Search Results (1,168)

Forest resources are among the most important ecosystems on the earth. The semantic segmentation and accurate positioning of ground objects in forest remote sensing (RS) imagery are crucial to the emergency treatment of forest natural disasters, especially forest fires. Currently, most existing methods for image semantic segmentation are built upon convolutional neural networks (CNNs). Nevertheless, these techniques face difficulties in directly accessing global contextual information and accurately detecting geometric transformations within the image’s target regions. This limitation stems from the inherent locality of convolution operations, which are restricted to processing data structured in Euclidean space and confined to square-shaped regions. Inspired by the graph convolution network (GCN) with robust capabilities in processing irregular and complex targets, as well as Swin Transformers renowned for exceptional global context modeling, we present a hybrid semantic segmentation framework for forest RS imagery termed GSwin–Unet. This framework embeds the GCN model into Swin–Unet architecture to address the issue of low semantic segmentation accuracy of RS imagery in forest scenarios, which is caused by the complex texture features, diverse shapes, and unclear boundaries of land objects. GSwin–Unet features a parallel dual-encoder architecture of GCN and Swin Transformer. First, we integrate the Zero-DCE (Zero-Reference Deep Curve Estimation) algorithm into GSwin–Unet to enhance forest RS image feature representation. Second, a feature aggregation module (FAM) is proposed to bridge the dual encoders by fusing GCN-derived local aggregated features with Swin Transformer-extracted features. Our study demonstrates that, compared with the baseline models TransUnet, Swin–Unet, Unet, and DeepLab V3+, the GSwin–Unet achieves improvements of 7.07%, 5.12%, 8.94%, and 2.69% in the mean Intersection over Union (MIoU) and 3.19%, 1.72%, 4.3%, and 3.69% in the average F1 score (Ave.F1), respectively, on the RGB forest RS dataset. On the NIRGB forest RS dataset, the improvements in MIoU are 5.75%, 3.38%, 6.79%, and 2.44%, and the improvements in Ave.F1 are 4.02%, 2.38%, 4.72%, and 1.67%, respectively. Meanwhile, GSwin–Unet shows excellent adaptability on the selected GID dataset with high forest coverage, where the MIoU and Ave.F1 reach 72.92% and 84.3%, respectively. Full article

Land surface temperature (LST) is essential for studying land–atmosphere energy exchange, the impact of climate change, and its influence on crop yields and hydrology. Although satellite remote sensing provides large-scale LST data, existing spatiotemporal fusion methods face challenges. Traditional algorithms have difficulty with heterogeneous surfaces, and deep-learning models often produce blurred details and inaccurate temperatures, which limits their use in high-precision applications. This study addresses these issues by developing a Deep-Learning Spatial and Temporal Fusion Model (DLSTFM) for Landsat-8 and MODIS LST imagery in Griffith, Australia. DLSTFM employs a dual-branch structure: one branch is dedicated to dual-temporal fusion, and the other branch is dedicated to multi-source feature fusion. Key innovations include the Spatial Adaptive Feature Modulation (SAFM) module, which performs adaptive multi-scale feature fusion, and the Temperature Adaptive Correction Module (TCM), which makes pixel-wise adjustments using reference data. Experiments demonstrate that DLSTFM significantly outperforms traditional methods and existing deep-learning fusion methods. DLSTFM achieves clearer surface features and a mean absolute temperature error of approximately 2.1 K. The model also demonstrated excellent generalization performance in another test area (Ardiethan) without retraining, showcasing its substantial practical value for high-accuracy LST fusion. Full article

Accurate detection of oil and gas (O&G) facilities in high-resolution remote sensing imagery is critical for infrastructure surveillance and sustainable resource management, yet conventional detectors struggle with severe class imbalance, extreme scale variation, and arbitrary orientation. In this work, we propose OGF Oriented R-CNN (Oil and Gas Facility Detection Oriented Region-based Convolutional Neural Network), an enhanced oriented detection model derived from Oriented R-CNN that integrates three improvements: (1) O&G Loss Function, (2) Class-Aware Hard Example Mining (CAHEM) module, and (3) Feature Pyramid Network with Feature Enhancement Attention (FPNFEA). Working in synergy, they resolve the coupled challenges more effectively than any standalone fix and do so without relying on rigid one-to-one matching between modules and individual issues. Evaluated on the O&G facility dataset comprising 3039 high-resolution images annotated with rotated bounding boxes across three classes (well sites: 3006, industrial and mining lands: 692, drilling: 244), OGF Oriented R-CNN achieves a mean average precision (mAP) of 82.9%, outperforming seven state-of-the-art (SOTA) models by margins of up to 27.6 percentage points (pp) and delivering a cumulative gain of +10.5 pp over Oriented R-CNN. Full article

High-resolution remote sensing images are gradually playing an important role in land cover mapping, urban planning, and environmental monitoring tasks. However, current segmentation approaches frequently encounter challenges such as loss of detail and blurred boundaries when processing high-resolution remote sensing imagery, owing to their complex backgrounds and dense semantic content. In response to the aforementioned limitations, this study introduces HMA-UNet, a novel segmentation network built upon the UNet framework and enhanced through a hybrid attention strategy. The architecture’s innovation centers on a composite attention block, where a lightweight split fusion attention (LSFA) mechanism and a lightweight channel-spatial attention (LCSA) mechanism are synergistically integrated within a residual learning structure to replace the stacked convolutional structure in UNet, which can improve the utilization of important shallow features and eliminate redundant information interference. Comprehensive experiments on the WHDLD dataset and the DeepGlobe road extraction dataset show that our proposed method achieves effective segmentation in remote sensing images by fully utilizing shallow features and eliminating redundant information interference. The quantitative evaluation results demonstrate the performance of the proposed method across two benchmark datasets. On the WHDLD dataset, the model attains a mean accuracy, IoU, precision, and recall of 72.40%, 60.71%, 75.46%, and 72.41%, respectively. Correspondingly, on the DeepGlobe road extraction dataset, it achieves a mean accuracy of 57.87%, an mIoU of 49.82%, a mean precision of 78.18%, and a mean recall of 57.87%. Full article

The Dead Sea (DS) region has experienced a sharp increase in sinkhole formation in recent years, posing environmental and infrastructure risks. The Geological Survey of Israel (GSI) employs Interferometric Synthetic Aperture Radar (InSAR) to monitor sinkhole activity and manually map land subsidence along the western shore of the DS. This process is both time-consuming and prone to human error. Automating detection with Deep Learning (DL) offers a transformative opportunity to enhance monitoring precision, scalability, and real-time decision-making. DL segmentation architectures such as UNet, Attention UNet, SAM, TransUNet, and SegFormer have shown effectiveness in learning geospatial deformation patterns in InSAR and related remote sensing data. This study provides a first comprehensive evaluation of a DL segmentation model applied to InSAR data for detecting land subsidence areas that occur as part of the sinkhole-formation process along the western shores of the DS. Unlike image-based tasks, our new model learns interferometric phase patterns that capture subtle ground deformations rather than direct visual features. As the ground truth in the supervised learning process, we use subsidence areas delineated on the phase maps by the GSI team over the years as part of the operational subsidence surveillance and monitoring activities. This unique data poses challenges for annotation, learning, and interpretability, making the dataset both non-trivial and valuable for advancing research in applied remote sensing and its application in the DS. We train the model across three partition schemes, each representing a different type and level of generalization, and introduce object-level metrics to assess its detection ability. Our results show that the model effectively identifies and generalizes subsidence areas in InSAR data across different setups and temporal conditions and shows promising potential for geographical generalization in previously unseen areas. Finally, large-scale subsidence trends are inferred by reconstructing smaller-scale patches and evaluated for different confidence thresholds. Full article

Hyperspectral image (HSI) classification is pivotal for remote sensing applications, including environmental monitoring, precision agriculture, and urban land-use analysis. However, its accuracy is often limited by scarce labeled data, class imbalance, and domain discrepancies between standard RGB and HSI imagery. Although recent deep learning approaches, such as 3D convolutional neural networks (3D-CNNs), transformers, and generative adversarial networks (GANs), show promise, they struggle with spectral fidelity, computational efficiency, and cross-domain adaptation in label-scarce scenarios. To address these challenges, we propose the Transformer–Graph Convolutional Network–Diffusion with Hybrid Domain Adaptation (TGDHTL) framework. This framework integrates domain-adaptive alignment of RGB and HSI data, efficient synthetic data generation, and multi-scale spectral–spatial modeling. Specifically, a lightweight transformer, guided by Maximum Mean Discrepancy (MMD) loss, aligns feature distributions across domains. A class-conditional diffusion model generates high-quality samples for underrepresented classes in only 15 inference steps, reducing labeled data needs by approximately 25% and computational costs by up to 80% compared to traditional 1000-step diffusion models. Additionally, a Multi-Scale Stripe Attention (MSSA) mechanism, combined with a Graph Convolutional Network (GCN), enhances pixel-level spatial coherence. Evaluated on six benchmark datasets including HJ-1A and WHU-OHS, TGDHTL consistently achieves high overall accuracy (e.g., 97.89% on University of Pavia) with just 11.9 GFLOPs, surpassing state-of-the-art methods. This framework provides a scalable, data-efficient solution for HSI classification under domain shifts and resource constraints. Full article

Building extraction underpins land-use assessment, urban planning, and disaster mitigation, yet dense urban scenes still cause missed small objects, target adhesion, and ragged contours. We present High-Resolution-Mamba (HR-Mamba), a high-resolution semantic segmentation network that augments a High-Resolution Network (HRNet) parallel backbone with edge-aware and sequence-state modeling. A Canny-enhanced, median-filtered stem stabilizes boundaries under noise; Involution-based residual blocks capture position-specific local geometry; and a Mamba-based State Space Models (Mamba-SSM) global branch captures cross-scale long-range dependencies with linear complexity. Training uses a composite loss of binary cross entropy (BCE), Dice loss, and Boundary loss, with weights selected by joint grid search. We further design a feature-driven adaptive post-processing pipeline that includes geometric feature analysis, multi-strategy simplification, multi-directional regularization, and topological consistency verification to produce regular, smooth, engineering-ready building outlines. On dense urban imagery, HR-Mamba improves F1-score from 80.95% to 83.93%, an absolute increase of 2.98% relative to HRNet. We conclude that HR-Mamba jointly enhances detail fidelity and global consistency and offers a generalizable route for high-resolution building extraction in remote sensing. Full article

Water body extraction plays a crucial role in remote sensing, supporting applications such as environmental monitoring and disaster prevention. Although Deep Convolutional Neural Networks (DCNNs) have achieved remarkable progress, their hierarchical architectures often introduce channel redundancy and hinder the joint representation of fine spatial structures and high-level semantics, leading to ineffective feature fusion and poor discrimination of water features. To address these limitations, a Parallel Attention Fusion Network (PAFNet) is proposed to achieve more effective multi-scale feature aggregation through parallel attention and adaptive fusion. First, the Feature Refinement Module (FRM) employs multi-branch asymmetric convolutions to extract multi-scale features, which are subsequently fused to suppress channel redundancy and preserve fine spatial details. Then, the Parallel Attention Module (PAM) applies spatial and channel attention in parallel, improving the discriminative representation of water features while mitigating interference from spectrally similar land covers. Finally, a Semantic Feature Fusion Module (SFM) integrates adjacent multi-level features through adaptive channel weighting, thereby achieving precise boundary recovery and robust noise suppression. Extensive experiments conducted on four representative datasets (GID, LandCover.ai, QTPL, and LoveDA) demonstrate the superiority of PAFNet over existing state-of-the-art methods. Specifically, the proposed model achieves 94.29% OA and 95.95% F1-Score on GID, 86.17% OA and 88.70% F1-Score on LandCover.ai, 98.99% OA and 98.96% F1-Score on QTPL, and 89.01% OA and 85.59% F1-Score on LoveDA. Full article

Remote sensing semantic segmentation holds significant application value in urban planning, environmental monitoring, and related fields. In recent years, multimodal approaches that fuse optical imagery with normalized Digital Surface Models (nDSM) have attracted widespread attention due to their superior performance. However, existing methods typically treat nDSM merely as an additional input channel, failing to effectively exploit its inherent 3D geometric priors, which limits segmentation accuracy in complex urban scenes. To address this issue, we propose a Geometry-aware Interactive Multi-Modal Network (GIMMNet), which explicitly models the geometric structure embedded in nDSM to guide the spatial distribution of semantic categories. Specifically, we first design a Geometric Position Prior Module (GPPM) to construct 3D coordinates for each pixel based on nDSM and extract intrinsic geometric priors. Next, a Geometry-Guided Disentangled Fusion Module (GDFM) dynamically adjusts fusion weights according to the differential responses of each modality to the geometric priors, enabling adaptive multimodal feature integration. Finally, during decoding, a Geometry-Attentive Context Module (GACM) explicitly captures the dependencies between land-cover categories and geometric structures, enhancing the model’s spatial awareness and semantic recovery capability. Experimental results on two public remote sensing datasets—Vaihingen and Potsdam—show that the proposed GIMMNet outperforms existing mainstream methods in segmentation performance, demonstrating that enhancing the model’s geometric perception capability effectively improves semantic segmentation accuracy. Notably, our method achieves an mIoU of 85.2% on the Potsdam dataset, surpassing the second-best multimodal approach, PACSCNet, by 2.3%. Full article

Heterogeneous remote sensing image change detection (Hete-CD) holds significant research value in military and civilian fields. The existing methods often rely on expert experience to design fixed deep network architectures for cross-modal feature alignment and fusion purposes. However, when faced with diverse land cover types, these methods often lead to blurred change boundaries and structural distortions, resulting in significant performance degradations. To address this, we propose an adaptive adversarial learning-based heterogeneous remote sensing image change detection method based on the differentiable filter combination search (DFCS) strategy to provide enhanced generalizability and dynamic learning capabilities for diverse scenarios. First, a fully reconfigurable self-learning discriminator is designed to dynamically synthesize the optimal convolutional architecture from a library of atomic filters containing basic operators. This provides highly adaptive adversarial supervision to the generator, enabling joint dynamic learning between the generator and discriminator. To further mitigate modality differences in the input stage, we integrate a feature fusion module based on the Gabor and local normalized cross-correlation (G-LNCC) to extract modality-invariant texture and structure features. Finally, a geometric structure-based collaborative supervision (GSCS) loss function is constructed to impose fine-grained constraints on the change map from the perspectives of regions, boundaries, and structures, thereby enforcing physical properties. Comparative experimental results obtained on five public Hete-CD datasets show that our method achieves the best F1 values and overall accuracy levels, especially on the Gloucester I and Gloucester II datasets, achieving F1 scores of 93.7% and 95.0%, respectively, demonstrating the strong generalizability of our method in complex scenarios. Full article

Fine-grained building function identification (BFI) is essential for sustainable urban development, land-use analysis, and data-driven spatial planning. Recent progress in fully supervised semantic segmentation has advanced multimodal BFI; however, most approaches still rely on static fusion and lack explicit multi-scale alignment. As a result, they struggle to adaptively integrate heterogeneous inputs and suppress cross-modal interference, which constrains representation learning. To overcome these limitations, we propose BuildFunc-MoE, an adaptive multimodal Mixture-of-Experts (MoE) network built on an effective end-to-end Swin-UNet backbone. The model treats high-resolution remote sensing imagery as the primary input and integrates auxiliary geospatial data such as nighttime light imagery, DEM, and point-of-interest information. An Adaptive Multimodal Fusion Gate (AMMFG) first refines auxiliary features into informative fused representations, which are then combined with the primary modality and passed through multi-scale Swin-MoE blocks that extend standard Swin Transformer blocks with MoE routing. This enables fine-grained, dynamic fusion and alignment between primary and auxiliary modalities across feature scales. BuildFunc-MoE further introduces a Shared Task-Expert Module (STEM), which extends the MoE framework to share experts between the main BFI task and auxiliary tasks (road extraction, green space segmentation, and water body detection), enabling parameter-level transfer. This design enables complementary feature learning, where structural and contextual information jointly enhance the discrimination of building functions, thereby improving identification accuracy while maintaining model compactness. Experiments on the proposed Wuhan-BF multimodal dataset show that, under identical supervision, BuildFunc-MoE outperforms the strongest multimodal baseline by over 2% on average across metrics. Both PyTorch and LuoJiaNET implementations validate its effectiveness, while the latter achieves higher accuracy and faster inference through optimized computation. Overall, BuildFunc-MoE offers a scalable solution for fine-grained BFI with strong potential for urban planning and sustainable governance. Full article

Terrace construction is a critical engineering practice for soil and water conservation as well as sustainable agricultural development on the Loess Plateau (LP), China, where high-precision dynamic monitoring is essential for informed regional ecological governance. To address the challenges of inadequate extraction accuracy and poor model generalization in time-series terrace mapping amid complex terrain and spectral confounding, this study proposes a novel Swin Transformer-based Terrace Dual-Branch Deformable Boundary Network (STDBNet) that seamlessly integrates multi-source remote sensing (RS) data with deep learning (DL). The STDBNet model integrates the Swin Transformer architecture with a dual-branch attention mechanism and introduces a boundary-assisted supervision strategy, thereby significantly enhancing terrace boundary recognition, multi-source feature fusion, and model generalization capability. Leveraging Sentinel-2 multi-temporal optical imagery and terrain-derived features, we constructed the first 10-m-resolution spatiotemporal dataset of terrace distribution across the LP, encompassing nine annual periods from 2017 to 2025. Performance evaluations demonstrate that STDBNet achieved an overall accuracy (OA) of 95.26% and a mean intersection over union (MIoU) of 86.84%, outperforming mainstream semantic segmentation models including U-Net and DeepLabV3+ by a significant margin. Further analysis reveals the spatiotemporal evolution dynamics of terraces over the nine-year period and their distribution patterns across gradients of key terrain factors. This study not only provides robust data support for research on terraced ecosystem processes and assessments of soil and water conservation efficacy on the LP but also lays a scientific foundation for informing the formulation of regional ecological restoration and land management policies. Full article

Urban scene classification in high-resolution remote sensing images is critical for applications such as power facility site selection and grid security monitoring. However, the complexity and variability of ground objects present significant challenges to accurate classification. While convolutional neural networks (CNNs) excel at extracting local features, they often struggle to model long-range dependencies. Transformers can capture global context but incur high computational costs. To address these limitations, this paper proposes a Global–Local Information Fusion Network (GLIFNet), which integrates VMamba for efficient global modeling with CNN for local detail extraction, enabling more effective fusion of fine-grained and semantic information. Furthermore, a Haar Wavelet Transform Attention Mechanism (HWTAM) is designed to explicitly exploit frequency-domain characteristics, facilitating refined fusion of multi-scale features. The experiment compared nine commonly used or most advanced methods. The results show that GLIFNet achieves mean F1 scores (mF1) of 90.08% and 87.44% on the ISPRS Potsdam and ISPRS Vaihingen datasets, respectively. This represents improvements of 1.26% and 1.91%, respectively, compared to the compared model. The overall accuracy (OA) reaches 90.43% and 92.87%, with respective gains of 2.28% and 1.58%. Experimental results on the LandCover.ai dataset demonstrate that GLIFNet achieved an mF1 score of 88.39% and an accuracy of 92.23%, exhibiting relative improvements of 0.3% and 0.28% compared with the control model. In summary, GLIFNet demonstrates advanced performance in urban scene classification from high-resolution remote sensing images and can provide accurate basic data for power construction. Full article

Landslide disasters are complex spatiotemporal phenomena. Existing deep learning (DL) models for remote sensing (RS) image analysis primarily exploit shallow visual features, inadequately incorporating critical geological, geographical, and environmental knowledge. This limitation impairs detection accuracy and generalization, especially in complex terrains and diverse vegetation conditions. We propose Knowledge Graph Embedding in Swin Feature Pyramid Networks (KGE–SwinFpn), a novel RS landslide segmentation framework that integrates explicit domain knowledge with deep features. First, a comprehensive landslide knowledge graph is constructed, organizing multi-source factors (e.g., lithology, topography, hydrology, rainfall, land cover, etc.) into entities and relations that characterize controlling, inducing, and indicative patterns. A dedicated KGE Block learns embeddings for these entities and discretized factor levels from the landslide knowledge graph, enabling their fusion with multi-scale RS features in SwinFpn. This approach preserves the efficiency of automatic feature learning while embedding prior knowledge guidance, enhancing data–knowledge–model coupling. Experiments demonstrate significant outperformance over classic segmentation networks: on the Yuan-yang dataset, KGE–SwinFpn achieved 96.85% pixel accuracy (PA), 88.46% mean pixel accuracy (MPA), and 82.01% mean intersection over union (MIoU); on the Bijie dataset, it attained 96.28% PA, 90.72% MPA, and 84.47% MIoU. Ablation studies confirm the complementary roles of different knowledge features and the KGE Block’s contribution to robustness in complex terrains. Notably, the KGE Block is architecture-agnostic, suggesting broad applicability for knowledge-guided RS landslide detection and promising enhanced technical support for disaster monitoring and risk assessment. Full article

Harvest-disrupting rain events (HDREs) are prolonged cloudy–rainy spells during winter wheat maturity that impede harvesting and drying, induce pre-harvest sprouting and grain mould, and threaten food security in the Huang–Huai–Hai Plain (HHHP), China’s core winter wheat region. Using daily meteorological records (1960–2019), remote sensing-derived land-use data and topography, we develop a hazard–exposure–vulnerability framework to quantify HDRE risk and its drivers at 1 km resolution. Results show that HDRE risk has increased markedly over the past six decades, with the area of medium-to-high risk rising from 26.9% to 73.1%. The spatial pattern evolved from a “high-south–low-north” structure to a concentrated high-risk belt in the central–northern HHHP, and the risk centroid migrated from Fuyang (Anhui) to Heze (Shandong), with an overall displacement of 124.57 km toward the north–northwest. GeoDetector analysis reveals a shift from a “humidity–temperature dominated” mechanism to a “sunshine–humidity–precipitation co-driven” mechanism; sunshine duration remains the leading factor (q > 0.8), and its interaction with relative humidity shows strong nonlinear enhancement (q = 0.91). High-risk hot spots coincide with low-lying plains and river valleys with dense winter wheat planting, indicating the joint amplification of meteorological conditions and underlying surface features. The results can support regional decision-making for harvest-season early warning, risk zoning, and disaster risk reduction in the HHHP. Full article