Pub Date : 2026-01-12DOI: 10.1109/JSTARS.2026.3651639
Yang Liu;Kun Zhang;Chun-Yi Song;Zhi-Wei Xu
In high-resolution maritime radar working in scanning mode, the classification and identification of ships require the recovery of the ship’s high-resolution range profiles (HRRPs) from radar returns. The return signal from the ship is a complex sparse signal interfered by non-Gaussian sea clutter. In this article, three sparse optimization methods matching the non-Gaussian characteristics of sea clutter, i.e., the sparse optimization matching K-distribution method, the sparse optimization matching generalized Pareto distribution method, the sparse optimization matching CGIG distribution method, are proposed to estimate complex HRRPs of ships. The compound Gaussian model is used to describe the non-Gaussianity of sea clutter, and the sparsity of ships’ complex HRRPs is constrained by the random distribution with one parameter. In the three methods, the Anderson–Darling test is used to search the parameters of the sparse constraint model. Besides, the non-Gaussian characteristics of sea clutter depend on the marine environment parameters and radar operating parameters. For different scenarios, the minimal criterion of the Kolmogorov–Smirnov distance is used to select the best model from the three compound Gaussian models, and then select the corresponding proposed methods. Simulated and measured radar data are used to evaluate the performance of the proposed methods and the results show that the proposed methods obtain better estimates of ship HRRPs compared to the recent SRIM method and the classical SLIM method.
{"title":"Estimation of Ships’ Complex High-Resolution Range Profiles Based on Sparse Optimization Method in Non-Gaussian Sea Clutter","authors":"Yang Liu;Kun Zhang;Chun-Yi Song;Zhi-Wei Xu","doi":"10.1109/JSTARS.2026.3651639","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3651639","url":null,"abstract":"In high-resolution maritime radar working in scanning mode, the classification and identification of ships require the recovery of the ship’s high-resolution range profiles (HRRPs) from radar returns. The return signal from the ship is a complex sparse signal interfered by non-Gaussian sea clutter. In this article, three sparse optimization methods matching the non-Gaussian characteristics of sea clutter, i.e., the sparse optimization matching K-distribution method, the sparse optimization matching generalized Pareto distribution method, the sparse optimization matching CGIG distribution method, are proposed to estimate complex HRRPs of ships. The compound Gaussian model is used to describe the non-Gaussianity of sea clutter, and the sparsity of ships’ complex HRRPs is constrained by the random distribution with one parameter. In the three methods, the Anderson–Darling test is used to search the parameters of the sparse constraint model. Besides, the non-Gaussian characteristics of sea clutter depend on the marine environment parameters and radar operating parameters. For different scenarios, the minimal criterion of the Kolmogorov–Smirnov distance is used to select the best model from the three compound Gaussian models, and then select the corresponding proposed methods. Simulated and measured radar data are used to evaluate the performance of the proposed methods and the results show that the proposed methods obtain better estimates of ship HRRPs compared to the recent SRIM method and the classical SLIM method.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"3998-4013"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11339885","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-12DOI: 10.1109/JSTARS.2026.3652404
Ali Caglayan;Nevrez Imamoglu;Toru Kouyama
Self-supervised pretraining has emerged as a powerful approach for learning transferable representations from large-scale unlabeled data, significantly reducing reliance on task-specific labeled datasets. Although masked autoencoders (MAEs) have shown considerable success in optical remote sensing, such as RGB and multispectral imagery, their application to synthetic aperture radar (SAR) data remains underexplored due to their unique imaging characteristics, including speckle content and intensity variability. In this work, we investigate the effectiveness of MAEs for SAR pretraining, specifically applying MixMAE [Liu, et al.,(2023)] to Sentinel-1 SAR imagery. We introduce SAR-W-MixMAE, a domain-aware self-supervised learning approach that incorporates an SAR-specific pixelwise weighting strategy into the reconstruction loss, mitigating the effects of speckle content and high-intensity backscatter variations. Experimental results demonstrate that SAR-W-MixMAE consistently improves baseline models in multilabel SAR image classification and flood detection tasks, extending the state-of-the-art performance on the popular BigEarthNet dataset. Extensive ablation studies reveal that pretraining duration and fine-tuning dataset size significantly impact downstream performance. In particular, early stopping during pretraining can yield optimal downstream task accuracy, challenging the assumption that prolonged pretraining enhances results. These insights contribute to the development of foundation models tailored for SAR imagery and provide practical guidelines for optimizing pretraining strategies in remote sensing applications.
自监督预训练已经成为一种从大规模未标记数据中学习可转移表征的强大方法，显著减少了对特定任务标记数据集的依赖。尽管掩膜自动编码器（MAEs）在光学遥感（如RGB和多光谱成像）中取得了相当大的成功，但由于其独特的成像特性（包括散斑含量和强度可变性），它们在合成孔径雷达（SAR）数据中的应用仍未得到充分探索。在这项工作中，我们研究了MAEs在SAR预训练中的有效性，特别是将MixMAE [Liu， et .,(2023)]应用于Sentinel-1 SAR图像。我们引入了SAR-W-MixMAE，这是一种领域感知的自监督学习方法，它将sar特定的像素加权策略纳入重建损失，减轻了散斑内容和高强度后向散射变化的影响。实验结果表明，SAR- w - mixmae在多标签SAR图像分类和洪水检测任务中不断改进基线模型，扩展了流行的BigEarthNet数据集的最先进性能。广泛的消融研究表明，预训练时间和微调数据集大小显著影响下游性能。特别是，在预训练期间提前停止可以产生最佳的下游任务准确性，挑战了延长预训练可以提高结果的假设。这些见解有助于开发适合SAR图像的基础模型，并为优化遥感应用中的预训练策略提供实用指南。
{"title":"SAR-W-MixMAE: Polarization-Aware Self-Supervised Pretraining for Masked Autoencoders on SAR Data","authors":"Ali Caglayan;Nevrez Imamoglu;Toru Kouyama","doi":"10.1109/JSTARS.2026.3652404","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3652404","url":null,"abstract":"Self-supervised pretraining has emerged as a powerful approach for learning transferable representations from large-scale unlabeled data, significantly reducing reliance on task-specific labeled datasets. Although masked autoencoders (MAEs) have shown considerable success in optical remote sensing, such as RGB and multispectral imagery, their application to synthetic aperture radar (SAR) data remains underexplored due to their unique imaging characteristics, including speckle content and intensity variability. In this work, we investigate the effectiveness of MAEs for SAR pretraining, specifically applying MixMAE [Liu, et al.,(2023)] to Sentinel-1 SAR imagery. We introduce SAR-W-MixMAE, a domain-aware self-supervised learning approach that incorporates an SAR-specific pixelwise weighting strategy into the reconstruction loss, mitigating the effects of speckle content and high-intensity backscatter variations. Experimental results demonstrate that SAR-W-MixMAE consistently improves baseline models in multilabel SAR image classification and flood detection tasks, extending the state-of-the-art performance on the popular BigEarthNet dataset. Extensive ablation studies reveal that pretraining duration and fine-tuning dataset size significantly impact downstream performance. In particular, early stopping during pretraining can yield optimal downstream task accuracy, challenging the assumption that prolonged pretraining enhances results. These insights contribute to the development of foundation models tailored for SAR imagery and provide practical guidelines for optimizing pretraining strategies in remote sensing applications.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"5590-5601"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11344788","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-12DOI: 10.1109/JSTARS.2026.3651577
Wei Huang;JiaLu Li;Qiqiang Chen;Junru Yin;Jiqiang Niu;Le Sun
In recent years, the integration of convolutional neural networks and Transformers has significantly advanced hyperspectral image (HSI) classification by jointly capturing local and global features. However, most existing methods primarily focus on the fusion of spectral–spatial features while neglecting the complementary information contained in frequency-domain features. To address this issue, we propose a spatial–frequency cross-attention fusion network (SFCFNet) that jointly models spectral, spatial, and frequency-domain features for HSI classification. The framework consists of three core modules: first, the multiscale spectral–spatial feature learning module extracts joint spectral spatial features using multiscale 3-D and 2-D convolutions. Next, the triple-branch representation module employs three branches to capture global spatial features of large-scale structures, local spatial features of fine-grained textures, and multiscale frequency features based on Haar wavelet decomposition, providing complementary multidomain representations for subsequent deep fusion. Finally, the dual-domain feature cross-attention fusion module achieves effective fusion of spatial structures and frequency-domain textures, enhancing the model’s ability to separate complex backgrounds from fine-grained targets and thereby improving classification performance. Compared with other methods, SFCFNet achieves higher overall accuracy on the Salinas, Houston2013, WHU-Hi-LongKou, and Xuzhou datasets, reaching 99.05%, 98.07%, 98.76%, and 98.18%, respectively.
{"title":"SFCFNet: A Spatial–Frequency Cross-Attention Fusion Network for Hyperspectral Image Classification","authors":"Wei Huang;JiaLu Li;Qiqiang Chen;Junru Yin;Jiqiang Niu;Le Sun","doi":"10.1109/JSTARS.2026.3651577","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3651577","url":null,"abstract":"In recent years, the integration of convolutional neural networks and Transformers has significantly advanced hyperspectral image (HSI) classification by jointly capturing local and global features. However, most existing methods primarily focus on the fusion of spectral–spatial features while neglecting the complementary information contained in frequency-domain features. To address this issue, we propose a spatial–frequency cross-attention fusion network (SFCFNet) that jointly models spectral, spatial, and frequency-domain features for HSI classification. The framework consists of three core modules: first, the multiscale spectral–spatial feature learning module extracts joint spectral spatial features using multiscale 3-D and 2-D convolutions. Next, the triple-branch representation module employs three branches to capture global spatial features of large-scale structures, local spatial features of fine-grained textures, and multiscale frequency features based on Haar wavelet decomposition, providing complementary multidomain representations for subsequent deep fusion. Finally, the dual-domain feature cross-attention fusion module achieves effective fusion of spatial structures and frequency-domain textures, enhancing the model’s ability to separate complex backgrounds from fine-grained targets and thereby improving classification performance. Compared with other methods, SFCFNet achieves higher overall accuracy on the Salinas, Houston2013, WHU-Hi-LongKou, and Xuzhou datasets, reaching 99.05%, 98.07%, 98.76%, and 98.18%, respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"4994-5008"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11340627","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146082022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-12DOI: 10.1109/JSTARS.2026.3651847
Kirk M. Scanlan;Anja Rutishauser;Sebastian B. Simonsen
The spatiotemporal properties of the Greenland Ice Sheet firn layer are an important factor when assessing overall ice sheet mass balance and internal meltwater storage capacity. Increasingly a target for the satellite remote sensing community, this study investigates the recovery of vertical firn density heterogeneity over a ten-year period from the synthesis of passive microwave and active radar altimetry measurements. The mismatch between ESA SMOS observations and a passive microwave forward model, initialized with surface densities estimated from the backscatter strength of ISRO/CNES SARAL and ESA CryoSat-2, serves as a proxy for vertical density variability. Validated with in situ measurements, the results demonstrate clear long-term patterns in Greenland firn heterogeneity characterized by spatially expansive sharp increases in firn heterogeneity following extreme melt seasons that require multiple quiescent years to rehabilitate. The results demonstrate that by the start of the 2023 melt season (i.e., the end of the timeframe considered), the Greenland firn layer had reached its most heterogeneous state of the preceding decade. Continued investigation into the synthesis of different remote sensing datasets represents a pathway toward generating novel insights into the spatiotemporal evolution of Greenland Ice Sheet surface conditions.
{"title":"Spatiotemporal Heterogeneity in Greenland Firn From the Synthesis of Satellite Radar Altimetry and Passive Microwave Measurements","authors":"Kirk M. Scanlan;Anja Rutishauser;Sebastian B. Simonsen","doi":"10.1109/JSTARS.2026.3651847","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3651847","url":null,"abstract":"The spatiotemporal properties of the Greenland Ice Sheet firn layer are an important factor when assessing overall ice sheet mass balance and internal meltwater storage capacity. Increasingly a target for the satellite remote sensing community, this study investigates the recovery of vertical firn density heterogeneity over a ten-year period from the synthesis of passive microwave and active radar altimetry measurements. The mismatch between ESA SMOS observations and a passive microwave forward model, initialized with surface densities estimated from the backscatter strength of ISRO/CNES SARAL and ESA CryoSat-2, serves as a proxy for vertical density variability. Validated with in situ measurements, the results demonstrate clear long-term patterns in Greenland firn heterogeneity characterized by spatially expansive sharp increases in firn heterogeneity following extreme melt seasons that require multiple quiescent years to rehabilitate. The results demonstrate that by the start of the 2023 melt season (i.e., the end of the timeframe considered), the Greenland firn layer had reached its most heterogeneous state of the preceding decade. Continued investigation into the synthesis of different remote sensing datasets represents a pathway toward generating novel insights into the spatiotemporal evolution of Greenland Ice Sheet surface conditions.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"4085-4098"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11339888","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Remote sensing change detection aims to identify changes on the Earth's surface from remote sensing images acquired at different times. However, the identification of changed areas is often hindered by pseudochanges in similar objects, leading to inaccurate identification of change boundaries. To address this issue, we propose a novel network named boundary-guided semantic context network (BSCNet), which decouples features to improve the feature representation ability for changing objects. Specifically, we design a selective context fusion module that selectively fuses semantically rich features by computing the similarity between features from adjacent stages of the backbone network, thereby preventing detailed features from being overwhelmed by contextual information. In addition, to enhance the ability to perceive changes, we design a context fast aggregation module that leverages a pyramid structure to help the model simultaneously extract and fuse detailed and semantic information at different scales, enabling more accurate change detection. Finally, we design a boundary-guided feature fusion module to aggregate edge-level, texture-level, and semantic-level information, which enables the network to represent change regions more comprehensively and precisely. Experimental results on the WHU-CD, LEVIR-CD, and SYSU-CD datasets show that BSCNet achieves F1 scores of 94.92%, 92.19%, and 82.55%, respectively.
{"title":"Learning Boundary-Aware Semantic Context Network for Remote Sensing Change Detection","authors":"Weiran Zhou;Guanting Guo;Huihui Song;Xu Zhang;Kaihua Zhang","doi":"10.1109/JSTARS.2026.3651696","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3651696","url":null,"abstract":"Remote sensing change detection aims to identify changes on the Earth's surface from remote sensing images acquired at different times. However, the identification of changed areas is often hindered by pseudochanges in similar objects, leading to inaccurate identification of change boundaries. To address this issue, we propose a novel network named boundary-guided semantic context network (BSCNet), which decouples features to improve the feature representation ability for changing objects. Specifically, we design a selective context fusion module that selectively fuses semantically rich features by computing the similarity between features from adjacent stages of the backbone network, thereby preventing detailed features from being overwhelmed by contextual information. In addition, to enhance the ability to perceive changes, we design a context fast aggregation module that leverages a pyramid structure to help the model simultaneously extract and fuse detailed and semantic information at different scales, enabling more accurate change detection. Finally, we design a boundary-guided feature fusion module to aggregate edge-level, texture-level, and semantic-level information, which enables the network to represent change regions more comprehensively and precisely. Experimental results on the WHU-CD, LEVIR-CD, and SYSU-CD datasets show that BSCNet achieves F1 scores of 94.92%, 92.19%, and 82.55%, respectively.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"4177-4187"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11339892","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As is well known, obtaining high-quality measured SAR vehicle data is difficult. As a result, deep learning-based data generation is frequently utilized for SAR target augmentation because of its affordability and simplicity of use. However, existing methods do not adequately consider the target scattering information during data generation, resulting in generated target SAR data that does not conform to the physical scattering laws of SAR imaging. In this article, we propose a SAR target data generation method based on target scattering features and cycle-consistent generative adversarial networks (CycleGAN). First, a physical model-based method called orthogonal matching pursuit (OMP) is adopted to extract the attribute scattering centers (ASCs) of SAR vehicle targets. Then, a multidimensional SAR target feature representation is constructed. Based on the scattering difference between the generated and real SAR target images, we introduce a loss function and further develop a generative model based on the CycleGAN. Therefore, the scattering mechanisms of SAR targets can be well learned, making the generated SAR data conform to the target scattering features. We conduct SAR target generation experiments under standard operating conditions (SOCs) and extended operating conditions (EOCs) on our self-acquired dataset as well as SAMPLE and MSTAR datasets. The SAR vehicle target data generated under SOC shows a more accurate scattering feature distribution to the real target data than other state-of-the-art methods. In addition, we generate SAR target data under EOC that conforms to SAR imaging patterns by modulating ASC feature parameters. Finally, the target recognition performance based on our proposed generated SAR vehicle data under SOC is validated, where the recognition rate increased by 4% after the addition of our generated target data.
{"title":"SAR Vehicle Data Generation With Scattering Features for Target Recognition","authors":"Dongdong Guan;Rui Feng;Yuzhen Xie;Huaiyue Ding;Yang Cui;Deliang Xiang","doi":"10.1109/JSTARS.2026.3652520","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3652520","url":null,"abstract":"As is well known, obtaining high-quality measured SAR vehicle data is difficult. As a result, deep learning-based data generation is frequently utilized for SAR target augmentation because of its affordability and simplicity of use. However, existing methods do not adequately consider the target scattering information during data generation, resulting in generated target SAR data that does not conform to the physical scattering laws of SAR imaging. In this article, we propose a SAR target data generation method based on target scattering features and cycle-consistent generative adversarial networks (CycleGAN). First, a physical model-based method called orthogonal matching pursuit (OMP) is adopted to extract the attribute scattering centers (ASCs) of SAR vehicle targets. Then, a multidimensional SAR target feature representation is constructed. Based on the scattering difference between the generated and real SAR target images, we introduce a loss function and further develop a generative model based on the CycleGAN. Therefore, the scattering mechanisms of SAR targets can be well learned, making the generated SAR data conform to the target scattering features. We conduct SAR target generation experiments under standard operating conditions (SOCs) and extended operating conditions (EOCs) on our self-acquired dataset as well as SAMPLE and MSTAR datasets. The SAR vehicle target data generated under SOC shows a more accurate scattering feature distribution to the real target data than other state-of-the-art methods. In addition, we generate SAR target data under EOC that conforms to SAR imaging patterns by modulating ASC feature parameters. Finally, the target recognition performance based on our proposed generated SAR vehicle data under SOC is validated, where the recognition rate increased by 4% after the addition of our generated target data.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"5520-5538"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11344756","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146175761","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-12DOI: 10.1109/JSTARS.2026.3650961
Shixin Liu;Pingyu Liu;Xiaofei Wang
The lack of prior knowledge is a challenging issue in target detection tasks for hyperspectral remote sensing images. In this article, we propose an effective network for object detection in hyperspectral remote sensing images. First, through spectral data augmentation methods, all surrounding pixels within a data block are encoded as the transformed spectral signature of the central pixel, thereby constructing a sufficient number of training sample pairs. Subsequently, a backbone network (PyramidMamba) was designed to establish long-term dependencies across the frequency domain and multiscale dimensions using the Mamba residual module and pyramid wavelet transform module. A residual self-attention module is further developed, integrating self-attention with convolutional operations to enhance feature extraction while improving the network's depth and stability. A backbone network was employed to extract representative vectors from augmented sample pairs, which were then optimized through a spectral contrast head to enhance the distinction between target and background features. Experimental results demonstrate that compared to mainstream algorithms, the proposed algorithm achieves higher detection accuracy and computational efficiency. It successfully learns deep nonlinear feature representations with stronger discriminative power, enabling effective separation of targets from background and delivering state-of-the-art performance.
{"title":"PyramidMamba: An Effective Hyperspectral Remote Sensing Image Target Detection Network","authors":"Shixin Liu;Pingyu Liu;Xiaofei Wang","doi":"10.1109/JSTARS.2026.3650961","DOIUrl":"https://doi.org/10.1109/JSTARS.2026.3650961","url":null,"abstract":"The lack of prior knowledge is a challenging issue in target detection tasks for hyperspectral remote sensing images. In this article, we propose an effective network for object detection in hyperspectral remote sensing images. First, through spectral data augmentation methods, all surrounding pixels within a data block are encoded as the transformed spectral signature of the central pixel, thereby constructing a sufficient number of training sample pairs. Subsequently, a backbone network (PyramidMamba) was designed to establish long-term dependencies across the frequency domain and multiscale dimensions using the Mamba residual module and pyramid wavelet transform module. A residual self-attention module is further developed, integrating self-attention with convolutional operations to enhance feature extraction while improving the network's depth and stability. A backbone network was employed to extract representative vectors from augmented sample pairs, which were then optimized through a spectral contrast head to enhance the distinction between target and background features. Experimental results demonstrate that compared to mainstream algorithms, the proposed algorithm achieves higher detection accuracy and computational efficiency. It successfully learns deep nonlinear feature representations with stronger discriminative power, enabling effective separation of targets from background and delivering state-of-the-art performance.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"4163-4176"},"PeriodicalIF":5.3,"publicationDate":"2026-01-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11329180","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026481","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-05DOI: 10.1109/JSTARS.2025.3650075
Zhenkai Wu;Xiaowen Ma;Kai Zheng;Rongrong Lian;Yun Chen;Zhenhua Huang;Wei Zhang;Siyang Song
Mamba, with itsadvantages of global perception and linear complexity, has been widely applied to identify changes of the target regions within the remote sensing (RS) images captured under complex scenarios and varied conditions. However, existing remote sensing change detection (RSCD) approaches based on Mamba frequently struggle to effectively perceive the inherent locality of change regions as they direct flatten and scan RS images (i.e., the features of the same region of changes are not distributed continuously within the sequence but are mixed with features from other regions throughout the sequence). In this article, we propose a novel locally adaptive SSM-based approach, termed CD-Lamba, which effectively enhances the locality of change detection while maintaining global perception. Specifically, our CD-Lamba includes a locally adaptive state-space scan (LASS) strategy for locality enhancement, a cross-temporal state-space scan strategy for bitemporal feature fusion, and a window shifting and perception mechanism to enhance interactions across segmented windows. These strategies are integrated into a multiscale cross-temporal LASS module to effectively highlight changes and refine changes’ representations feature generation. CD-Lamba significantly enhances local–global spatio-temporal interactions in bitemporal images, offering improved performance in RSCD tasks. Extensive experimental results show that CD-Lamba achieves state-of-the-art performance on four benchmark datasets with a satisfactory efficiency-accuracy tradeoff.
{"title":"CD-Lamba: Boosting Remote Sensing Change Detection via a Cross-Temporal Locally Adaptive State Space Model","authors":"Zhenkai Wu;Xiaowen Ma;Kai Zheng;Rongrong Lian;Yun Chen;Zhenhua Huang;Wei Zhang;Siyang Song","doi":"10.1109/JSTARS.2025.3650075","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3650075","url":null,"abstract":"Mamba, with itsadvantages of global perception and linear complexity, has been widely applied to identify changes of the target regions within the remote sensing (RS) images captured under complex scenarios and varied conditions. However, existing remote sensing change detection (RSCD) approaches based on Mamba frequently struggle to effectively perceive the inherent locality of change regions as they direct flatten and scan RS images (i.e., the features of the same region of changes are not distributed continuously within the sequence but are mixed with features from other regions throughout the sequence). In this article, we propose a novel locally adaptive SSM-based approach, termed CD-Lamba, which effectively enhances the locality of change detection while maintaining global perception. Specifically, our CD-Lamba includes a locally adaptive state-space scan (LASS) strategy for locality enhancement, a cross-temporal state-space scan strategy for bitemporal feature fusion, and a window shifting and perception mechanism to enhance interactions across segmented windows. These strategies are integrated into a multiscale cross-temporal LASS module to effectively highlight changes and refine changes’ representations feature generation. CD-Lamba significantly enhances local–global spatio-temporal interactions in bitemporal images, offering improved performance in RSCD tasks. Extensive experimental results show that CD-Lamba achieves state-of-the-art performance on four benchmark datasets with a satisfactory efficiency-accuracy tradeoff.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"4028-4044"},"PeriodicalIF":5.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11322867","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026536","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-05DOI: 10.1109/JSTARS.2025.3650498
Lei Chen;Haiping Xiao
Considering the challenges of traditional monitoring methods in achieving large-scale surface subsidence monitoring over mining areas, as well as the difficulties in modeling settlement prediction methods and acquiring model hyperparameters, this article integrates rainfall data from the mining area, analyzes the spatiotemporal evolution characteristics of surface subsidence using small baseline subset interferometric synthetic aperture radar (SBAS-InSAR) technology, and proposes an APO-BiLSTM settlement prediction model. This model employs the Arctic Puffin Optimization (APO) to optimize the hyperparameters of a bidirectional long short-term memory (BiLSTM) network. The research results indicate that rainfall has caused the formation of nine distinct subsidence areas in the mining area, with Subsidence Area IX experiencing the most severe subsidence, covering an area of 9.31 km2, with an average annual subsidence rate as high as -331 mm/a and a maximum cumulative subsidence of 427 mm. In the early stages of subsidence, a “subsidence-lifting-subsidence-lifting” phenomenon is observed, which gradually stabilizes in the later stages. In addition, compared to the LSTM and BiLSTM models, the proposed APO-BiLSTM model reduces the root mean square error of single-step predictions by 79.8% and 76.6%, respectively, and the mean absolute error by 79.1% and 75.9%, while increasing the R2 by 6.0% and 4.4% . The absolute error of 78.3% of the high coherence points is less than 4 mm, indicating that the model has promising application prospects in large-scale surface subsidence prediction in mining areas.
{"title":"Spatiotemporal Evolution of Surface Subsidence in Large-Scale Mining Areas Under Rainfall Influence and Optimization Model Development","authors":"Lei Chen;Haiping Xiao","doi":"10.1109/JSTARS.2025.3650498","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3650498","url":null,"abstract":"Considering the challenges of traditional monitoring methods in achieving large-scale surface subsidence monitoring over mining areas, as well as the difficulties in modeling settlement prediction methods and acquiring model hyperparameters, this article integrates rainfall data from the mining area, analyzes the spatiotemporal evolution characteristics of surface subsidence using small baseline subset interferometric synthetic aperture radar (SBAS-InSAR) technology, and proposes an APO-BiLSTM settlement prediction model. This model employs the Arctic Puffin Optimization (APO) to optimize the hyperparameters of a bidirectional long short-term memory (BiLSTM) network. The research results indicate that rainfall has caused the formation of nine distinct subsidence areas in the mining area, with Subsidence Area IX experiencing the most severe subsidence, covering an area of 9.31 km<sup>2</sup>, with an average annual subsidence rate as high as -331 mm/a and a maximum cumulative subsidence of 427 mm. In the early stages of subsidence, a “subsidence-lifting-subsidence-lifting” phenomenon is observed, which gradually stabilizes in the later stages. In addition, compared to the LSTM and BiLSTM models, the proposed APO-BiLSTM model reduces the root mean square error of single-step predictions by 79.8% and 76.6%, respectively, and the mean absolute error by 79.1% and 75.9%, while increasing the R<sup>2</sup> by 6.0% and 4.4% . The absolute error of 78.3% of the high coherence points is less than 4 mm, indicating that the model has promising application prospects in large-scale surface subsidence prediction in mining areas.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"4045-4055"},"PeriodicalIF":5.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11328805","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-05DOI: 10.1109/JSTARS.2025.3650563
Jiayi Liu;Zhe Guo;Rui Luo;Yi Liu;Shaohui Mei
In optical remote sensing, thin clouds pose a significant challenge for cloud removal due to their high brightness and spectral similarity to bright man-made objects, such as buildings. Existing thin cloud removal methods typically rely on single feature extraction or fixed physical model, which struggle to differentiate thin clouds from bright backgrounds in complex scenes, resulting in suboptimal image recovery. To address these issues, we propose atmospheric scattering-driven recovery enhancement network (ASENet), a novel network that integrates atmospheric scattering modeling with multilevel feedback enhancement mechanism to improve thin cloud removal for complex scenes. By learning the shape details of both thin clouds and ground features, ASENet dynamically adjusts weights in high-concentration cloud regions, ensuring clearer image recovery. Specifically, we design a feature fusion residual dehazing generator, which leverages deep residual blocks and high-resolution dehazing modules to capture environmental memory and enhance detail features, improving the model's adaptability and recovery accuracy in thin cloud regions. In addition, to better preserve the edges and textures of buildings and other ground objects, we introduce a spatial detail enhanced discriminator that incorporates the cascaded feedback-based feature mapping. This enables ASENet to better capture image details, maintain structural consistency, and effectively distinguish thin clouds from high-reflectance background objects. Extensive experiments on three benchmark datasets L8-ImgSet, RICE1, and WHUS2-CR demonstrate that our proposed ASENet outperforms state-of-the-art methods across both subjective and objective evaluation metrics, proving its effectiveness in thin cloud removal tasks under complex scenes.
{"title":"ASENet: Thin Cloud Removal Network for Complex Scenes via Atmospheric Scattering Modeling and Feedback Enhancement","authors":"Jiayi Liu;Zhe Guo;Rui Luo;Yi Liu;Shaohui Mei","doi":"10.1109/JSTARS.2025.3650563","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3650563","url":null,"abstract":"In optical remote sensing, thin clouds pose a significant challenge for cloud removal due to their high brightness and spectral similarity to bright man-made objects, such as buildings. Existing thin cloud removal methods typically rely on single feature extraction or fixed physical model, which struggle to differentiate thin clouds from bright backgrounds in complex scenes, resulting in suboptimal image recovery. To address these issues, we propose atmospheric scattering-driven recovery enhancement network (ASENet), a novel network that integrates atmospheric scattering modeling with multilevel feedback enhancement mechanism to improve thin cloud removal for complex scenes. By learning the shape details of both thin clouds and ground features, ASENet dynamically adjusts weights in high-concentration cloud regions, ensuring clearer image recovery. Specifically, we design a feature fusion residual dehazing generator, which leverages deep residual blocks and high-resolution dehazing modules to capture environmental memory and enhance detail features, improving the model's adaptability and recovery accuracy in thin cloud regions. In addition, to better preserve the edges and textures of buildings and other ground objects, we introduce a spatial detail enhanced discriminator that incorporates the cascaded feedback-based feature mapping. This enables ASENet to better capture image details, maintain structural consistency, and effectively distinguish thin clouds from high-reflectance background objects. Extensive experiments on three benchmark datasets L8-ImgSet, RICE1, and WHUS2-CR demonstrate that our proposed ASENet outperforms state-of-the-art methods across both subjective and objective evaluation metrics, proving its effectiveness in thin cloud removal tasks under complex scenes.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"19 ","pages":"3964-3982"},"PeriodicalIF":5.3,"publicationDate":"2026-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11328777","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：