Search Results (4,446)

Mountain forests on the western edge of the Sichuan Basin are challenging to monitor at high resolution because rugged topography, cloud cover, and Landsat-7 SLC-off artifacts create data gaps, while the 2008 Wenchuan earthquake and subsequent restoration further alter vegetation dynamics. We fused Landsat 5/7/8/9 surface reflectance with MODIS MOD13Q1 using an index-then-fusion STARFM framework to reconstruct a continuous 30 m NDVI record for 2000–2024 and quantified forest fraction dynamics using annual forest/non-forest maps, transition analysis, and K-means clustering of pixel-wise NDVI trajectories. To identify dominant controls, we applied a multi-output random forest with spatial block cross-validation and SHAP attribution. The fused NDVI agrees well with MODIS across 100,000 samples (R² = 0.953; RMSE = 0.032), and the regional mean NDVI increased from 0.711 (2000) to 0.774 (2024), showing a post-2008 decline–stagnation–recovery pattern. Forest fraction rose from 48.2% to 72.9%, with accelerated gains after 2010 (+21.4%), and improving trajectories dominated (70.95%), concentrating near the Longmenshan fault zone. The driver model generalized well (micro-mean R² = 0.875), and SHAP ranked elevation (32.6%) and initial forest fraction (32.3%) above temperature and precipitation. These results provide high-resolution evidence of mountain forest change and its primary controls to support terrain-informed ecological management. Full article

Seasonal tropical wetlands such as the Brazilian Pantanal are increasingly threatened by climate variability and extreme hydrological events, creating a need for robust monitoring tools that capture flood dynamics at high spatial and temporal resolution. This study used Sentinel-1 Synthetic Aperture Radar (SAR) imagery to map and monitor flooding in the northern Pantanal, a Ramsar site renowned for its wildlife, between 2017 and 2020. Ground Range Detected (GRD) VV-polarized scenes were preprocessed using radiometric terrain normalization and speckle filtering (Lee filter, 5 × 5 window) to improve the separability of water and non-water surfaces. Flooded areas were initially extracted with Otsu’s histogram thresholding and validated using high-resolution optical imagery (PlanetScope and Landsat-8). A supervised Random Forest classifier then refined land-cover discrimination into three classes (open water/flood, open land/vegetation, and others), achieving an overall accuracy of 97.70% on the independent testing dataset (n = 6622), while temporal consistency was supported by Cuiabá River hydrological data. The results revealed strong interannual variability in flood extent, with inundation covering 34.7% of the reserve in March 2017 compared with 0.75% in March 2020 and reaching a peak of 79.9% in April 2017. Overall, Sentinel-1 SAR effectively delineated open water and flood-affected surfaces under persistent cloud cover, demonstrating its value for complementing existing products such as MapBiomas, strengthening wetland management, and supporting scalable flood monitoring in other tropical flood-prone Ramsar sites. Full article

Changes in land use and land cover (LULC) are among the leading contributors to global environmental transformation. Analyzing these dynamics is essential for understanding historical land utilization patterns and identifying the key drivers behind such shifts. This research focuses on LULC changes in the Kunar region of eastern Afghanistan. To classify the LULC types, the study area was divided into nine major classes using the Support Vector Machine (SVM) algorithm, based on Landsat 07 Enhanced Thematic Mapper Plus (ETM+) data for 2004 and Landsat 8 Operational Land Imager (OLI) data for 2014 and 2024. Past and present changes were evaluated using ArcGIS 10.8, while future scenarios for 2034 and 2044 were simulated using the Land Change Modeler (LCM) embedded in the TerrSet platform, combined with the Cellular Automata–Markov Chain (CA-MC) model with 90% kappa agreement validation value. From 2004 to 2024, grassland expanded significantly from 68.93% (3406 km²) to 73.94% (3654 km²). Built-up areas grew from 0.59% (29.10 km²) in 2014 to 1.02% (50.39 km²) in 2024. Conversely, dense forest cover declined from 27.50% (1358.90 km²) to 22.96% (1134.75 km²), a decrease of 224.15 km². Barren land, after a temporary increase, also showed a net decline. Projections for 2034 and 2044 suggest a further reduction in forested areas to 1077 km², while grasslands and urbanized zones are expected to increase to 3690 km² and 60.63 km², respectively. These trends emphasize a swift transition in land use patterns, primarily driven by the conversion of forested and barren landscapes into settlements and grasslands. The findings underline the urgent need for implementing sustainable land management strategies to curb environmental degradation and ensure balanced land resource utilization in the future. Full article

The Tianshan–Pamir mountain region, serving as the core “water tower” for countries in Central Asia east of the Aral Sea, is a critical bulwark for sustaining downstream socioeconomic systems. However, constrained by complex topography and harsh climatic conditions, this region suffers from a severe scarcity of long-term, continuous hydrological observation data. This study focuses on a typical data-scarce mountainous area, coupling UAV and satellite imagery-based (e.g., Landsat/Sentinel) flow inversion with a hybrid spatial regionalization method—integrating spatial proximity, basin similarity, and regression-based hydrograph reconstruction—to quantitatively estimate long-term discharge time series. The results indicate that, for the validation of instantaneous discharge inversion, the Nash–Sutcliffe efficiency coefficient (NSE) at 29 river cross-sections was consistently greater than 0.80, with the coefficient of determination (R²) reached 0.94 (p < 0.01). Subsequently, for the long-term discharge series reconstructed using the regionalization method, the NSE values at three representative verification sites—each corresponding to a distinct basin type—were 0.88, 0.84, and 0.86, respectively. These findings exhibit higher precision compared to direct temporal upscaling, confirming the reliability of the regionalization method across varying temporal scales. An analysis of monthly discharge trends from 1989 to 2020 revealed a decreasing trend in the discharge of glacier-dominated rivers, with an average rate of change of −2.89 ± 2.54% (p < 0.05); the Pamir Plateau experienced the largest decline (−4.89 ± 6.58%), which is closely linked to large-scale glacial retreat within the basins. Conversely, the discharge of non-glacier-dominated rivers showed an increasing trend, with a multi-year average rate of change of +0.32 ± 8.43% (n.s.), primarily driven by shifts in precipitation and vegetation cover. This research introduces a new approach for hydrological monitoring in data-scarce regions and provides essential data and methodological support for water resource management decisions in arid zones. Full article

Accurate mapping of near-surface air temperature ($T_{\mathrm{air}}$) at the fine spatial resolution is required for city-scale monitoring and remains a critical challenge in Earth Observation (EO). Reliance on ground-based measurements is constrained by their sparse spatial coverage and high operational costs. We present a novel, scalable machine learning framework designed to overcome this limitation. Our method utilizes interpretable Convolutional Neural Networks (CNNs) to fuse high-resolution Landsat data, integrating both thermal and reflective spectral bands, with contextual spatiotemporal metadata. This approach allows for inference, at 30 m resolution, of $T_{\mathrm{air}}$ fields without relying on dense, localized ground monitoring networks. Our hybrid CNN architecture is optimized for spatial generalization, maintaining strong and transferable performance (station-wise $R^2\approx 0.88$) across diverse environments from humid coasts ($R^2\approx 0.89$) to arid interiors ($R^2\approx 0.84$). Although focused on a specific geographical region, our results suggest a robust and reproducible pathway for generating spatially consistent temperature fields from globally available EO archives, directly supporting urban heat island mitigation, climate policy development, and high-resolution public health assessment worldwide. Full article

In response to land-use and land-cover (LULC) changes in South Africa, which have varied effects on biodiversity, several studies have characterized LULC changes using remote sensing data due to its cost-effectiveness, repetitiveness, spatial coverage and flexibility. However, the geotemporal and methodological characteristics of these studies remain relatively unknown. In this regard, we review remote sensing-based studies conducted in South Africa using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). From the 343 articles retrieved from Web of Science, Google Scholar, and Scopus databases, 103 studies were eligible for analysis. The analysis showed that (a) various remote sensing datasets were increasingly and effectively used to characterize LULC in South Africa over the period 2001–2024, primarily Landsat data with integration of various advanced classification algorithms; (b) most studies were conducted in the eastern seaboard, particularly in the Maputaland–Pondoland–Albany hotspot and highveld to the north, and (c) much research dealt with issues pertaining to “pristine class” conversion to urban area and other human-induced activities, mainly in biodiversity-rich landscapes. Overall, LULC studies achieved consistently reliable accuracies, largely using publicly available geospatial datasets, thereby creating an accessible foundation for all researchers. LULC research is expected to increase as conservation efforts strengthen amid ongoing developments in South Africa. Full article

Accurate tree species mapping is critical for forest inventory, biodiversity assessment, and ecosystem management. In mountainous regions, terrain-induced radiometric non-stationarity and limited field access often produce scarce, clustered, and environmentally biased samples, limiting model generalization. To address this issue, this study proposes a terrain-aware self-supervised representation learning framework for tree species classification under small-sample conditions. The framework integrates terrain information into representation learning and adopts a hybrid contrastive–generative self-supervised strategy to learn discriminative and terrain-robust features from large volumes of unlabeled multi-source remote sensing data. These learned representations are subsequently combined with limited field samples to produce regional-scale tree species maps. Experiments conducted across Yunnan Province, China, using Sentinel-1, Sentinel-2 and Landsat time-series data show that the proposed framework substantially improvesa class separability and classification robustness in complex mountainous environments. The framework achieves an overall accuracy of 75.8%, significantly outperforming conventional feature engineering (38.3–40.6%) and supervised deep learning models (37.3–47.8%). Species with relatively homogeneous structure and strong ecological niche dependence can be accurately mapped with limited training samples, whereas structurally complex forest communities require broader environmental sample coverage. Overall, the results highlight the potential of terrain-aware self-supervised representation learning as a scalable and data-efficient paradigm for forest mapping in mountainous and environmentally heterogeneous regions. Full article

Wetlands are highly productive ecosystems that play a vital role in maintaining ecological balance. This study presents a geospatial assessment of the Harike Wetland, Punjab, using hyperspectral (PRISMA) and multispectral (Landsat series) satellite data to analyze its ecological structure and water dynamics. Six spectral indices—Normalized Difference Vegetation Index (NDVI), Normalized Dif-ference Aquatic Vegetation Index (NDAVI), Normalized Difference Water Index (NDWI), Modified NDWI (MNDWI), Floating Algal Index (FAI), and Algal Bloom Detection Index (ABDI)—were employed to map terrestrial agricultural cropland (paddy), aquatic vegetation and surface water. Threshold-based classification of index outputs was used to estimate the spatial extent of major land cover types. NDVI and NDAVI effectively captured vegetation patterns, while NDWI and MNDWI improved surface water delineation. Additionally, Z-spectral analysis was applied to extract and compare the reflectance profiles of agricultural cropland, open water, and algae, as well as built-up areas, enhancing spectral contrast and classification accuracy, particularly in spectrally mixed zones. The integration of index-based mapping with detailed spectral profiling demonstrates the advantage of combining multispectral and hyperspectral data for wetland monitoring and provides valuable insights to support wetland conservation and sustainable water management. Full article

Bangka’s mangroves contribute to Indonesia’s species-rich coastal ecosystems, yet they have experienced substantial degradation, largely driven by human activities such as tin mining. Establishing long-term records of mangrove extent is essential for understanding distribution dynamics, assessing impacts, and guiding conservation strategies. In this study, we applied change detection techniques, a random forest classifier, and the LandTrendr algorithm to analyze Landsat time-series data from 1994 to 2023 across Bangka Island. We quantified multi-decadal changes in mangrove extent, periods of disturbance and recovery, and discrepancies between local and global datasets. Mangrove dynamics were spatially heterogeneous, with both expansion and loss observed across regions in landward and seaward settings. Over the 30-year period, total gains reached 4956.39 ha (10.30% of the baseline), yet the net change indicated an overall loss of 1055.85 ha. LandTrendr analysis further revealed sustained mangrove expansion since 1989. Observed changes reflect the combined influence of natural processes, including accretion and erosion, and human pressures, particularly tin mining. Although net area loss aligns with national trends, the drivers in this mining-dominated region differ from those elsewhere, and some mangrove areas remain absent from global datasets. These findings emphasize the need to better capture local gain–loss dynamics to support effective management and conservation. Full article

Urban areas in arid environments are increasingly affected by the urban heat island (UHI) effect, which intensifies thermal stress, disrupts ecological balance, and poses challenges for sustainable urban development. Understanding and predicting spatiotemporal variations in land surface temperature (LST) and land use dynamics is therefore critical for effective urban planning. This study develops a predictive framework for Riyadh, Saudi Arabia, using long-term Landsat time series data (1993–2023) and deep learning models to evaluate urban thermal patterns via the Urban Thermal Field Variation Index (UTFVI). Artificial Neural Networks (ANNs) with six hidden layers for LST and seven for UTFVI forecast future trends up to 2043. The results indicate that urban areas expanded by 521.62 km², increasing from 8.73% to 19.56% between 1993 and 2023, and are projected to reach 1509.40 km² (25.28%) by 2043, while vegetation coverage declined from 0.771% to 0.674%. The highest average summer LST increased from 56.73 °C in 1993 to 59.89 °C in 2023 and is predicted to rise to 60.79 °C by 2033 and 61.52 °C by 2043. Winter temperatures exhibited a comparable upward trend, rising from 30.75 °C to 32.33 °C in 2023 and projected to reach 34.48 °C by 2043. UTFVI analysis revealed a substantial expansion of weak thermal field zones, which covered 2778 km² in 2023 and are expected to reach 3018.44 km² (57%) by winter 2043, accompanied by a marked contraction of strong thermal field areas. The ANN models achieved a high predictive performance, with RMSE values of 0.759 (summer) and 0.789 (winter) for UTFVI and correlation coefficients of 0.91 and 0.89, respectively. Projections further indicate that, by 2043, approximately 39.31% of the study area will experience summer temperatures between 48 °C and 53 °C, compared to 5.59% in 2023. These findings highlight the accelerating interaction between urban growth and thermal intensification in arid cities. The proposed modeling framework provides a robust decision-support tool for urban planners and policymakers to mitigate UHI impacts and promote climate-resilient and sustainable urban development. Full article

To address the limitations of traditional forest above-ground biomass (AGB) retrieval methods—namely, the restricted accuracy of physical models and the limited generalization ability of purely data-driven models—this study proposes a differentiable physical modeling (DPM) approach for forest AGB estimation. The method adopts the water cloud model (WCM) as a physics-based framework, grounded in radiative transfer theory, and integrates C-band synthetic aperture radar (SAR) data with multispectral imagery. Within the PyTorch tensor computation framework, automatic differentiation (AD) is employed to seamlessly couple the WCM with the deep fully connected neural network (DFCNN), enabling a differentiable implementation of the WCM. Using mean squared error (MSE) as the loss function, the neural network parameters are optimized through backpropagation and gradient descent, thereby constructing an end-to-end trainable DPM model that effectively retrieves forest AGB while preserving physical interpretability and generalization capability. To validate the proposed method, two representative test sites were selected: Simao in Pu’er, Yunnan Province, and Genhe in Inner Mongolia. GF-3 PolSAR and RADARSAT-2 data were used to extract backscattering coefficients and compute the radar vegetation index (RVI), while Landsat 8 OLI imagery was employed to calculate the normalized difference vegetation index (NDVI), difference vegetation index (DVI), and soil-adjusted vegetation index (SAVI). These datasets, together with ASTER GDEM, field-measured biomass, and other relevant datasets, were integrated to construct a multisource dataset combining remote sensing and ground observations. The performance of the DPM model was then compared with the traditional WCM and several data-driven models, including the fully connected neural network (FNN), generalized regression neural network (GRNN), RF, and Adaptive Boosting (AdaBoost). The results indicate that the DPM model achieved R² = 0.60, RMSE = 24.23 Mg/ha, Bias = 0.4 Mg/ha, and ubRMSE = 22.43 Mg/ha in Simao, and R² = 0.48, RMSE = 33.29 Mg/ha, Bias = 0.87 Mg/ha, and ubRMSE = 33.28 Mg/ha in Genhe, demonstrating consistently better performance than both the WCM and all tested data-driven models. The DPM model demonstrated consistent performance across ecologically contrasting forest regions. It alleviated the systematic overestimation bias of purely data-driven models and overcame the limitations in predictive accuracy resulting from the simplified structure of the WCM. The differentiability of the WCM enables the loss function errors to be backpropagated through the neural network, thereby allowing the optimization of the physical model parameters. Overall, the DPM framework integrates the advantages of both physical models and data-driven approaches, providing an estimation method with acceptable accuracy for forest AGB retrieval. It also offers theoretical and practical insights for the integration of deep learning and physical knowledge in other research fields. Full article

Bolivia is home to approximately 20% of the tropical glaciers in South America, which are sensitive indicators of climate change and critical water resources. Glaciers in the Cordillera Real supply meltwater to Bolivia’s administrative capital, La Paz, making it important to accurately assess their evolution. This study reassesses the trajectory of glacier loss in the Cordillera Real between 1992 and 2024. We construct a time-evolving glacier inventory utilizing remote sensing data (Landsat) and techniques to limit the impact of ephemeral snow cover. Our inventory is at a temporal resolution (5- to 8-year spacing) that allows us to assess the trajectory of glacier loss using statistical models. Between 1992 and 2024, the Cordillera Real lost 103.67 ± 9.97 km² of glacierized area, representing a 42.0 ± 2.1% reduction. We find that glaciers in the Cordillera Real have been retreating at a constant absolute loss rate of 2.99 [2.32, 3.67] km² yr⁻¹ and a constant fractional loss rate of 1.6 [1.3, 1.9]% yr⁻¹, contrasting with past studies that suggest accelerating or decelerating loss rates. Our findings provide new insights into the current extent of glaciers in the Cordillera Real and their longevity. The time-evolving inventory is available for use in future studies on the evolution of glaciers in the Cordillera Real and the impacts of their continued loss. Full article

This study investigates the cooling effects of coastal wetland systems in Hue City, Vietnam. The analysis focuses on their riparian buffer zones, defined here as areas within 600 m of the wetland boundary. Landsat 8 imagery was used to derive land surface temperature (LST) from 1 March to 31 July 2025—a recent period marked by multiple heatwaves across the region. To assess the cooling performance of wetlands, data samples were collected within the buffer zones. A Light Gradient Boosting Machine was trained to characterize the relationship between cooling intensity and a set of influencing factors (e.g., distance to wetland boundary, land use/land cover, built-up density, and green space density). The model explains approximately 91% of the variation in cooling intensity around wetlands. Notably, a machine-learning-based simulation framework was proposed to attain insights into the cooling characteristics of the riparian zone. The result indicates a mean cooling effect of about 2 °C and an effective cooling distance of 210 m from the wetland boundary. Partial dependence analysis further reveals that increasing built-up density substantially weakens cooling performance and implies that, for the conditions observed in Hue City, maintaining built-up density near wetlands below roughly 45% is favorable for sustaining effective cooling of the blue space, as indicated by the model-based partial dependence analysis. Overall, the research findings provide a data-driven basis for informing urban planning and wetland management in Hue City to mitigate heat stress. Full article

Mountain ecosystems are susceptible to climate change, and alpine treeline ecotones (ATEs) represent one of the significant responsive indicators of climate-driven environmental change. This study examines long-term spatiotemporal dynamics of the ATE across the Eastern Slopes of the Canadian Rocky Mountains (ESCR) from 1984 to 2023, with the objective of assessing whether regional climate warming has influenced ATE extent and elevation across different aspects and watersheds. Multi-decadal Landsat imagery, ERA5-Land temperature data, and topographic variables were integrated within a Google Earth Engine (GEE) framework to map ATEs using the Alpine Treeline Ecotone Index (ATEI), a probabilistic approach designed to capture transitional vegetation zones. Temporal trends were evaluated using non-parametric statistics, correlation analyses, and watershed- and aspect-based comparisons. Results indicate that the total alpine treeline ecotone (ATE) area in the ESCR was approximately 13.3% larger in 2023 than in 1984. However, the temporal evolution of ATE extent and elevation was non-monotonic, and linear trend analyses did not detect statistically significant increasing or decreasing trends over the full study period. ATE elevation and expansion exhibited pronounced spatial heterogeneity, with greater changes occurring on north- and northwest-facing slopes and within selected watersheds. In contrast, summer (July–September) temperatures increased significantly (+2.84 °C), exceeding global land-only warming rates, and vegetation greenness (NDVI) showed a strong, statistically significant positive relationship with temperature. These findings show that while climate warming has clearly increased vegetation productivity, elevational ATE dynamics remain spatially heterogeneous and temporally non-synchronous with summer temperature trends. Full article

The Urban Heat Island (UHI) effect represents a major barrier to sustainable urban development, amplifying energy demand, public health risks, and climate vulnerability. This study provides an advanced geospatial assessment of UHI dynamics in Southampton, UK, using Landsat 8 and 9 imagery (2017–2023) to evaluate seasonal and interannual variations relevant to climate-resilient urban planning. This study integrates spatial techniques, including Land Surface Temperature estimation, NDVI-based emissivity modelling, hotspot analysis, and urban–rural gradient profiling, to identify persistent UHI hotspots concentrated in high-density commercial and industrial zones, with intensities reaching 2–3 °C above the citywide mean. It combines seasonal UHI mapping, hotspot analysis, and urban–rural gradient profiling to provide a comprehensive assessment of Southampton’s thermal landscape. The findings reveal persistent UHI hotspots in the city centre and industrial zones, with intensity peaks of 2–3 °C above the mean. Temporal analysis reveals winter-intensified UHI patterns, consistent with climate-sensitive processes observed in temperate coastal environments. Green spaces demonstrate measurable cooling benefits (up to ~1 °C), underscoring their role as sustainable nature-based mitigation strategies. By delivering a replicable, data-driven framework for continuous environmental monitoring, the research directly supports sustainable urban design, targeted greening interventions, and climate-adaptation policies. The findings provide practical tools for reducing heat stress, enhancing energy efficiency, and strengthening long-term urban resilience in medium-sized coastal cities. Full article