Search Results (2,923)

LULCC is a major driver of habitat fragmentation, biodiversity loss, and declining landscape connectivity, particularly in rapidly urbanizing regions. Although Islamabad has experienced substantial urban expansion and forest-cover change, long-term city-scale assessments linking land-cover dynamics with landscape connectivity remain limited. This study examined spatiotemporal LULCC in Islamabad from 1991 to 2021 and assessed whether recent forest recovery improved landscape structural connectivity. Landsat images acquired in 1991, 2001, 2011, and 2021 were classified into five land-cover categories: water, forest, built-up area, bare land, and agricultural land. Classification was performed using the Random Forest (RF) algorithm in Google Earth Engine (GEE). Landscape composition and spatial configuration were quantified using FRAGSTATS 4.3, while forest fragmentation was evaluated using the Landscape Fragmentation Tool v2.0 (LFT) with a 100 m edge threshold. The classifications achieved overall accuracies above 90%, with Kappa coefficients (K) greater than 0.85. Built-up area increased from 76.31 km², representing 7.55% of the study area, in 1991, to 258.62 km², or 25.60%, in 2021, demonstrating rapid urban expansion and associated habitat conversion. Forest cover increased to 340.86 km² in 2001, declined to 271.96 km² in 2011, and subsequently recovered to 409.22 km² in 2021. Despite this increase in forest extent, fragmentation metrics indicated persistent spatial subdivision and limited structural connectivity. High patch density (PD), reduced landscape aggregation, and changes in the largest patch index (LPI) indicated persistent spatial subdivision and limited habitat continuity. These findings highlight the value of integrating RF-based land-cover classification, multitemporal remote sensing, and landscape metrics for urban environmental monitoring. The findings suggest that future land-use planning should consider landscape connectivity, protection of existing forest patches, and spatially coordinated restoration alongside continued reforestation. Full article

Aerial image classification remains challenging due to complex spatial structures, high intra-class variability, and the need to capture semantic information across multiple spatial scales. This study investigates the potential of the Swin Transformer architecture to address the limitations of conventional deep learning approaches, particularly their restricted ability to model long-range contextual dependencies in high-resolution aerial images. The analysis focuses on the contribution of hierarchical feature representations extracted from different stages of the Swin Transformer to classification performance. Experiments were conducted on the AID, UCM21, and NWPU-RESISC45 benchmark datasets using multiple model variants and varying training proportions. The results show that combining intermediate and high-level features with the classification head achieves competitive and generally improved classification performance compared to other configurations, emphasizing the importance of multi-scale semantic feature representation. Additional analyses reveal that input image size and data augmentation strategies influence performance, while attention maps are used as an auxiliary visualization tool to support qualitative interpretation by highlighting relevant spatial regions. Overall, the findings indicate that hierarchical attention mechanisms and multi-stage feature integration can provide an effective representation strategy for Transformer-based aerial image classification. Full article

Ecosystems and the services they provide are essential for life but continue to undergo degradation worldwide. Satellite remote sensing has been essential for environmental mapping for decades, but can suffer poor accuracy when applied to mapping terrestrial ecosystems. Geospatial Foundation Models (GeoFMs) integrate diverse spatial data, including image data, spatial context, and temporal dynamics, and output readily available covariates called embeddings. GeoFM embeddings likely possess an improved ability to detect ecosystems over traditional approaches. In this study, we investigate whether the use of embeddings from Google’s AlphaEarth Foundations model yields improvements to ecosystem maps developed in the Republic of Maldives compared to single-date Sentinel-2 satellite imagery. We compare (1) per-class accuracies, (2) the effect of decreasing numbers of map classes on overall accuracy, and (3) the relationships between confidence, accuracy, and the number of training samples for each class. AlphaEarth outperforms Sentinel-2 (1) for individual ecosystems, (2) with increasing numbers of classes, and (3) with fewer training data samples while also being more confident in its classifications. We expect that these advantages will promote rapid uptake and expansion in the use of GeoFMs to address challenging spatial analyses, such as mapping global ecosystems and landscapes with limited available data. Full article

Global land abandonment drives secondary forest succession in mountains, yet long-term spatial dynamics remain poorly quantified. We traced 80 years (1945–2025) of forest expansion across Greece’s Rhodope Mountains using an integrated remote sensing framework. Historical baselines (>25% canopy closure) were derived via Object-Based Image Analysis of 1945 panchromatic orthophotos. Because grayscale media lacks spectral species resolution, taxa trajectories were inferred by intersecting 1945 canopy footprints with field-validated 2025 Sentinel-2 classifications. Landscape metrics and spatial statistics quantified colonization pathways for eight dominant taxa. Unconstrained natural forest expansion drove massive structural coalescence, doubling the Largest Patch Index and reducing patch densities universally. Spatial patterns corresponded with known dispersal mechanisms: heavy-seeded broadleaves (Fagus sylvatica, Quercus spp.) expanded conservatively near historical cores, whereas wind-dispersed pioneers (Pinus sylvestris, Betula pendula) colonized distant environments. Notably, Picea abies shifted downward (−204.7 m) toward valley floors. This was an empirical shift interpreted as a response to grazing cessation and potential reliance on riparian micro-refugia, rather than upward temperature-driven migration. While spontaneous coalescence enhances connectivity, unchecked homogenization threatens open-habitat biodiversity, requiring targeted silvicultural interventions to maintain landscape heterogeneity. Full article

Accurate and transferable soybean mapping is essential for agricultural monitoring and area verification, yet conventional Transformer models can be limited in modeling complex nonlinear phenological relationships and maintaining training stability. This study proposes an improved Transformer-KAN model for multi-temporal Sentinel-2 data. Temporal positional encoding, multi-head self-attention with relative positional bias, and a Pre-LayerNorm residual structure are introduced to strengthen phenological sequence modeling, while FastKAN replaces the conventional MLP-based feed-forward network to enhance nonlinear feature representation. The model was trained using 2023 samples from Hailun City and directly evaluated in Bozhou, McLean, and Cass without retraining or fine-tuning. Cross-year transferability was further evaluated by applying the Hailun-trained model to data from Bozhou and McLean from 2021 to 2025. The proposed model achieved overall accuracies of 0.975, 0.983, 0.958, and 0.966 in Hailun, Bozhou, McLean, and Cass, respectively, with corresponding Kappa coefficients of 0.895, 0.887, 0.883, and 0.916. Complexity analysis showed that Transformer-KAN required 0.8142 M parameters and 1.1967 M FLOPs, with an average inference time of 3.0191 ms per sample, compared with 0.6130 M parameters, 0.7971 M FLOPs, and 1.4009 ms per sample for the conventional Transformer, indicating that the improved feature representation was accompanied by increased computational complexity. Cross-year classification performance remained generally high from 2021 to 2025, although interannual variations were observed due to differences in crop growth conditions, phenological timing, and image acquisition quality. Discrepancies between remote-sensing-derived and officially reported soybean areas were mainly related to differences in statistical definitions and residual classification uncertainties, rather than model transferability. Overall, Transformer-KAN provides accurate and transferable soybean mapping and can serve as a spatially explicit complement to official agricultural statistics. Full article

Active jamming in complex electromagnetic environments can severely degrade radar remote sensing imaging and target detection, especially when deceptive and suppressive jamming components coexist. Existing deep learning methods usually formulate jamming recognition as a closed set classification task, which provides limited information about component superposition, time-frequency localization, and physical jamming parameters. To address these limitations, this paper proposes a prior-guided lightweight dual-task network for structured composite active jamming cognition. The proposed framework extracts multi-domain handcrafted features and decision tree based coarse priors from the received signal, and fuses them with short-time Fourier transform (STFT) time-frequency images through a confidence-gated MobileViT_CA-based network. The recognition branch predicts the jamming family, fine-grained class, and composite attributes, while the segmentation branch estimates component masks for copy, convolution, and noise components. A FiLM-conditioned mask refinement module further improves mask continuity and boundary quality, enabling the extraction of physical parameters such as bandwidth, center frequency, coverage duration, delay, slice width, and repetition interval. Experiments on a 22-class active jamming dataset show that the proposed method, built on a 1.92 M-parameter MobileViT_CA backbone, achieves 93.78% overall classification accuracy, 96.49% jamming family accuracy, and 89.17% accuracy on the 12 composite classes. The FiLM-conditioned mask refinement module improves the test-set mIoU from 67.55% to 82.93%, and most representative physical parameters are estimated with relative errors below 15%. Full article

Rapid and reliable assessment of structural damage following disasters is critical for prioritizing rescue operations. In this study, we present a unified deep learning framework for building damage assessment from satellite imagery. The proposed approach integrates segmentation-driven feature construction, morphological processing, cost-sensitive learning, and cross-disaster evaluation to support robust performance under limited and imbalanced data conditions. The framework combines an adapted U-Net for building localization with a hybrid convolutional neural network (CNN)-deep neural network (DNN) classifier for damage-level prediction and evaluates transferability across disaster events, geographic regions, and sensing conditions. The proposed method is evaluated on selected events from the xView2 Building Damage Assessment (xBD) and BRIGHT datasets, using optical imagery from xBD and pre-disaster optical and post-disaster Synthetic Aperture Radar (SAR) imagery from BRIGHT. Despite the limited and highly imbalanced event-specific samples, the framework achieves a mean cross-validation macro-F1 score of 70% and a maximum fold-level score of 77% on the Mexico earthquake subset of xBD and up to 98% on earthquake-related events in BRIGHT. Cross-validation characterizes performance variability across source-image-grouped data partitions, while cross-disaster evaluation reveals event-dependent transferability and provides a preliminary indication that structural domain similarity may be related to transfer performance. Although the evaluation is constrained by data availability, the results indicate that lightweight, cost-sensitive deep learning frameworks may support auxiliary post-disaster screening and decision support in resource-constrained scenarios. This study highlights both the potential and the remaining challenges of deploying artificial intelligence (AI) for rapid post-disaster assessment. Full article

Forest inventory compartments provide extensive and management-relevant reference information for satellite-based tree species mapping, but their dominant-species attributes are defined at the stand level rather than for individual image pixels. Existing applications commonly derive training samples from compartment centres or assign polygon labels to enclosed pixels, which may introduce boundary effects, uneven class representation, and disproportionate contributions from individual compartments. However, the intermediate step of converting inventory polygons into spatially controlled pixel-level reference samples has received comparatively limited attention. Here, we developed a geometry-constrained reference sample construction framework that integrates interior-position screening, class balancing, source compartment contribution control, and spatial-spacing constraints. The framework was evaluated for mapping Korean pine, larch, white birch, and spruce in a temperate mixed forest in northeastern China using Sentinel-1/2 time series and ancillary predictors. Predictor–classifier combinations were selected using compartment-grouped out-of-fold evaluation, sampling workflows were compared on 60 independently withheld compartments, and the final map was further assessed using 306 independent reference points. Relative to centroid sampling, the geometry-constrained workflow increased compartment-level macro-F1 from 0.612 to 0.709. XGBoost with optical time series and ancillary predictors achieved the best development-set performance, while inclusion of the complete Sentinel-1 time series provided no further gain. The final model achieved an overall accuracy of 0.827 and a macro-F1 of 0.820 on the independent reference points. Aggregation of 10 m predictions further enabled compartment-level characterization of mapped dominant species, dominance strength, and mixing intensity. These results demonstrate that reference sample construction is a consequential step in tree species mapping from polygon-based forest inventories and provide a practical approach for linking pixel-level remote sensing classification with forest management units. Full article

Drought is a complex and periodic issue that has a significant impact on agriculture and water resources, particularly in semi-arid areas. This study evaluated meteorological and agricultural drought conditions in the Thanjavur district by combining rainfall data with remote-sensing methods. Meteorological drought was analyzed using 33 years of rainfall data and the Standardized Precipitation Index (SPI) (1992–2024) using 20 rainfall stations for the data available between 1992 and 2024. The spatial variation in rainfall was analyzed using Kriging interpolation in GIS. Agricultural droughts were analyzed using the Normalized Difference Vegetation Index (NDVI) and Vegetation Con0dition Index (VCI) using multi-temporal Landsat satellite images (Landsat 5 and Landsat 8). Land Use and Land Cover (LULC) classification was included to determine drought vulnerability across different land types. The NDVI and VCI indices showed an intensification of agricultural drought in 2010. The results demonstrated temporal and spatial differences in drought conditions for the years 1992, 1997, 2004, 2009, 2014, 2019, and 2024 and indicated that the region experienced periodic severe drought conditions of 3%, 3%, 3%, 8%, 19%, 9%, and 11% in the study area, respectively. During the drought period, the vegetation indices showed a strong sensitivity of agricultural areas to changes in rainfall, and low NDVI and VCI values indicated increased vegetation stress. Meteorological and agricultural droughts were integrated using the Analytical Hierarchy Process (AHP) method by combining various indicators to analyze the drought condition across the Thanjavur district. The multiple criteria decision-making (MCDM) method uses pairwise comparisons of various factors, such as giving high importance to SPI and rainfall, followed by vegetation indices and LULC. The consistency ratio validated the reliability of the weighting term. This method shows that combining meteorological and remote sensing indicators advances a robust framework for monitoring and assessing droughts. Conceptual droughts illustrate how meteorological droughts are associated with the development of agricultural droughts. The results of this study can be adopted for effective drought management, irrigation planning, and sustainable agricultural practices in this region. Full article

Land subsidence induced by excessive groundwater withdrawal has become one of the most significant geohazards affecting the Konya Closed Basin, Turkey. Although previous studies have successfully monitored ground deformation using geodetic and remote sensing techniques, limited attention has been devoted to transforming deformation measurements into quantitative, spatially classified hazard information. This study presents a severity-based framework for delineating land-subsidence hazard zones and critical hotspots in the Konya metropolitan area by integrating SBAS-InSAR observations and spatial statistical analyses. A total of 82 Sentinel-1 SAR acquisitions (41 ascending and 41 descending images) acquired between January 2023 and May 2026 were processed using the Small Baseline Subset (SBAS) technique. Ascending and descending line-of-sight deformation measurements were combined to derive vertical deformation rates, which were integrated with spatial statistical indicators and a composite severity index to quantify deformation clustering and classify subsidence severity. Hazard zones and critical hotspot areas were delineated through severity-based classification and spatial connectivity analyses. The results reveal a continuous north–south-oriented subsidence deformation belt extending across the eastern Konya. Maximum vertical subsidence rates exceeded 230 mm/yr, while spatial statistical analyses confirmed strongly clustered and statistically significant deformation patterns. Severity-based hazard zonation identified four hazard classes and a continuous high-hazard corridor. Clustering analysis further identified a dominant hotspot belt covering approximately 160 km², with mean subsidence rates of approximately 142 mm/yr. A sensitivity analysis of the composite severity index weighting scheme, the spatial statistical neighborhood distance, the DBSCAN clustering parameters, and the number of Jenks severity classes confirmed that the resulting hazard zones and critical hotspot belt are robust to reasonable parameter variations. The findings demonstrate that land subsidence in Konya is organized as a spatially continuous regional-scale deformation system rather than a collection of isolated subsidence centers. The proposed framework transforms InSAR-derived deformation measurements into quantitative, decision-support hazard information and provides a transferable methodology for land-subsidence hazard assessment in groundwater-stressed urban environments. Full article

Optical remote sensing images acquired in rugged mountains are affected by reflectance distortion caused by both topography and shadows. Most topographic correction (TC) methods normalize sunlit slopes but can become unstable in self shadow and cast shadow, where little or no direct solar radiation reaches the surface. This study builds on the topographic shadow effect correction (TSEC) model and develops TSEC+TC, a partitioned framework for horizontal equivalent normalization. Using a shadow mask extended to penumbra, the framework integrates TSEC for shadowed pixels with conventional TC for sunlit pixels. Both branches target horizontal equivalent reflectance, enabling simultaneous correction of topographic and shadow effects across the scene. We implemented TSEC+TC with path length correction (PLC) and SCS with C (SCSC) models and evaluated it using ten multi-temporal Landsat 8 OLI scenes under different illumination conditions. The results showed that TSEC+TC reduced terrain-related brightness variation and improved land cover classification in the auxiliary comparison relative to uncorrected and TC-only results. For TSEC+SCSC, the R² values between corrected reflectance and cosi were below 0.025 for both Red and SWIR1 bands, and the coefficient of variation of reflectance across aspects was consistently lower than the corresponding values for SE and SCSC, with a maximum of 36.00%. Shadow area analyses indicated that TSEC+TC compensated reflectance distortion in self shadow and cast shadow areas, reduced TC-induced outliers, and better preserved spectral patterns than TC-only correction. Tests using Sentinel-2 MSI and GF-1 WFV imagery provided preliminary evidence of applicability to other sensors. Accounting for the topographic shadow effect improved TC performance in complex mountainous areas. Full article

Remote sensing scene classification plays a vital role in various Earth observation applications. Although supervised learning remains the dominant paradigm, vast quantities of unlabeled imagery remain significantly underutilized. To leverage these unlabeled resources and enhance categorization accuracy, we propose a novel framework based on the Vision Transformer (ViT) that integrates a dynamic masking strategy with a cross-modal semantic learning mechanism. Specifically, a dynamic masking strategy guided by a smooth reconstruction loss is designed to learn robust feature representations from unlabeled samples prior to downstream fine-tuning. Furthermore, we incorporate cross-modal learning to enrich semantic information, thereby addressing the inherent supervisory limitations of conventional one-hot labels. Comprehensive experiments demonstrate that the proposed method significantly improves classification accuracy while maintaining high pre-training efficiency and strong generalization capabilities. Full article

Effective control and management of the encroaching and invasive Vachellia karroo (V. karroo) in grassland and savanna biomes depends on accurate information about its spatial distribution, making remote sensing approaches essential for mapping the extent of affected areas. Although Sentinel-2 satellite data are widely used for land use and land cover applications, they often lack the spatial details required to distinguish woody species like V. karroo. The fusion of Sentinel-2 data with high-resolution UAV imagery offers a promising approach to enhance spectral information for species-level discrimination. This study evaluated UAV, Sentinel-2, and fused UAV–Sentinel-2 imagery for discrimination of V. karroo in grassland and savanna biomes of the Eastern Cape, South Africa. Field data and imagery were collected in October 2022 and classified using Random Forest (RF) and Support Vector Machine (SVM) algorithms to distinguish V. karroo. The findings showed that V. karroo was more prevalent in the savanna biome. SVM marginally outperformed RF in classifying V. karroo in the grassland biome, achieving overall accuracies ranging from 68.9% to 97.4%, compared to 57.8% to 97.4% for RF. Among the datasets, the fused UAV–Sentinel-2 images yielded the highest classification accuracy, with an overall accuracy of 97.4% and a kappa coefficient of 0.96. The UAV images also demonstrated high classification accuracy, with an overall accuracy of 91.67% and a kappa coefficient of 0.77, confirming its value for fine-scale mapping and reference data support. In contrast, the Sentinel-2 images produced lower classification accuracy, with an overall accuracy of 84.6% and a kappa coefficient of 0.75, mainly due to their coarser spatial resolution. Classification was more challenging in the savanna site, where mixed vegetation structure increased confusion between V. karroo and grass. These findings show that fused UAV–Sentinel-2 images can improve species-level discrimination, while UAV and Sentinel-2 data remain complementary for fine-scale mapping and broader monitoring of bush encroachment in grassland and savanna ecosystems. Full article

Accurate mapping of crop residue cover (CRC) is important for sustainable agricultural management because residue supports soil health, erosion control, and carbon sequestration. Traditional ground-based CRC methods are labor-intensive and spatially limited, increasing interest in UAV-based remote sensing. UAVs can carry RGB, multispectral, and hyperspectral sensors, which capture different spectral information for distinguishing crop residue from soil. This study compared four high-spatial-resolution (2.5 cm) UAV imagery types—RGB, multispectral, visible–near-infrared (VNIR) hyperspectral, and shortwave infrared (SWIR) hyperspectral—for fine-scale CRC classification. A fully connected neural network (FCNN) was developed to classify residue and soil pixels. Performance was evaluated using two complementary approaches: pixel-level accuracy assessment based on manually delineated image samples and plot-level validation against residue percentages derived from ground photos. Results showed that high pixel-level classification accuracy values were achieved across all imagery types, with overall accuracies above 94%. However, plot-level validation revealed that sensor performance depended on the evaluation metric considered. Multispectral imagery produced the highest R² with ground photo-derived reference CRC values (R² = 0.672). These results indicate that greater spectral dimensionality did not necessarily improve plot-level CRC estimation under the tested field conditions. More importantly, the findings show that high pixel-level classification accuracy does not necessarily translate into stronger plot-level CRC estimation, highlighting the importance of using complementary validation approaches when evaluating UAV-based CRC estimation. Full article

This study proposes an adaptive Support Vector Machine (SVM) classification method based on an enhanced Starfish Optimization Algorithm (SFOAE-SVM) for hyperspectral image (HSI) classification. HSI classification remains a critical challenge in remote sensing due to the high dimensionality of spectral features, spectral mixing, scarcity of labeled samples, and complex land-cover distributions. The SFOAE algorithm is used for global hyperparameter optimization of SVMs, accounting for the distributional characteristics of the target HSI data. The approach aims to improve search capability and reduce the likelihood of convergence to local optima by combining multi-dimensional topology-oriented expansion with global exploration. Experimental results demonstrate that SFOAE-SVM achieves competitive classification accuracy and stable performance compared with conventional SVM parameter selection strategies and other optimization-based methods across three benchmark hyperspectral remote-sensing datasets. These results indicate that the proposed method offers a promising optimization-assisted SVM framework for hyperspectral remote-sensing image classification. Full article