Search Results (165)

High-resolution remote sensing imagery plays an essential role in urban management and environmental monitoring, providing detailed insights for applications ranging from land cover mapping to disaster response. Semantic segmentation methods are among the most effective techniques for comprehensive land cover mapping, and they commonly employ ImageNet-based pre-training semantics. However, traditional fine-tuning processes exhibit poor transferability across different downstream tasks and require large amounts of labeled data. To address these challenges, we introduce Denoising Diffusion Probabilistic Models (DDPMs) as a generative pre-training approach for semantic features extraction in remote sensing imagery. We pre-trained a DDPM on extensive unlabeled imagery, obtaining features at multiple noise levels and resolutions. In order to integrate and optimize these features efficiently, we designed a multi-layer perceptron module with residual connections. It performs channel-wise optimization to suppress feature redundancy and refine representations. Additionally, we froze the feature extractor during fine-tuning. This strategy significantly reduces computational consumption and facilitates fast transfer and deployment across various interpretation tasks on homogeneous imagery. Our comprehensive evaluation on the sparsely labeled dataset MiniFrance-S and the fully labeled Gaofen Image Dataset achieved mean intersection over union scores of 42.7% and 66.5%, respectively, outperforming previous works. This demonstrates that our approach effectively reduces reliance on labeled imagery and increases transferability to downstream remote sensing tasks. Full article

Erosion gullies can reduce arable land area and decrease agricultural machinery efficiency; therefore, automatic gully extraction on a regional scale should be one of the preconditions of gully control and land management. The purpose of this study is to compare the effects of the grey level co-occurrence matrix (GLCM) and topographic–hydrologic features on automatic gully extraction and guide future practices in adjacent regions. To accomplish this, GaoFen-2 (GF-2) satellite imagery and high-resolution digital elevation model (DEM) data were first collected. The GLCM and topographic–hydrologic features were generated, and then, a gully label dataset was built via visual interpretation. Second, the study area was divided into training, testing, and validation areas, and four practices using different feature combinations were conducted. The DeepLabV3+ and ResNet50 architectures were applied to train five models in each practice. Thirdly, the trainset gully intersection over union (IOU), test set gully IOU, receiver operating characteristic curve (ROC), area under the curve (AUC), user’s accuracy, producer’s accuracy, Kappa coefficient, and gully IOU in the validation area were used to assess the performance of the models in each practice. The results show that the validated gully IOU was 0.4299 (±0.0082) when only the red (R), green (G), blue (B), and near-infrared (NIR) bands were applied, and solely combining the topographic–hydrologic features with the RGB and NIR bands significantly improved the performance of the models, which boosted the validated gully IOU to 0.4796 (±0.0146). Nevertheless, solely combining GLCM features with RGB and NIR bands decreased the accuracy, which resulted in the lowest validated gully IOU of 0.3755 (±0.0229). Finally, by employing the full set of RGB and NIR bands, the GLCM and topographic–hydrologic features obtained a validated gully IOU of 0.4762 (±0.0163) and tended to show an equivalent improvement with the combination of topographic–hydrologic features and RGB and NIR bands. A preliminary explanation is that the GLCM captures the local textures of gullies and their backgrounds, and thus introduces ambiguity and noise into the convolutional neural network (CNN). Therefore, the GLCM tends to provide no benefit to automatic gully extraction with CNN-type algorithms, while topographic–hydrologic features, which are also original drivers of gullies, help determine the possible presence of water-origin gullies when optical bands fail to tell the difference between a gully and its confusing background. Full article

Land desertification represents a significant and sensitive global ecological issue. In the Inner Mongolia region of China, soil desertification and salinization are widespread, resulting from the combined effects of extreme drought conditions and human activities. Using Gaofen 5B AHSI imagery as our data source, we collected spectral data for seven distinct land cover types: lush vegetation, yellow sand, white sand, saline soil, saline shell, saline soil with saline vegetation, and sandy soil. We applied Particle Swarm Optimization (PSO) to fine-tune the Wavelet Packet (WP) decomposition levels, thresholds, and wavelet basis function, ensuring optimal spectral decomposition and reconstruction. Subsequently, PSO was deployed to optimize key hyperparameters of the Random Forest algorithm and compare its performance with the ResNet-Transformer model. Our results indicate that PSO effectively automates the search for optimal WP decomposition parameters, preserving essential spectral information while efficiently reducing high-frequency spectral noise. The Genetic Algorithm (GA) was also found to be effective in extracting feature bands relevant to land desertification, which enhances the classification accuracy of the model. Among all the models, integrating wavelet packet denoising, genetic algorithm feature selection, the first-order differential (FD), and the hybrid architecture of the ResNet-Transformer, the WP-GA-FD-ResNet-Transformer model achieved the highest accuracy in extracting soil sandification and salinization, with Kappa coefficients and validation set accuracies of 0.9746 and 97.82%, respectively. This study contributes to the field by advancing hyperspectral desertification monitoring techniques and suggests that the approach could be valuable for broader ecological conservation and land management efforts. Full article

Ningxia has emerged as a strategic hub for China’s photovoltaic (PV) industry by leveraging abundant solar energy resources and geoclimatic advantages. This study analyzed the spatiotemporal expansion trends and microclimatic impacts of PV installations (2015–2024) using Gaofen-1 (GF-1) and Landsat8 satellite imagery with deep learning algorithms and multidimensional environmental metrics. Among semantic segmentation models, DeepLabV3+ had the best performance in PV extraction, and the Mean Intersection over Union, precision, and F1-score were 91.97%, 89.02%, 89.2%, and 89.11%, respectively, with accuracies close to 100% after manual correction. Subsequent land surface temperature inversion and spatial buffer analysis quantified the thermal environmental effects of PV installation. Localized cooling patterns may be influenced by albedo and vegetation dynamics, though further validation is needed. The total PV site area in Ningxia expanded from 59.62 km² to 410.06 km² between 2015 and 2024. Yinchuan and Wuzhong cities were primary growth hubs; Yinchuan alone added 99.98 km² (2022–2023) through localized policy incentives. PV installations induced significant daytime cooling effects within 0–100 m buffers, reducing ambient temperatures by 0.19–1.35 °C on average. The most pronounced cooling occurred in western desert regions during winter (maximum temperature differential = 1.97 °C). Agricultural zones in central Ningxia exhibited weaker thermal modulation due to coupled vegetation–PV interactions. Policy-driven land use optimization was the dominant catalyst for PV proliferation. This study validates “remote sensing + deep learning” framework efficacy in renewable energy monitoring and provides empirical insights into eco-environmental impacts under “PV + ecological restoration” paradigms, offering critical data support for energy–ecology synergy planning in arid regions. Full article

In January 2025, a magnitude 6.8 earthquake struck Dingri County, Shigatse, Tibet, causing severe damage. Rapid and precise extraction of damaged buildings is essential for emergency relief and rebuilding efforts. This study proposes an approach integrating YOLO-E (Real-Time Seeing Anything) and the Segment Anything Model 2 (SAM2) to extract damaged buildings with multi-source remote sensing images, including post-earthquake Gaofen-7 imagery (0.80 m), Beijing-3 imagery (0.30 m), and pre-earthquake Google satellite imagery (0.15 m), over the affected region. In this hybrid approach, YOLO-E functions as the preliminary segmentation module for initial segmentation. It leverages its real-time detection and segmentation capability to locate potential damaged building regions and generate coarse segmentation masks rapidly. Subsequently, SAM2 follows as a refinement step, incorporating shapefile information from pre-disaster sources to apply precise, pixel-level segmentation. The dataset used for training contained labeled examples of damaged buildings, and the model optimization was carried out using stochastic gradient descent (SGD), with cross-entropy and mean squared error as the selected loss functions. Upon evaluation, the model reached a precision of 0.840, a recall of 0.855, an F1-score of 0.847, and an IoU of 0.735. It successfully extracted 492 suspected damaged building patches within a radius of 20 km from the earthquake epicenter, clearly showing the distribution characteristics of damaged buildings concentrated in the earthquake fault zone. In summary, this hybrid YOLO-E and SAM2 approach, leveraging multi-source remote sensing imagery, delivers precise and rapid extraction of damaged buildings with a precision of 0.840, recall of 0.855, and IoU of 0.735, effectively supporting targeted earthquake rescue and post-disaster reconstruction efforts in the Dingri County fault zone. Full article

Debris flows pose significant risks to mountainous regions, and quick, accurate volume estimation is crucial for hazard assessment and post-disaster response. Traditional volume estimation methods, such as ground surveys and aerial photogrammetry, are often limited by cost, accessibility, and timeliness. While remote sensing offers wide coverage, existing optical and Synthetic Aperture Radar (SAR)-based techniques face challenges in direct volume estimation due to resolution constraints and rapid terrain changes. This study proposes a Super-Resolution Shape from Shading (SRSFS) approach enhanced by a Non-local Piecewise-smooth albedo Constraint (NPC), hereafter referred to as NPC SRSFS, to estimate debris-flow erosion volume using single high-resolution optical satellite imagery. By integrating publicly available global Digital Elevation Model (DEM) data as prior terrain reference, the method enables accurate post-disaster topography reconstruction from a single optical image, thereby reducing reliance on stereo imagery. The NPC constraint improves the robustness of albedo estimation under heterogeneous surface conditions, enhancing depth recovery accuracy. The methodology is evaluated using Gaofen-6 satellite imagery, with quantitative comparisons to aerial Light Detection and Ranging (LiDAR) data. Results show that the proposed method achieves reliable terrain reconstruction and erosion volume estimates, with accuracy comparable to airborne LiDAR. This study demonstrates the potential of NPC SRSFS as a rapid, cost-effective alternative for post-disaster debris-flow assessment. Full article

The Xixia Imperial Tombs (XITs) represent a crucial, yet still largely mysterious, component of the Tangut civilization’s legacy. Located in northwestern China, this extensive necropolis offers invaluable insights into the Tangut state, culture, and burial practices. This study employs an integrated approach utilizing multi-resolution and multi-temporal satellite remote sensing data, including Gaofen-2 (GF-2), Landsat-8 OLI, declassified GAMBIT imagery, and Google Earth, combined with deep learning techniques, to conduct a comprehensive archaeological investigation of the XITs’ burial landscape. We performed geomorphological analysis of the surrounding environment and automated identification and mapping of burial mounds and mausoleum features using YOLOv5, complemented by manual interpretation of very-high-resolution (VHR) satellite imagery. Spectral indices and image fusion techniques were applied to enhance the detection of archaeological features. Our findings demonstrated the efficacy of this combined methodology for archaeology prospect, providing valuable insights into the spatial layout, geomantic considerations, and preservation status of the XITs. Notably, the analysis of declassified GAMBIT imagery facilitated the identification of a suspected true location for the ninth imperial tomb (M9), a significant contribution to understanding Xixia history through remote sensing archaeology. This research provides a replicable framework for the detection and preservation of archaeological sites using readily available satellite data, underscoring the power of advanced remote sensing and machine learning in heritage studies. Full article

This study investigates the influence of root cohesion spatial heterogeneity on rainfall-induced landslide distribution across the Loess Plateau, addressing limitations in existing methods that oversimplify root reinforcement. Leveraging Landsat and GaoFen satellite images, we developed a regional root cohesion inversion model that quantifies spatial heterogeneity using tree height (derived from time series Landsat imagery) and above-ground biomass (from 30 m resolution satellite products). This approach, integrated with land use-specific hydrological parameters and an infinite slope stability model, significantly improves landslide susceptibility predictions compared to models ignoring root cohesion or using uniform assignments. High-resolution pre- and post-rainfall GaoFen satellite imagery validated landslide inventories, revealing dynamic susceptibility patterns: farmland exhibited the highest risk, followed by artificial and secondary forests, with susceptibility escalating post-rainfall. This study underscores the critical role of remote sensing-driven root cohesion mapping in landslide risk assessment, offering actionable insights for land use planning and disaster mitigation on the Loess Plateau. Full article

Pine wilt disease has caused severe damage to China’s forest ecosystems. Utilizing the rich information from very-high-resolution (VHR) satellite imagery for large-scale and accurate monitoring of pine wilt disease is a crucial approach to curbing its spread. However, current research on identifying infected trees using VHR satellite imagery and deep learning remains extremely limited. This study introduces several advanced self-attention algorithms into the task of satellite-based monitoring of pine wilt disease to enhance detection performance. We constructed a dataset of discolored pine trees affected by pine wilt disease using imagery from the Gaofen-2 and Gaofen-7 satellites. Within the unified semantic segmentation framework MMSegmentation, we implemented four single-head attention models—NLNet, CCNet, DANet, and GCNet—and two multi-head attention models—Swin Transformer and SegFormer—for the accurate semantic segmentation of infected trees. The model predictions were further analyzed through visualization. The results demonstrate that introducing appropriate self-attention algorithms significantly improves detection accuracy for pine wilt disease. Among the single-head attention models, DANet achieved the highest accuracy, reaching 73.35%. The multi-head attention models exhibited an excellent performance, with SegFormer-b2 achieving an accuracy of 76.39%, learning the features of discolored pine trees at the earliest stage and converging faster. The visualization of model inference results indicates that DANet, which integrates convolutional neural networks (CNNs) with self-attention mechanisms, achieved the highest overall accuracy at 94.43%. The use of self-attention algorithms enables models to extract more precise morphological features of discolored pine trees, enhancing user accuracy while potentially reducing production accuracy. Full article

Prompt and precise cropland mapping is indispensable for safeguarding food security, enhancing land resource utilization, and advancing sustainable agricultural practices. Conventional approaches faced difficulties in complex terrain marked by fragmented plots, pronounced elevation differences, and non-uniform field borders. To address these challenges, we propose DAENet, a novel deep learning framework designed for accurate cropland extraction from high-resolution GaoFen-1 (GF-1) satellite imagery. DAENet employs a novel Geometric-Optimized and Boundary-Restrained (GOBR) Block, which combines channel attention, multi-scale spatial attention, and boundary supervision mechanisms to effectively mitigate challenges arising from disjointed cropland parcels, topography-cast shadows, and indistinct edges. We conducted comparative experiments using 8 mainstream semantic segmentation models. The results demonstrate that DAENet achieves superior performance, with an Intersection over Union (IoU) of 0.9636, representing a 4% improvement over the best-performing baseline, and an F1-score of 0.9811, marking a 2% increase. Ablation analysis further validated the indispensable contribution of GOBR modules in improving segmentation precision. Using our approach, we successfully extracted 25,556.98 hectares of cropland within the study area, encompassing a total of 67,850 individual blocks. Additionally, the proposed method exhibits robust generalization across varying spatial resolutions, underscoring its effectiveness as a high-accuracy solution for agricultural monitoring and sustainable land management in complex terrain. Full article

The accurate identification of water bodies in hyperspectral images (HSIs) remains challenging due to hierarchical representation imbalances in deep learning models, where shallow layers overly focus on spectral features, boundary ambiguities caused by the relatively low spatial resolution of satellite imagery, and limited detection capability for small-scale aquatic features such as narrow rivers. To address these challenges, this study proposes Heuristic–Adaptive Spectral–Spatial Neural Architecture Search with Dynamic Cell Evaluation (HASSDE-NAS). The architecture integrates three specialized units; a spectral-aware dynamic band selection cell suppresses redundant spectral bands, while a geometry-enhanced edge attention cell refines fragmented spatial boundaries. Additionally, a bidirectional fusion alignment cell jointly optimizes spectral and spatial dependencies. A heuristic cell search algorithm optimizes the network architecture through architecture stability, feature diversity, and gradient sensitivity analysis, which improves search efficiency and model robustness. Evaluated on the Gaofen-5 datasets from the Guangdong and Henan regions, HASSDE-NAS achieves overall accuracies of 92.61% and 96%, respectively. This approach outperforms existing methods in delineating narrow river systems and resolving water bodies with weak spectral contrast under complex backgrounds, such as vegetation or cloud shadows. By adaptively prioritizing task-relevant features, the framework provides an interpretable solution for hydrological monitoring and advances neural architecture search in intelligent remote sensing. Full article

To address the issues of high computational complexity and boundary feature loss encountered when extracting farmland information from high-resolution remote sensing images, this study proposes an innovative CNN–Transformer hybrid network, MAMNet. This framework integrates a lightweight encoder, a global–local Transformer decoder, and a bidirectional attention architecture to achieve efficient and accurate farmland information extraction. First, we reconstruct the ResNet-18 backbone network using deep separable convolutions, reducing computational complexity while preserving feature representation capabilities. Second, the global–local Transformer block (GLTB) decoder uses multi-head self-attention mechanisms to dynamically fuse multi-scale features across layers, effectively restoring the topological structure of fragmented farmland boundaries. Third, we propose a novel bidirectional attention architecture: the Detail Improvement Module (DIM) uses channel attention to transfer semantic features to geometric features. The Context Enhancement Module (CEM) utilizes spatial attention to achieve dynamic geometric–semantic fusion, quantitatively distinguishing farmland textures from mixed ground cover. The positional attention mechanism (PAM) enhances the continuity of linear features by strengthening spatial correlations in jump connections. By cascading front-end feature module (FEM) to expand the receptive field and combining an adaptive feature reconstruction head (FRH), this method improves information integrity in fragmented areas. Evaluation results on the 2022 high-resolution two-channel image dataset from Chenggong District, Kunming City, demonstrate that MAMNet achieves an mIoU of 86.68% (an improvement of 1.66% and 2.44% over UNetFormer and BANet, respectively) and an F1-Score of 92.86% with only 12 million parameters. This method provides new technical insights for plot-level farmland monitoring in precision agriculture. Full article

The wildland–urban interface (WUI) has been a global phenomenon, yet parameter threshold determination remains a persistent challenge in this field. In China, a significant research gap exists in the development of WUI mapping methodology. This study proposes a novel mapping approach that delineates the WUI by integrating both vegetation and building environment perspectives. GaoFen 1 Panchromatic Multi-spectral Sensor (GF1-PMS) imagery was leveraged as the data source. Building location was extracted using object-oriented and hierarchical classification techniques, and the pixel dichotomy method was employed to estimate fractional vegetation coverage (FVC). Building location and FVC were used as input for the WUI mapping. In this methodology, the threshold of FVC was determined by incorporating the remote sensing characteristics of the WUI types, whereas the buffer range of vegetation was refined through sensitivity analysis. The proposed method demonstrated high applicability in Anning City, achieving an overall accuracy of 88.56%. The total WUI area amounted to 49,578.05 ha, accounting for 38.08% of Anning City’s entire area. Spatially, the intermix WUI was predominantly distributed in the Taiping sub-district of Anning City, while the interface WUI was mainly concentrated in the Bajie sub-district of Anning City. MODIS fire spots from 2003 to 2022 were primarily clustered in the Qinglong sub-district, Wenquan sub-district, and Caopu sub-district of Anning City. Our findings indicated a spatial overlap between the WUI and fire-prone areas in Anning City. This study presents an effective methodology for threshold determination and WUI mapping, making up for the scarcity of mapping methodologies in China. Moreover, our approach offers valuable insights for a wise decision in fire risk. Full article

Cloud detection in satellite imagery plays a pivotal role in achieving high-accuracy retrieval of biophysical parameters and subsequent remote sensing applications. Although numerous methods have been developed and operationally deployed, their accuracy over challenging surfaces—such as snow-covered mountains, saline–alkali lands in deserts or Gobi regions, and snow-covered surfaces—remains limited. Additionally, the efficiency of collecting training samples for prevalent deep learning-based methods heavily relies on large-scale pixel-level annotations, which are both time-consuming and labor-intensive. To address these challenges, we propose a Texture-Enhanced Network that integrates an object-oriented dynamic threshold pseudo-labeling method and a texture-feature-enhanced attention module to enhance both the efficiency of deep learning methods and detection accuracy over challenging surfaces. First, an object-oriented dynamic threshold pseudo-labeling approach is developed by leveraging object-oriented principles and adaptive thresholding techniques, enabling the efficient collection of large-scale labeled samples for challenging surfaces. Second, to exploit the spatial continuity of clouds, cross-channel correlations, and their distinctive texture features, a texture-feature-enhanced attention module is designed to improve feature discrimination for challenging positive and negative samples. Extensive experiments on a Chinese GaoFen satellite imagery dataset demonstrate that the proposed method achieves state-of-the-art performance. Full article

Volume of change provides a comprehensive and objective reflection of land surface transformation, meeting the emerging demand for feature change monitoring in the era of big data. However, existing land surface monitoring methods often focus on a single dimension, either horizontal or vertical, making it challenging to achieve quantitative volumetric change monitoring. Accurate volumetric change measurements are indispensable in many fields, such as monitoring open-pit coal mines. Therefore, the main content and conclusions of this paper are as follows: (1) A method for Automatic Control Points Extraction from ICESat-2/ATL08 products was developed, integrating Land cover types and Phenological information (ACPELP), achieving a mean absolute error (MAE) of 1.05 m in the horizontal direction and 1.99 m in the vertical direction for stereo change measurements. This method helps correct image positioning errors, enabling the acquisition of geospatially aligned GaoFen-7 (GF-7) imagery. (2) A function-based classification system for open-pit coal mines was established, enabling precise extraction of stereoscopic change region to support accurate volumetric calculations. (3) A method for calculating the mining and stripping volume of open-pit coal mines based on GF-7 imagery is proposed. The method utilizes photogrammetry to extract elevation features and combines spectral features with elevation data to estimate stripping volumes, achieving an excellent error rate (ER) of 0.26%. The results indicate that our method is cost-effective and highly practical, filling the gap in accurate and comprehensive monitoring of land surface changes. Full article