Search Results (160)

Accurate time series forecasting is fundamental to geohazard early warning, yet remains a major challenge. Conventional in situ geotechnical monitoring remains costly and spatially constrained, whereas deep learning applied to remote sensing data has become increasingly prevalent but often suffers from opacity of model decision-making. To address this issue, we propose a Transformer-based forecasting framework, namely PatchTST-Fusion, adapted for multivariate Multi-Temporal Interferometric Synthetic Aperture Radar (MT-InSAR) time series. The framework integrates model interpretability analysis through TimeSHAP, providing temporal and feature-level attributions across the input sequence. Landslide deformation time series are first derived from Copernicus Sentinel-1 SAR data. Variational Mode Decomposition is then applied to decompose the non-linear signals into trend, seasonal, and noise components. The denoised displacement series are modeled and forecast using the proposed PatchTST-Fusion, which incorporates rainfall and reservoir water level fluctuations as feature-level drivers. Application to the Daping landslide cluster in the Three Gorges Reservoir Area in China demonstrates that our method captures both the long-term and transient non-linear coupling between deformation and its triggers, surpassing state-of-the-art models including CNN-BiGRU-Attention, Informer and original PatchTST with 7–55% improvements in MAE and 10–52% improvements in RMSE. Beyond predictive gains, feature attribution of environmental triggers via TimeSHAP reveals that rainfall and reservoir regulation exert temporally distinct influences on slope kinematics, with high relative importance concentrated in specific periods and characteristic lagged responses. This interpretable framework provides both enhanced forecasting accuracy and process-based insights, offering a broadly applicable tool for landslide early warning in reservoir regions. Full article

Evapotranspiration (ET) is a key component of the terrestrial water and energy cycle, and its long-term dynamics are essential for regional hydrological assessment in subtropical China. In this study, two widely used satellite-based ET products, MOD16 and PML-V2, were selected for intercomparison because they provide consistent spatial (500 m) and temporal (8-day) resolutions. Validation against flux observations showed that PML-V2 performed better than MOD16 and was therefore used for subsequent analysis. Based on the 500 m, 8-day PML-V2 dataset, the spatiotemporal variation in ET in subtropical China during 2001–2020 was examined using the Theil–Sen slope estimator, Mann–Kendall test, and Hurst exponent. To identify the most relevant controls on ET variation, eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) were used to screen environmental factors and rank their relative importance. Multiple linear regression (MLR) was then applied only to the selected dominant factors to quantify their contributions. Residual analysis was used to distinguish climate–vegetation effects from residual influences, which could arise from human activities and unmodeled natural processes. The results showed that annual ET averaged 669 mm and increased significantly at a rate of 2.03 mm yr⁻¹ from 2001 to 2020, with an accelerated increase after 2010. Spatially, ET exhibited clear gradients from south to north and from coastal to inland regions. Downward shortwave radiation (SWDown) and leaf area index (LAI) were the dominant drivers over most of the study area, although their controls varied geographically, with northern subregions being more energy-limited and southern subregions being jointly influenced by vegetation and temperature. Residual ET trends largely coincide with cropland and urbanising areas, indicating a partial influence of human activities, while in subregions such as XM, complex terrain and hydrological heterogeneity suggest that unmodeled natural processes may dominate. These findings enhance understanding of ET dynamics in subtropical China and demonstrate the value of high-resolution remote sensing products for regional hydrological monitoring and driver attribution. Full article

Remote sensing technologies provide valuable geospatial data for analyzing environmental conditions and for supporting spatial ecological modeling across large, heterogeneous landscapes. In this study, multi-source remote sensing–derived environmental variables were integrated with ensemble machine learning techniques to model the habitat suitability of the common leopard (Panthera pardus) in Azad Jammu and Kashmir (AJ&K), Pakistan. Environmental predictors derived from satellite observations included land cover, vegetation condition, terrain attributes, and climate-related indicators. To ensure model reliability, multicollinearity among predictors was evaluated, and spatial clustering patterns of leopard occurrence records were examined using global spatial autocorrelation analysis. Two complementary machine learning algorithms, Maximum Entropy (MaxEnt) and Random Forest (RF), were implemented and integrated through a weighted ensemble approach to improve predictive accuracy and robustness. The ensemble model achieved high predictive performance with an area under the curve (AUC) value of 0.942, outperforming individual algorithms. The resulting habitat suitability map indicates that approximately 30% of the study region is highly suitable habitat, primarily in the northern and central districts, including Muzaffarabad, Neelum, Hattian, Poonch, and Sudhnutti. Variable importance analysis identified remotely sensed land cover, elevation, vegetation cover, slope, and temperature seasonality as the dominant predictors of habitat suitability, whereas anthropogenic indicators such as proximity to roads and population density had secondary effects in fragmented areas. The results demonstrate the potential of integrating remote sensing data and ensemble machine learning for spatial habitat modeling and wildlife conservation planning in mountainous ecosystems. Full article

Detecting changes in vegetation condition is crucial for monitoring heterogeneous systems like natural grasslands. However, a background of high spatial and temporal variability in environmental variables and plant responses challenges field surveys and remote sensing. Monitoring fine-scale heterogeneity and transitions influenced by invasive species remains challenging. To address this gap, this study developed an approach to map vegetation condition across multiple years using condensed seasonal NDVI patterns derived from Sentinel-2 time series. The approach was evaluated in the temperate grasslands of South Australia (Mediterranean-type climate), dominated by iron-grass (Lomandra effusa) and impacted by invasive annuals. A beta regression model was trained using an NDVI time series and field-based iron-grass cover from a single year (2022), achieving a pseudo-R² of 0.63 (RMSE = 9.48 ± 3.43%). Extrapolating the model across 2019–2025 yielded similar spatial patterns in cover, revealing good agreement between field-based data and predictions (pseudo-R² = 0.53 to 0.69) and between predictions for each year (pseudo-R² = 0.84 to 0.9). Despite rainfall and NDVI variability, the approach enabled the detection of subtle changes and the identification of trends. This approach holds great potential for mapping continuous attributes of vegetation condition over time, contributing to the conservation and monitoring of grasslands. Full article

Remote sensing image analysis is crucial for many research fields, yet acquiring frequent high-quality remote sensing imagery is not always feasible due to prohibitive costs and logistical efforts. As a solution, ground-to-satellite cross-view image generation has emerged as a promising approach for synthesizing remote sensing images from readily available ground sensor data. However, existing methods face two critical limitations that bottleneck their performance, including instability in object structural attributes in ground views and reduced image fidelity and consistency due to environmental occlusions. To address these challenges, this paper proposes a geometrically constrained controllable generation model specifically tailored for remote sensing image generation, called GCCG-RSI. To overcome the limitation of structural instability, GCCG-RSI introduces LiDAR ranging accuracy to constrain the geometric shapes of the generated image. To mitigate occlusion-induced fidelity issues, GCCG-RSI employs an attention mechanism to derive a unified fused representation that integrates texture and spatial structure information. The representation is utilized as a conditional control signal to guide the diffusion model in accurately synthesizing remote sensing imagery. Experimental results demonstrate that, compared with state-of-the-art methods, GCCG-RSI infers remote sensing images with superior realism and fidelity using ground-view images and point clouds with limited perspective. Overall, the proposed method provides an effective image preprocessing approach that contributes to significantly narrowing the domain discrepancy between ground and satellite images, thereby facilitating the execution of downstream tasks. Full article

Lake color is an intuitive indicator reflecting the ecological and physicochemical status of lakes and is of great value for both ecological monitoring and environmental assessment. However, the types, spatiotemporal variations, and driving mechanisms of global lake color phenology remain unclear. In this study, we systematically analyzed the color phenology of 975 global lakes based on Landsat remote sensing data from 1984 to 2021. The results indicate that lake color phenology can be categorized into six types, including the perennial green type, evergreen type, and seasonal patterns (spring green, summer green, autumn green, and winter green). Approximately 43.9% of the lakes are classified as the evergreen type, mainly concentrated in the Southern Hemisphere. Further research reveals notable spatial differences in the change in lake color phenology: about 69.4% of lakes in the Southern Hemisphere exhibit relatively stable phenological patterns (frequency of changes within the study area ≤ 2), while approximately 64.4% in the Northern Hemisphere show phenological variations. This dynamic disparity is closely related to lake attributes (area, water depth, elevation) as well as external climatic and watershed conditions (precipitation, wind speed, vegetation). Our findings contribute to developing the interannual patterns of lake color into a novel ecological indicator, thereby advancing the dynamic monitoring and assessment of global lake status. Full article

Dry soil spectral reflectance provides a stable baseline for characterizing soil optical properties and supporting the retrieval of soil attributes from remote sensing. However, despite the large number of studies on soil spectral reflectance, most existing research primarily focuses on empirical relationships between spectra and soil properties. The representation and prediction of dry soil reflectance as a baseline condition, particularly under the influence of environmental factors, remain insufficiently explored, and the generalizability of existing models still needs improvement. Therefore, this study collects 700 dry soil samples with laboratory-measured spectral reflectance from Northeast China and quantitatively analyzes the contribution of environmental covariates (soil properties, parent material, and geographical location) using the SHAP method. Then, an environmental and edaphic-factor-driven smooth dry soil reflectance model (EEDSR) model covering 400–2500 nm is developed based on gradient boosting regression (GBR), and its accuracy is evaluated using global ISRIC soil datasets. Our results indicate the following: (1) the reflectance of dry soil is closely related to the soil properties in the VIS to SWIR range. The reflectance of dry soil of 400–2500 nm is positively correlated with clay percentage, longitude, and parent material but negatively correlated with latitude, sand percentage and silt percentage. And its correlation with other variables (such as soil organic matter, pH, and EC) varies with wavelength. (2) The EEDSR model exhibited high predictive accuracy across the 400–2500 nm spectral range (R² = 0.93, RMSE = 0.018). Additionally, incorporating parent material (PM) and geographical factors into the predictor set enhanced the accuracy of dry soil reflectance prediction by 13.4%. (3) The spatial consistency between the predicted soil reflectance in Northeast China and the satellite observations indicates that the EEDSR model has good performance in predicting soil reflectance, as the bias of reflectance gradually increasing from west to east is consistent with the precipitation distribution in Northeast China. (4) The generalization ability of the EEDSR model was confirmed by global ISRIC datasets (R = 0.94), outperforming the deep learning-based Soil Optical Generative Model (SOGM) (R = 0.27). Overall, this study presents an efficient and interpretable framework for modeling dry soil spectral reflectance, providing a robust reference for soil reflectance prediction and remote sensing-based soil property retrieval. Full article

Evaluating whether zoning-based management is associated with measurable ecosystem function benefits is crucial for China’s national park system reform, yet most existing assessments emphasize greening or productivity alone. Here, we evaluate zoning-associated patterns in the Three-River Headwaters Region by combining MODIS-derived carbon use efficiency (CUE = NPP/GPP; 2001–2024), a boundary–buffer comparison with environmental matching, and an explainable machine learning attribution framework. NPP increased across all zones, whereas CUE remained stable to slightly declining, indicating a productivity–efficiency decoupling in the remote sensing record. Core and Buffer zones maintained higher long-term median CUE than the Outside zone, but matched boundary contrasts were heterogeneous, and the Experimental–Outside CUE contrast, although robust in sign, was small in magnitude. Zone–year attribution (2002–2020) suggests that interannual CUE variability is dominated by climate and land surface structure/change, while human pressure shows a smaller negative association; these grouped SHAP contributions should be interpreted as indicative rather than precise estimates. Post-2020 climate baseline residuals show persistent negative CUE anomalies in Buffer and Experimental zones, suggesting additional non-climatic influences but not demonstrating causality. Given the temperature-sensitive structure of MOD17 and the representativeness limits of QC-filtered 500 m observations, we interpret these results as management-consistent patterns rather than stand-alone causal proof. The findings support incorporating carbon use efficiency into zonal monitoring and may inform differentiated, efficiency-oriented management review. Full article

Accurate estimation of forest soil organic carbon (SOC) is considered critical for understanding terrestrial carbon cycling and supporting climate change mitigation strategies. However, the canopy block, intricate vertical structure of forests, and the constraints of single-source remote sensing data have presented considerable obstacles for estimating forest SOC. This study proposes a forest SOC estimation and uncertainty analysis (ForSOC-UA) framework to enhance forest SOC estimation and quantify its uncertainty in the natural secondary forests of northern China by integrating hyperspectral imagery (ZY-1F), synthetic aperture radar data (Sentinel-1), and environmental covariates (such as topography, vegetation, and soil indices). The performance of traditional machine learning models (RF, SVM, and CNN), geographically weighted regression (GWR), and a geographically weighted random forest (GWRF) model was compared across three different soil depths (0–5 cm, 5–10 cm, and 10–30 cm). The results showed that GWRF consistently outperformed all other models across all soil depth layers, with the highest accuracy achieved using multi-source data (R² = 0.58, RMSE = 27.49 g/kg, rRMSE = 0.31). Analysis of feature importance revealed that soil moisture, terrain characteristics, and Sentinel-1 polarization attributes were the primary predictors, while spectral derivatives in the red and near-infrared bands from ZY-1F also played a significant role for forest SOC estimation. The uncertainty analysis indicated a forest SOC estimation uncertainty of 37.2 g/kg in the 0–5 cm soil layer, with a decreasing trend as depth increased. This pattern is associated with the vertical spatial distribution of the measured forest SOC. This integrated approach effectively captures spatial heterogeneity and nonlinear relationships between feature and forest SOC, while also assessing estimation uncertainty, so providing a robust methodology for predicting forest SOC. The ForSOC-UA framework addresses the uncertainty quantification of SOC estimation at different vertical depths based on machine learning, providing methodological enhancements for the assessment of large-scale forest SOC and the monitoring of carbon sinks within forest ecosystems. Full article

Drought is one of the major disasters constraining crop production. The accurate identification of the dominant environmental factors that drive drought stress at different growth stages of maize is essential for developing stage-specific and precise water management strategies, enhancing drought resistance, and ensuring food security. However, a key challenge is quantifying the nonlinear interactions among multiple environmental factors. This study focuses on the rain-fed agricultural region of Northwest China. To address the limited availability of drought event samples in this region and the inadequacy of traditional statistical methods in capturing complex inter-factor relationships, we integrate a small-sample modeling framework based on an improved Conditional Generative Adversarial Network (CGAN) with an attribution framework that employs SHapley Additive exPlanations (SHAP) for interpretability analysis. We incorporate ten environmental factors derived from multi-source remote sensing: temperature (T_max, T_min, T_mean), precipitation (P), evapotranspiration (ET), soil moisture at 0–10 cm (SM_0–10) and at 10–40 cm (SM_10–40), and solar-induced chlorophyll fluorescence (SIF_max, SIF_min, SIF_mean). Sample sets were established for different maize phenological stages. The CGAN model was employed to achieve high-precision estimation of maize drought severity levels, while the SHAP method was used to quantitatively analyze the dominant factors and their contributions at each phenological stage. The results show that the CGAN model achieved coefficients of determination (R²) of 0.963, 0.972, and 0.979 for the seedling, jointing–tasseling, and maturity stages, respectively, demonstrating excellent nonlinear modeling capability under small samples. SHAP analysis reveals a clear dynamic evolution of dominant factors across phenological stages. Evapotranspiration (ET) dominated in the seedling stage, reflecting the primary role of surface water–heat balance, while the jointing–tasseling stage transitioned to a co-dominance of ET, topsoil moisture (SM_0–10), and minimum SIF, indicating intensified crop transpiration and physiological stress under the meteorological drought framework, and the maturity stage shifted to an absolute dominance centered on mean temperature (T_mean), highlighting the critical impact of heat stress. This study provides a data-driven quantitative perspective for understanding maize drought mechanisms and offers a scientific basis for formulating differentiated drought management strategies for different growth stages. Furthermore, it demonstrates the potential of integrating CGAN with SHAP for agricultural remote sensing and drought attribution research in data-scarce regions. Full article

Vegetation restoration in water-limited regions typically increases evapotranspiration (ET) while reducing runoff. Over the past four decades, Daihai Lake in China’s northwest inland river basin has experienced significant shrinkage. Previous studies attribute this primarily to climate change and water resource exploitation, yet the impact of vegetation dynamics remains insufficiently examined. This study analyzed changes in the water budget across different vegetation types in the Daihai Lake Basin, based on remote sensing-derived precipitation and ET data, and employed correlation analysis to examine the relationships between environmental factors (such as climate change, afforestation projects, and water-saving irrigation) and lake shrinkage. Our findings revealed that afforestation has expanded forest cover by 69.42 km² since 2000, accounting for 73.95% of the total forest area. Notably, forest ET demonstrated the strongest negative correlation (r = −0.89, p < 0.001) with lake area among all vegetation types. Grasslands emerged as the primary water-surplus vegetation, contributing 81.34% to the basin’s total water surplus. The synergistic effects of precipitation reduction, temperature increase, and enhanced ET from forest expansion drove the shrinkage of the lake. These results highlight the need for science-based vegetation management in arid and semi-arid regions, where we recommend adopting shrub-grass combined restoration approaches to enhance the sustainability of ecological restoration. Full article

The Arid Region of Northwest China (ARNC) functions as a critical ecological barrier for the Eurasian hinterland. To clarify the non-linear drivers of eco-environmental dynamics, a long-term (2000–2024) Remote Sensing Ecological Index (RSEI) time series was constructed and analyzed using an interpretable machine learning framework (XGBoost-SHAP). The analysis reveals pronounced spatial asymmetry in ecological evolution: improvements are concentrated in localized, human-managed areas, while degradation occurs as a diffuse process driven by geomorphological inertia. The ARNC exhibits low-level stability (mean RSEI 0.25–0.30) and marked unbalanced dynamics, with significant degradation (19.9%) affecting more than twice the area of improvement (6.5%). Attribution analysis identifies divergent driving mechanisms: ecological improvement (R² = 0.559) is primarily anthropogenic (58.3%), whereas degradation (R² = 0.692) is mainly governed by natural constraints (58.4%), particularly structural topographic factors, where intrinsic landscape vulnerability is exacerbated by human activities. SHAP analysis corroborates a “Greenness-Quality Paradox” in stable agroecosystems, where high vegetation cover coincides with reduced evaporative cooling and secondary salinization from irrigation, resulting in declining Eco-Environmental Quality (EEQ). A zero-threshold effect for grazing intensity is also identified, indicating that any increase beyond the baseline immediately initiates ecological decline. In response, a Resist-Accept-Direct (RAD) framework is proposed: direct salt-water balance regulation in oases, resist hydrological cutoff in ecotones, and accept natural dynamics in the desert matrix. These findings provide a scientific basis for reconciling artificial greening initiatives with hydrological sustainability in water-limited regions. 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

Over the past several centuries, many lakes in the Yunnan Plateau disappeared or are disappearing due to climate change and human activities; the developments of these lakes are thus crucial for understanding their evolutions and underlying causes. Here we present a near 260-year history of water area changes in Lake Zhehai, a disappearing lake in northeastern Yunnan of Southwest China, based on historical documents such as local and regional annals and gazetteers, water conservancy records, and old maps using GIS and remote sensing techniques, to identify the dominant drivers of the lake disappearing. Results show that the reconstructed water area of Lake Zhehai was ca. 1500, 710, 370, 340, and 110 ha in 1761, 1912, 1935, 1950, and 1975 AD; this indicates that Lake Zhehai experienced three-phase lake evolution over the past 260 years, i.e., large lake in 1761–1920 AD, shrinking lake in 1921–1980 AD, and disappearing lake since 1981. Significant changes in the water area of Lake Zhehai were mainly attributed to both climate change and human activities, especially human activities as dominant drivers during the last two phases of lake evolution. Our findings provide a reference for both understanding the driving mechanisms of large shallow lake evolution during historical times in Yunnan, as well as assessing strategies of lake environmental protection under global warming and increasing human activities. Full article

Uniform application of fertilizers and pesticides continues to dominate global agriculture despite significant spatial variability in soil and crop conditions. This mismatch results in avoidable yield gaps, excessive chemical waste, and environmental pressures, including nutrient leaching and greenhouse gas emissions. The integration of Artificial Intelligence (AI) and Remote Sensing (RS) has emerged as a transformative framework for diagnosing this variability and enabling site-specific, climate-responsive management. This systematic synthesis reviews evidence from 2000–2025 to assess how AI–RS technologies optimize agrochemical efficiency. A comprehensive search across Scopus, Web of Science, IEEE Xplore, ScienceDirect, and Google Scholar were used. Following rigorous screening and quality assessment, 142 studies were selected for detailed analysis. Data extraction focused on sensor platforms (Landsat-8/9, Sentinel-1/2, UAVs), AI approaches (Random Forests, CNNs, Physics-Informed Neural Networks), and operational outcomes. The synthesized data demonstrate that AI–RS systems can predict critical soil attributes, specifically salinity, moisture, and nutrient levels, with 80–97% accuracy in some cases, depending on spectral resolution and algorithm choice. Operational implementations of Variable-Rate Application (VRA) guided by these predictive maps resulted in fertilizer reductions of 15–30%, pesticide use reductions of 20–40%, and improvements in water-use efficiency of 25–40%. In fields with high soil heterogeneity, these precision strategies delivered yield gains of 8–15%. AI–RS technologies have matured from experimental methods into robust tools capable of shifting agrochemical science from reactive, uniform practices to predictive, precise strategies. However, widespread adoption is currently limited by challenges in data standardization, model transferability, and regulatory alignment. Future progress requires the development of interoperable data infrastructures, digital soil twins, and multi-sensor fusion pipelines to position these technologies as central pillars of sustainable agricultural intensification. Full article