indicating potential for sustainable irrigation under certain drought and climate conditions. Overall, the northwestern portion of the study area exhibits the lowest water availability; cities such as Urumqi warrant particular attention. These findings identify at-risk areas and those with better water resilience, supporting targeted water–vegetation management. Full article

Amid rapid urbanization, the rapid increase in urban vehicles has exacerbated parking scarcity, particularly in areas surrounding hospitals. As the core city of the Huaihai Economic Zone, Xuzhou’s medical institutions serve a broad region spanning 178,000 square kilometers. The pronounced mismatch between parking supply and demand in these areas severely impacts traffic efficiency and public service quality. To address this challenge, this study proposes a data-driven parking resource planning methodology for the identification and planning of informal/shared parking spaces (utilizing underutilized idle spaces) in hospital vicinities, integrating multi-source geospatial data from OpenStreetMap, remote sensing imagery, and field surveys. The methodology involves data preprocessing (e.g., format conversion, building boundary calibration), parking space identification and classification (e.g., buffer zone delineation, vacant land categorization, shape-based division), and layout optimization using a genetic algorithm combined with manual refinement. Applied within a 1 km radius around two hospitals in Xuzhou, the results demonstrate significant improvements in space utilization and provide a scientific basis for temporary parking facility planning. The results provide practical decision support for urban spatial management and temporary parking governance in high-demand public service areas. Full article

As a unique cultural heritage of Chinese ethnic minorities, Dong architecture provides rich historical and cultural information. Rapid and accurate extraction of ethnic building information from remote sensing images in complex terrain and high-density settlement environments is highly important for the protection of architectural heritage and the management of rural space. Huanggang Dong Village in Liping County, Guizhou Province, China, is taken as a case study. This paper develops a multifeature fusion machine learning framework for the automatic recognition of Dong ethnic architecture based on centimeter-level visible images captured by UAV. First, the vegetation index, HSI color features and texture features based on the gray level co-occurrence matrix are extracted from the UAV visible light orthophoto image. Through the random forest feature importance ranking and correlation test, six key features, namely, the VDVI, HSI-S, HSI-I, mean, variance and contrast, are selected to construct a multifeature space. This step constitutes the feature construction stage of the proposed methodology and provides the basis for subsequent classification. Second, on the basis of a support vector machine (SVM) and random forest (RF), classification models are constructed. The effects of different feature combinations and different algorithms on classification accuracy are systematically compared, and the results are evaluated in terms of overall accuracy (OA), the kappa coefficient, user accuracy (UA) and producer accuracy (PA). This second part highlights the classification phase of the methodology, which tests the feature space using different algorithms and evaluates the performance of the models. The experimental data fully show that under the condition of a single feature, the SVM model dominated by texture features performs best, with an OA of 85.33% and a kappa of 0.799; under the condition of multifeature fusion, the RF algorithm has a stronger ability to integrate multisource features. The accuracy of building category recognition based on the total feature and dimensionality reduction feature space is particularly prominent. The total feature and overall accuracy reach 89.00%, and the kappa coefficient is 0.850. The UA and PA reached 89.66% and 94.55%, respectively. Through in-depth comparative analysis, the vegetation index–color–texture multifeature fusion and machine learning classification framework based on UAV visible light images can achieve high-precision extraction of Dong architecture without relying on high-cost sensors. It can effectively alleviate the confusion between water bodies and shadows and between dark roofs and vegetation and effectively separate traditional Dong architecture from roads, vegetation and other elements. It provides a low-cost and feasible way for digital archiving, dynamic monitoring and protection management of the traditional village architectural heritage of ethnic minorities. Full article

Chlorophyll-a (Chl-a) is a critical indicator of freshwater ecosystem health, reflecting phytoplankton biomass and primary productivity. This study investigates the long-term dynamics of Chl-a concentrations in Chao Lake, China, over three decades (1993–2023), employing an integrated approach combining remote sensing, causality, and comprehensive land use and climate data analysis. Our findings reveal a dramatic 175% increase in Chl-a levels, from 37.26 km² (1.71%) in 1993 to 102.41 km² (4.71%) in 2023, highlighting the ongoing eutrophication crisis. Significant correlations were established between land cover changes and Chl-a dynamics, with built-up areas exhibiting a positive correlation of 0.763 with Chl-a. In contrast, vegetation cover showed an inverse correlation of −0.766. Rising land surface temperatures (LST) increased by 1.8 °C from 1993 to 2023, significantly affecting nutrient cycling and algal bloom proliferation. Precipitation trends indicate a decline of approximately 10% over the study period, further exacerbating hydrological stress and nutrient concentrations. Employing Convergent and Geographic Convergent cross-mapping, we established robust causal relationships, confirming that urbanization and climate variability are primary drivers of Chl-a fluctuations. These findings stress the urgent need for targeted management strategies to mitigate nutrient loading and improve water quality in Chao Lake. Full article

Accurate and reliable vehicle detection, tracking, and counting across different surveillance platforms are fundamental requirements for developing smart Traffic Management Systems (TMS) and promoting sustainable urban mobility. Recent advances in both ground-level surveillance and remote sensing using deep learning have opened new opportunities for extracting detailed vehicular information from high-resolution aerial and surveillance video data. Our research reported here aims to present a unified, real-time vehicle analysis framework that integrates lightweight deep learning–based detection, robust multi-object tracking, and trajectory-driven counting within a single modular pipeline. The proposed framework employs a “You Only Look Once” system, YOLOv10-S as the detection backbone and enhances its robustness through supervision-level knowledge distillation without introducing any architectural modifications. Temporal consistency is enforced using an observation-centric multi-object tracking algorithm (OC-SORT), enabling stable identity preservation under camera motion and dense traffic conditions. Vehicle counting is performed using a trajectory-based virtual gate strategy, reducing duplicate counts and improving counting reliability. Comprehensive experiments conducted on the UA-DETRAC and VisDrone benchmarks show that the proposed framework effectively balances detection performance, tracking robustness, counting accuracy, and real-time efficiency in both ground-based and aerial surveillance settings. Furthermore, cross-dataset evaluations under direct train–test transfer highlight the inherent challenges of domain shift while showing that knowledge distillation consistently improves robustness in detection, tracking identity consistency, and vehicle counting. Overall, this framework enables effective real-world traffic monitoring by adopting a scalable and practical system design, where reliability is prioritized over architectural complexity. Full article

While understanding the drivers of river water quality is crucial, the dependence on ground observations hinders the accurate quantification of driver thresholds, as well as the scale-dependent effects of buffer zones. By transcending the limitations of ground observations, satellite remote sensing provides the spatially continuous data required to define effective buffer zones and determine the threshold intervals for natural and anthropogenic drivers, effectively promoting sustainable watershed management. Herein, we determined the total nitrogen (TN), total phosphorus (TP), permanganate index (COD_Mn), and turbidity in the Minjiang River of Fujian Province by synergizing Sentinel-2 imagery and in situ data (2021–2024). Subsequently, we further employed generalized additive models (GAMs) considering scale-dependent (50 m to 20 km) characteristics to screen and evaluate the natural–anthropogenic factors influencing the water quality indicators. The GAMs revealed that TN exhibited multiphasic responses to forest cover and water area, characterized by alternating positive and negative effects across their range. TP was found to be predominantly driven by agricultural and urban land use, showing clear scale–threshold effects. This study provides an integrated framework that moves beyond retrieval to quantitatively assess the impact of multi-scale natural–anthropogenic factors, offering actionable insights for precise watershed zoning and science-based management for the sustainable development of river systems. Full article

Flood inundation mapping (FIM) is essential in disaster risk management, infrastructure planning, and climate adaptation. Traditional hydrodynamic models, such as the Hydrologic Engineering Center’s River Analysis System (HEC-RAS) and LISFLOOD-Floodplain (LISFLOOD-FP), provide physically interpretable flood simulations but are often data- and computation-intensive and difficult to scale across regions. In recent years, machine learning (ML) and deep learning (DL) approaches have emerged as data-driven alternatives that leverage remote sensing observations, digital elevation models (DEMs), and hydro-climatic datasets to enable scalable and near-real-time flood mapping. Our review synthesizes recent advances in ML-based flood inundation mapping, categorizing methods into traditional machine learning techniques (e.g., Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB)), deep learning architectures (e.g., Convolutional Neural Networks (CNNs), U-Net, Long Short-Term Memory networks (LSTM)), and emerging hybrid and physics-informed frameworks. We evaluate model performance across flood extent and flood depth estimation tasks, highlighting strengths, limitations, and common benchmarking practices reported in the literature. The review identifies key challenges related to model interpretability, data bias, transferability, and regulatory acceptance, and highlights recent progress in explainable artificial intelligence (XAI), uncertainty-aware modeling, and physics-informed learning as pathways toward operational adoption. By unifying terminology, performance metrics, and methodological comparisons, this review provides a coherent framework for advancing trustworthy, scalable, and decision-relevant flood inundation mapping under increasing climate-driven flood risk. Full article

Tillage–residue management is a controllable lever for improving maize yield and system resilience under climate variability. Here we propose a mixed-effects spatiotemporal learning framework (ME-LSTM) that integrates multi-source observations to enable robust yield prediction and management system evaluation across heterogeneous sites and years. First, we construct multi-year sliding-window inputs to represent legacy effects and cumulative influences of past management and environment. Second, a deep temporal encoder learns nonlinear dependencies from climate–soil–remote-sensing sequences to enhance interannual extrapolation. Third, a mixed-effects module explicitly separates management fixed effects from hierarchical random effects (e.g., source/study, site, year, and plot), absorbing source-specific biases and unobserved heterogeneity while improving interpretability. Finally, we parameterize management × climate/soil interactions to quantify system-specific sensitivities to environmental drivers and to support scenario-based comparison and recommendation of management options. Across multi-ecological maize datasets, ME-LSTM achieved an R² of 0.8989 with an RMSE of 309.83 kg ha⁻¹ on the test set. Ablation analyses show that removing remote-sensing features or ground-based temporal information substantially degrades performance, confirming the complementary value of multi-source fusion. Benchmarking against strong temporal baselines (LSTM, GRU, BiGRU, and Transformer) further demonstrates consistent accuracy gains of ME-LSTM, highlighting its suitability for small-sample, noisy, and hierarchically structured agricultural data. Overall, ME-LSTM provides an interpretable and scalable tool for climate-adaptive optimization of tillage–residue management and supports robust, actionable decision-making across diverse agro-ecological conditions. Full article

Sediment management is defined as the strategic monitoring and control of erosion, transport, and deposition processes to maintain environmental and infrastructural stability. Terrestrial laser scanning (TLS) has emerged as a critical high-precision technology for monitoring sediment dynamics, erosion processes, and geomorphic change detection across diverse environments, including riverine, coastal, watershed, and infrastructure-related landscapes. While the field of TLS technology has seen significant advancements in recent years, including improvements in data accuracy, enhanced operational performance, artificial intelligence (AI), machine learning-based processing, and integration with other remote sensing tools such as unmanned aerial vehicles (UAVs) and satellite light detection and ranging (LiDAR), the study has focused on these developments. These advancements have further extended the application prospects of TLS technology. Despite these advancements, there remains a crucial need to systematically identify global research trends to identify the effectiveness, limitations, and knowledge gaps of TLS in sediment management. The methodological advantages and challenges of TLS applications provide insights into its gradual development role in enhancing sediment monitoring and environmental resilience. The objective of this study is to synthesize the current state of sediment management by conducting a systematic review of 108 peer-reviewed research papers retrieved from academic databases, including Google Scholar, ResearchGate, ScienceDirect, Scopus, and Web of Science, from 28 countries, published between 2000 and 2025. The study will evaluate the effectiveness of TLS methodologies in comparison to conventional techniques and management procedures, following the PRISMA 2020 guidelines. It will examine their capacity to enhance measurement accuracy, reduce error margins, and improve structural guidelines, particularly by advancing TLS technology through the integration of AI and machine learning (ML) algorithms. The findings of the study indicate that TLS and Iterative Closest Point (ICP) techniques can enhance the analysis of 3D models of dam deformation, ensuring improved structural monitoring and safety. The findings offer insights into the evolving role of TLS in sediment monitoring, emphasizing its potential for enhancing environmental management and climate resilience strategies. Furthermore, this review identifies future research directions to optimize TLS applications in sediment management through interdisciplinary approaches. Full article