Search Results (407)

Satellite -derived environmental features can predict county-level life expectancy (LE) across the contiguous United States with a mean absolute error of 1.08 years over two decades, without using any census or sociodemographic inputs. We assembled 61,680 county-year observations across 3084 counties from 2000–2019, integrating features from 11 satellite and gridded data streams. The data streams include the Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature and vegetation indices, Sentinel-1 synthetic aperture radar, Sentinel-2 and Landsat optical imagery, the United States Department of Agriculture (USDA) Cropland Data Layer, the European Commission Joint Research Centre (JRC) Global Surface Water layer, the Copernicus Digital Elevation Model, the European Space Agency Climate Change Initiative (ESA CCI) soil moisture record, and the Food and Agriculture Organization (FAO) gridded livestock densities. After a supervised pruning step that removed low-importance variables, a Random Forest regressor was trained and evaluated using 5-fold cross-validation grouped by county. The grouping places all 20 years of each county exclusively in either the training set or the test set, which prevents spatial information leakage between folds. Coefficient of determination, mean absolute error, and root mean squared error are reported as $R^2=0.631\pm 0.013$, MAE $=1.08\pm 0.02$ years, and RMSE $=1.48\pm 0.04$ years. Moran’s I, a measure of residual spatial autocorrelation, is $0.0988$ ($p=0.001$), which supports geographic generalisation. Multimodal fusion reduces unexplained variance by approximately one-third relative to the strongest single-modality baseline (MODIS land surface temperature alone, $R^2=0.442$). TreeSHAP attribution analysis reveals a feature hierarchy in which nighttime land surface temperature features carry roughly $6.16\times$ the cumulative attribution weight of all daytime channels combined. The model response shows a protective inflection near a minimum overnight temperature of about 7.5 °C. Because all input streams are globally available, the framework is architecturally extensible to regions where civil registration and vital statistics systems are incomplete; however, the trained model and its thresholds require recalibration against local mortality data before application outside the contiguous United States. With that caveat, the approach supports satellite-based monitoring of United Nations Sustainable Development Goal (UN SDG) Target 3.9. Full article

Flood risks are escalating under climate change, necessitating advanced methods to improve runoff prediction and multivariate flood-risk assessment. In this study, a physics–XGBoost-based Bayesian model averaging with bivariate copulas (PXB-BVC) framework was developed by integrating the Soil and Water Assessment Tool (SWAT), the Hydrologiska Byråns Vattenbalansavdelning (HBV) model, Extreme Gradient Boosting (XGBoost), Bayesian model averaging (BMA), and bivariate copulas. Spatially detailed underlying surface parameters including 30 m land-use data derived from the 2000 China land-use remote sensing monitoring data were pre-processed and reclassified using ArcGIS to support spatially explicit hydrological simulation. The framework was applied to the Xiangxi River Basin (XXRB), China, under four general circulation models and three shared socioeconomic pathways. PXB-BVC improved daily runoff simulation by combining process-based hydrological information with nonlinear machine learning correction, achieving Nash–Sutcliffe efficiency (NSE) values of 0.95 during calibration and 0.89 during validation. Future runoff generally increased from the near-term to the late-century period, with stronger changes under SSP585 and Sen slopes reaching up to 0.46 m³ s⁻¹ yr⁻¹, although the magnitude and significance of trends varied among GCMs. The dependence structures among flood peak, flood volume, and flood duration showed non-stationary behavior under future climate forcing, with Kendall’s tau for peak–volume pairs mostly ranging from 0.6 to 0.8. The revised bivariate return-period analysis further indicates that inferred flood-risk changes depend on the joint risk definition. Under SSP245 and ACCESS-ESM1–5, OR-type joint return periods show that representative near-future 50-year events may become more frequent in 2061–2100, whereas AND-type return periods show weaker and less uniform changes among flood-characteristic pairs. Conditional probability analysis also indicates enhanced compound risk under high-emission conditions: given an extreme peak flow, the probability of accompanying high flood volume increases from 0.23 to 0.56, while the probability of prolonged duration increases from 0.18 to 0.45. These results demonstrate that the PXB-BVC framework can support non-stationary multivariate flood-risk assessment and provide useful information for climate-resilient water-resource management and infrastructure planning. Full article

Remote sensing change detection (CD) aims to localize land-surface changes from bi-temporal imagery and plays an important role in applications such as urban monitoring, disaster assessment, and environmental analysis. In high-resolution scenarios, CD performance is often degraded by cross-temporal appearance inconsistency, large variations in target scale, and boundary ambiguity introduced during multi-level decoding. To address these challenges, we propose MIGA-Net, an end-to-end framework that jointly models spatio-temporal interaction, adaptive multi-scale context aggregation, and hierarchical boundary refinement. Specifically, the Spatio-Temporal Graph Interaction Module (ST-GIM) combines interactive attention and graph reasoning to suppress pseudo-changes caused by illumination or seasonal shifts; the Adaptive Gated Context Pyramid Module (AGCP) performs content-driven scale selection and regulates context injection through a gated residual mechanism to reduce noise amplification; and the Hierarchical Boundary-Aware Refinement Module (HBAR) integrates semantic channel filtering and explicit boundary attention for progressive contour recovery. Experiments on LEVIR-CD, WHU-CD, and SYSU-CD demonstrate that MIGA-Net achieves F1 scores of 91.84%, 92.52%, and 82.92%, and IoU scores of 84.91%, 86.08%, and 70.83%, respectively. The proposed method yields consistent improvements in both quantitative metrics and structural boundary quality, indicating its effectiveness for robust pseudo-change suppression and structurally faithful prediction in high-resolution remote sensing CD. Full article

Rapid urbanization and climate change have intensified the interconnected challenges of surface heating, air pollution, and declining ecosystem functions, with important implications for regional sustainability. Taking Henan Province, China, as the study area, this study selected 2013, 2018, and 2023 as representative years and used land surface temperature (LST), fine particulate matter (PM2.5), ozone (O3), and net primary productivity (NPP) to characterize the thermal environment, air pollution, and carbon sequestration capacity. Pearson correlation analysis, multiple linear regression, and XGBoost-SHAP were integrated to examine bivariate associations, independent linear associations, factor importance, nonlinear responses, and potential threshold characteristics associated with natural, ecological, and anthropogenic factors. The results showed marked spatial differences in the four environmental variables. The multiple linear regression models explained 57.4–69.0% of the variation in LST, 23.8–72.0% in O3, 81.0–84.8% in PM2.5, and 57.4–62.5% in NPP. Natural factors generally showed relatively large and temporally stable standardized coefficients. Precipitation and potential evapotranspiration were positively associated with LST, whereas elevation and precipitation were negatively associated with PM2.5 and O3. NDVI showed an environmentally favorable pattern, being negatively associated with LST, PM2.5, and O3 but positively associated with NPP. Anthropogenic variables generally exhibited smaller and less temporally stable coefficients. The XGBoost models demonstrated good predictive performance, particularly for PM2.5, with R² values of 0.945, 0.920, and 0.905 in 2013, 2018, and 2023, respectively. SHAP analysis identified DEM, PRE, PET, and NDVI as the main contributors to model predictions and revealed nonlinear responses and potential threshold characteristics. These findings indicate that coordinated management of vegetation cover, hydrothermal conditions, and urban development can support heat mitigation, air pollution control, ecosystem productivity, and more sustainable, climate-resilient, and low-carbon development in rapidly urbanizing regions. Full article

Flood susceptibility in Pakistan is strongly influenced by hydro-climatic variability, land-surface conditions, topography, and recurrent floodplain exposure; however, national-scale studies often lack a comprehensive assessment that captures both spatial patterns and temporal flood-risk dynamics within a single framework. This study is one of Pakistan’s first national efforts to address the gap between flood risk assessment and prioritization through a unified geospatial assessment. This study assesses flood susceptibility across Pakistan for 2002, 2012, and 2022 using a GIS-based AHP approach by integrating climatic, environmental, topographic, hydrological, soil, LULC, and anthropogenic indicators. The study results were further analyzed through district-level assessments, risk change analysis, persistence mapping, LULC exposure assessments, and the Comprehensive Flood Risk Priority Index (FRPI). The results show that high and very high flood susceptibility zones are primarily concentrated along the Indus River corridor, lower floodplains, and coastal Sindh, accounting for more than 7% of the total land area of Pakistan. Persistent flood hotspots are identified in Rann of Kutch (66.6%), Jacobabad (65.0%), and Jafarabad (61.1%), indicating strong temporal stability of flood-prone conditions. LULC exposure analysis reveals that cropland is the dominant exposed class, with the highest district-level exposure observed in Badin (17.1%) and Larkana (10.1%). The FRPI further identifies priority flood-risk zones where susceptibility, persistence, risk change, and exposure converge, with the highest FRPI values observed in Jacobabad (0.742), Rann of Kutch (0.738), and Badin (0.711). Model validation demonstrates strong predictive performance, with susceptibility ROC-AUC values ranging from 0.85 to 0.87 and FRPI AUC reaching 0.85. The proposed framework provides a robust decision-support tool for targeted flood-risk management and climate-resilient land-use planning in Pakistan. Full article

Mycotoxin contamination of cereal crops poses escalating food safety risks across the Central and Balkan European (CBE) corridor under climate change, yet no PRISMA 2020-compliant synthesis of remote sensing (RS) and machine learning (ML) evidence for this region exists. We conducted an AI-augmented systematic review applying a four-stage automated pipeline—PICO domain scoring, SBERT semantic deduplication, and Thompson-sampling reinforcement learning—to 36,038 corpus records (2010–2025), yielding 156 included studies (inter-rater κ = 0.81 (95% CI: 0.74–0.88)). Logistic growth modelling identified a 56-fold corpus expansion with inflection at t₀ = 2024.8 (R² = 0.981). Satellite multispectral imaging dominated the literature (91.7% of studies); random forest and gradient boosting models achieved R² = 0.74–0.80 for aflatoxin B1 and deoxynivalenol prediction in CBE maize and wheat when integrating vegetation indices, land surface temperature, and precipitation covariates. Deep learning surpassed classical ML in annual study count from 2021, reaching ~60% relative share by 2025, though the performance advantage narrows at field scale relative to laboratory hyperspectral benchmarks (98–99% accuracy). A five-percentage-point CBE–global performance gap is largely consistent with differences in sample size and multi-toxin design scope rather than algorithmic access. The country × mycotoxin gap matrix identifies zero eligible studies for four CBE nations and for T-2/HT-2 toxins across the Balkan states. Climate-driven satellite mycotoxin prediction emerges as the field’s active research frontier. Full article

This study focuses on the quantitative simulation of the spatiotemporal distribution characteristics of permafrost area, providing scientific value for Mongolian Plateau permafrost dynamics. Understanding the permafrost area of the Mongolian Plateau and accurately predicting future changes in permafrost area are crucial for sustainable environmental development. In this study, ERA5-Land surface temperature (LST) combined with the temperature at the top of permafrost (TTOP) model are used to calculate the annual permafrost area from 1980 to 2024. In addition, this study used the long short-term memory (LSTM) model to predict permafrost area on the Mongolian Plateau from 2025 to 2100. In this study, it is concluded that (1) the study area is not uniformly covered with permafrost, and its distribution is mainly limited to the northern part of the Mongolian Plateau, with a permafrost area of 53.20 × 10⁴ km²; (2) the permafrost area is estimated with an accuracy and precision of 0.94 when compared to the baseline value derived from borehole permafrost data; (3) under the CMIP6 three different shared socioeconomic pathway (SSP) 1-2.6, 2-4.5, and 5-8.5 future scenarios, the distribution of permafrost area shows a downward trend. This study provides a theoretical reference for distribution permafrost area in geographical space, which can help achieve the sustainable development of ice and snow resources. Full article

Soil surface moisture (SSM) is a critical indicator of agricultural drought, yet high-resolution projections under climate change remain scarce. This study develops a machine learning framework to predict and project SSM at 1 km resolution across five European Living Labs (LLs), encompassing vineyards, olive groves, and fruit tree systems. Historical Sentinel-1 SSM observations (2014–2024) were used to train ensemble models (Random Forest, XGBoost, ExtraTrees, LightGBM) incorporating climate variables, soil texture, topography, and land use. Tree-based models achieved R² values of 0.63–0.87. Vineyards showed the highest predictability (R² ≈ 0.87), reflecting their sensitivity to short-term atmospheric demand and surface water availability, whereas olive groves were the least predictable (R² ≈ 0.63–0.68), consistent with deeper rooting systems and greater drought buffering capacity. When forced with bias-corrected CMIP6 projections under SSP1-2.6 and SSP5-8.5 for 2041–2070, models indicate minimal changes under SSP1-2.6 but pronounced SSM declines of 8–24% under SSP5-8.5, with historically wetter regions experiencing the largest absolute losses. SHAP analysis confirmed precipitation and potential evapotranspiration as dominant predictors across all crops. This framework provides spatially explicit, crop-relevant SSM projections to support climate adaptation in European agricultural landscapes. Full article

Net primary productivity (NPP) is an important indicator for assessing ecosystem productivity and carbon cycling. The Yellow River Basin (YRB), as an important ecological conservation zone and economic region in China, is highly sensitive to climate change, land use change, and ecological restoration. Understanding the spatiotemporal variation in NPP and its relationships with environmental factors is therefore important for regional ecological management. In this study, MODIS NPP data, ERA5-Land environmental variables, land use data, machine learning algorithms, and SHAP-based model interpretation were used to analyze the spatiotemporal patterns of NPP and the nonlinear responses of NPP to environmental factors in the YRB from 2001 to 2020. The results showed the following: (1) NPP exhibited a spatial pattern of higher values in the south and lower values in the north. The annual average NPP showed a fluctuating upward trend, and most pixels showed varying degrees of increase during the study period. (2) Moisture-related variables contributed more strongly to model-predicted NPP variations in the entire basin than thermal variables. (3) For different ecosystem types, surface solar radiation downwards (SSRD) made the largest contribution to model-predicted NPP variations in cropland and forest ecosystems and showed a negative relationship with NPP, whereas evapotranspiration (E) contributed most strongly to model-predicted NPP in grassland ecosystems and showed a positive relationship with NPP. (4) Most environmental factors showed nonlinear associations with model-predicted NPP, and SHAP-derived response thresholds differed among ecosystem types. These thresholds should be interpreted as model-based nonlinear response points rather than confirmed ecological tipping points or ecological regime shifts. This study provides a reference for understanding the heterogeneous responses of vegetation productivity to environmental factors in the YRB. Full article

Change detection (CD) refers to the analysis of changes in the utilization of land, buildings, and other targets in the same surface environment using relevant technologies and remote sensing images. Although deep learning-based change detection methods have achieved excellent results, they remain highly dependent on extensive labeled data. High-resolution remote sensing imagery typically encompasses an abundance of details and a greater quantity of pixels compared to low-resolution datasets. Therefore, data annotation costs are significantly higher. Currently, within the context of semi-supervised change detection (SSCD) driven by consistency learning, pseudo-labels are usually selected only by threshold screening, but this ignores the spatial relationships among pixels and does not fully utilize unlabeled data, thereby affecting the model’s performance. Consequently, we propose a semi-supervised high-resolution remote sensing image change detection method based on label expansion. First, a “one weak, two strong” (OW-TS) consistency regularization (CR) framework is introduced to constrain the overall consistency between the prediction results of weak and strong augmentations, as well as between the two strong augmentations. At the same time, the location interaction map (LIM) is introduced to utilize the global–local relationship between pixels and mine the consistency of pseudo-labels, thereby improving the model’s accuracy. Empirical findings indicate that when the model is trained utilizing 20% labeled data and 80% unlabeled data on the LEVIR-CD dataset, the IoU^c index reaches 83.38%. The model performs well in smoothing the boundary between changed and unchanged areas and is comparable in performance to some fully supervised methods. Full article

Coastal cities are prone to flooding due to extreme rainfall, rising sea levels, and urbanization. This study develops a non-stationary flood risk prediction framework for a coastal city to assess the combined effects of rainfall, tide, and land surface change on future flood inundation and socioeconomic risk. Future rainfall was predicted by integrating the time-varying parameter distribution (TVPD) model with CMIP6 data through a genetic algorithm; future tides were estimated using the TVPD model; and land use in 2035 was simulated using the Markov–PLUS model. Flood inundation and the associated socioeconomic risks were then evaluated. The results showed that the integrated rainfall prediction approach reduced RMSE by 13.4% compared with the individual models. The land use simulation also showed acceptable performance, with a Kappa coefficient of 0.79 and an FOM value of 0.15. Under the combined effects of rainfall, tide, and land use change, the future peak inundation volume increased by 19.97% on average relative to the baseline period, while the affected population and economic losses increased by 72,603 people and US$12.61 billion, respectively. These results indicate that flood risk in coastal cities may be substantially exacerbated under a non-stationary environment, and the proposed framework can provide support for future flood risk assessment and adaptation planning. Full article

The Eastern Mediterranean, notably Cyprus, is a climate change hotspot facing severe heatwaves. Accurate numerical weather prediction of these extremes requires precise land–atmosphere modeling and initial and boundary conditions. This study assesses replacing the default USGS Land-Use and Land-Cover (LULC) dataset with the 10 m ESA WorldCover 2021 dataset in the Weather Research and Forecasting (WRF) model to simulate the 15–29 July 2023 Cyprus heatwave. The updated LULC increased urban representation six-fold. Statistical validations showed significant improvements in 2 m temperature, relative humidity, and 10 m wind speed predictions across 85% of observational sites. Dynamically, it restored urban thermal memory, effectively capturing the daytime Urban Cool Island effect and nocturnal heat release. Furthermore, radiosonde validations showed that the update corrected nocturnal Planetary Boundary Layer Height (PBLH) underestimations and dampened exaggerated daytime convective mixing. However, crucial limitations remain. High-frequency diagnostics indicated the model still suffers from damped thermal inertia, missing the abrupt temperature spikes and rapid nocturnal cooling typical of semi-arid microclimates. Additionally, the updated configuration failed to capture severe atmospheric stagnation during peak heatwave conditions, highlighting that deep-rooted kinetic errors persist within default boundary layer parameterizations despite static surface improvements. Full article

Numerical simulations quantify the transient impacts of implementing green infrastructure (GI) grass swales on unconfined aquifer storage and groundwater-surface water interactions around the Red Butte Creek (RBC) of Utah, USA. The Red Butte Creek Watershed (RBCW) transitions from undeveloped mountainous National Forest land to downstream urbanized areas within Salt Lake Valley (SLV). This reconnaissance-level study demonstrates that increasing stormwater infiltration in urbanized areas during the rainy months (April-June) can, until at least the subsequent March, (a) enhance aquifer recharge and support sustainable groundwater yields; and (b) improve surface water availability. Simulations predict hydrologic impacts of aquifer recharge resulting from hypothetical grass-swale implementation within a 704-acre area located around RBC. The employed model, HyperRBC, is an adaptation of a United States Geological Survey (USGS) transient numerical flow, MODFLOW, model implementation for SLV. Adaptations involved (a) uniformly refined horizontal discretization of seven aquifer layers within a sub-area encompassing parts of RBCW and an adjacent watershed; (b) updated input data; and (c) MODFLOW’s Streamflow-Routing (SFR) package to simulate RBC flow and aquifer-stream seepage. Model predictions indicated that by the end of next March: (a) about 3% of the GI-induced recharge would remain within the unconfined aquifer in the HyperRBC area; (b) 66.6% of the recharge would flow northward into the downgradient continuation of the unconfined aquifer; and (c) 30.3% would discharge to nearby stream and river. In summary, predicted hydrologic changes due to the short-term GI-induced recharge highlight increased groundwater availability within and outside the study area for at least the subsequent 12 months, including high-water-demand summer. These findings show the importance of GI in interim environmental management and in enhancing the effective use of water resources. Full article

Gravity Recovery and Climate Experiment (GRACE) satellites primarily monitor changes in land water storage, including groundwater, soil moisture, lake and river surface water, and canopy and snow water. However, its coarse spatial resolution of 0.25 degrees limits its ability to observe smaller basins. To assess aquifer depletion and evaluate a long-term water resource management framework, GRACE data are crucial. It remains rare for GRACE-focused studies to be conducted in great depth. A comprehensive review of 80 articles published between 2011 and 2025 was conducted using the Scopus and Web of Science databases. These articles focused on downscaling GRACE data using machine learning (ML) methods. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines were used in this review. This study highlights the attributes of ML models, the input variables used, the evaluation metrics, and the output resolution. Based on the analysis of the articles, random forest (RF) methods were used in the majority of the papers. Gradient boosting (GB), artificial neural networks (ANN), support vector machines (SVM), support vector regression (SVR), and long short-term memory (LSTM) were the most widely used ML methods. As input variables, rainfall (Pr), soil moisture (SM), and runoff (Qs) are essential. In 2011, there were very few journal articles; since 2021, the number has increased. The number of published studies from China was the highest (24), followed by the USA (12) and Iran (9). A total of 38 journals published reviewed articles. In terms of articles, Remote Sensing generates 19%, Journal of Hydrology has 10%, and Journal of Hydrology: Regional Studies has 8%. The paper also discusses limitations, challenges, recommendations, and potential future directions for improving the accuracy of the GWS change prediction model. Full article

Rapid urbanization combined with global climate change is intensifying the Surface Urban Heat Island (SUHI) effect worldwide, posing significant risks to human health, thermal comfort, and quality of life in cities. Characterized by notably higher temperatures in urban areas compared to their rural surroundings, the SUHI phenomenon is driven by factors such as increased built-up density and reduced vegetation cover. In this context, open-source remote sensing data, particularly from the Landsat satellite series, play a crucial role in studying surface urban heat islands. Available freely, Landsat’s multispectral and thermal imagery provides extensive spatial coverage and consistent temporal frequency, enabling long-term diachronic analyses. This study leverages a 40-year time series (1984–2024) of Landsat thermal data to map surface temperature variations in urban environments between Kenitra and Rabat cities, facilitating the identification of heat-excess zones linked to anthropogenic factors. Based on the results obtained, the LU/LC maps show that the study area is characterized by the notable growth of urbanization over the period 1984–2024, particularly in the dynamic poles of the region such as the city centers of Kénitra, Rabat, and Sale. This dynamic is highlighted by an increase from 1.8% to 3% in the total area of the region, accompanied by a remarkable decrease in agricultural land and bare soils. The evaluation of the Random Forest (RF) model’s performance also indicates that it successfully classified the data and predicted the LU/LC classes effectively, as confirmed by metric indices such as the Receiver Operating Characteristic curve and the Kappa index, which present very high average values exceeding 90%. Furthermore, the exploitation of the thermal bands of Landsat images provided relevant information on surface temperature variation. The SUHI maps show that the Rabat-Sale-Kenitra (RSK) region experienced a progressive increase in temperature over the study period, rising from 27 °C in 1984 to 44 °C in 2024. This value could increase further due to the continuous dynamics of urbanization. Together, these tools provide a robust framework for understanding the spatiotemporal dynamics of surface urban heat islands and support sustainable urban planning. Full article