{"title":"Spatiotemporal Attention Network for Chl-a Prediction With Sparse Multifactor Observations","authors":"Xudong Jiang;Yunfan Liu;Shuyu Wang;Wengen Li;Jihong Guan","doi":"10.1109/LGRS.2025.3563458","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3563458","url":null,"abstract":"Chlorophyll-a (Chl-a) is a critical indicator of water quality, and accurate Chl-a prediction is essential for marine ecosystem protection. However, existing methods for Chl-a prediction cannot adequately uncover the correlations between Chl-a and other environmental factors, e.g., sea surface temperature (SST) and photosynthetically active radiation (PAR). In addition, it is also difficult for these methods to learn the burst distributions of Chl-a data, i.e., increasing sharply for certain short periods of time and remaining stable for the rest of time. Furthermore, as original Chl-a, SST, and PAR data are often of high sparsity, most approaches rely on complete reanalysis data, which can incur accumulated error accumulation and degrade prediction performance. To address these three issues, we proposed a spatiotemporal attention network entitled SMO-STANet for Chl-a prediction. Concretely, the multibranch spatiotemporal embedding module and spatiotemporal attention module are developed to learn the correlations between Chl-a and the two external factors, i.e., SST and PAR, thus facilitating the learning of the underlying spatiotemporal distribution of Chl-a. In addition, we designed a scaled loss function to enable SMO-STANet to adapt to the burst distributions of Chl-a. Finally, we develop a sparse observation data completion module to address the issue of data sparsity. According to the experimental results on two real datasets, SMO-STANet outperforms existing methods for Chl-a prediction by a large margin. The code is available at <uri>https://github.com/ADMIS-TONGJI/SMO-STANet</uri>","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shichao Zhou;Zekai Zhang;Yingrui Zhao;Wenzheng Wang;Zhuowei Wang
{"title":"Single-Frame Infrared Small Target Detection With Dynamic Multidimensional Convolution","authors":"Shichao Zhou;Zekai Zhang;Yingrui Zhao;Wenzheng Wang;Zhuowei Wang","doi":"10.1109/LGRS.2025.3563588","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3563588","url":null,"abstract":"Mainly resulting from remote imaging, the target of interest in infrared imagery tends to occupy very few pixels with faint radiation value. The absence of discriminative spatial features of infrared small targets challenges traditional single-frame detectors that rely on handcrafted filter engineering to amplify local contrast. Recently, emerging deep convolutional network (DCN)-based detectors use elaborate multiscale spatial contexts representation to “semantically reason” the small and dim infrared target in pixel level. However, the multiple spatial convolution-downsampling operation adopted by such leading methods could cause the loss of target appearance information during the initial feature encoding stage. To further enhance the low-level feature representation capacity, we advocate the insight of traditional matching filter and propose a novel pixel-adaptive convolution kernel modulated by multidimensional contexts (i.e., dynamic multidimensional convolution, DMConv). Precisely, the DMConv is refined by three collaborative and indispensable attention functions that focus on spatial layout, channel, and kernel number of convolution kernel, respectively, so as to effectively mine, highlight, and enrich fine-grained spatial features with moderate computational burden. Extensive experiments conducted on two real-world infrared single-frame image datasets, i.e., SIRST and Infrared Small Target Detection (IRSTD)-1k, favorably demonstrate the effectiveness of the proposed method and obtain consistent performance improvements over other state-of-the-art (SOTA) detectors.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"SAIG: Semantic-Aware ISAR Generation via Component-Level Semantic Segmentation","authors":"Yuxin Zhao;Huaizhang Liao;Derong Kong;Zhixiong Yang;Jingyuan Xia","doi":"10.1109/LGRS.2025.3563712","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3563712","url":null,"abstract":"This letter addresses the challenge of generating high-fidelity inverse synthetic aperture radar (ISAR) images from optical images, particularly for space targets. We propose a framework for the generation of ISAR images incorporating component refinement, which attains high-fidelity ISAR scattering characteristics through the integration of an advanced generation model predicated on semantic segmentation, designated as semantic-aware ISAR generation (SAIG). SAIG renders ISAR images from optical equivalents by learning mutual semantic segmentation maps. Extensive simulations demonstrate its effectiveness and robustness, outperforming state-of-the-art (SOTA) methods by over 8% across key evaluation metrics.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dongyang Hou;Yang Yang;Siyuan Wang;Xiaoguang Zhou;Wei Wang
{"title":"Spatial–Frequency Multiple Feature Alignment for Cross-Domain Remote Sensing Scene Classification","authors":"Dongyang Hou;Yang Yang;Siyuan Wang;Xiaoguang Zhou;Wei Wang","doi":"10.1109/LGRS.2025.3563349","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3563349","url":null,"abstract":"Domain adaptation is a pivotal technique for improving the classification performance of remote sensing scenes impacted by data distribution shifts. The existing spatial-domain feature alignment methods are vulnerable to complex scene clutter and spectral variations. Considering the robustness of frequency representation in preserving edge details and structural patterns, this letter presents a novel spatial-frequency multiple alignment domain adaptation (SFMDA) method for remote sensing scene classification. First, a frequency-domain invariant feature learning module is introduced, which employs the Fourier transform and high-frequency mask strategy to derive frequency-domain features exhibiting enhanced interdomain invariance. Subsequently, a spatial-frequency feature cross fusion module is developed to achieve more robust and domain-representative spatial-frequency fusion representations through dot product attention and interaction mechanisms. Finally, a multiple feature alignment strategy is devised to minimize both spatial-domain feature differences and fusion feature discrepancies across the source and target domains, thereby facilitating more effective interdomain knowledge transfer. Experimental results on six cross-domain scenarios demonstrate that SFMDA outperforms eight state-of-the-art (SOTA) methods, achieving a 3.87%–17.98% accuracy improvement. Furthermore, SFMDA is compatible with the existing spatial-domain learning frameworks, enabling seamless integration for further performance gains. Our code will be available at <uri>https://github.com/GeoRSAI/SFMDA</uri>","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"QS-FDTD Modeling of Dispersive Superparamagnetic Soils for Time-Domain Electromagnetic Method","authors":"Talha Saydam;Serkan Aksoy","doi":"10.1109/LGRS.2025.3561498","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3561498","url":null,"abstract":"Time-domain electromagnetic (TDEM) method is extensively utilized in geophysical surveys for detection of groundwater and mineral deposits. However, the dispersive effect of superparamagnetic (SPM) soils significantly impacts performance of these systems. In modeling of the SPM soils, the distribution of magnetic particles in the soil is generally accounted with a log-uniform model in which time-relaxation constants are distributed uniformly in a finite time range. In this study, the effect of the SPM soils on the TDEM system performance is analyzed by a quasi-static finite-difference time-domain (QS-FDTD) method. The treatment of the magnetic dispersive SPM soil of the log-uniform model is performed by an auxiliary differential equation (ADE) technique (without any convolution) in the QS-FDTD method. The numerical results are validated for a homogeneous SPM half-space problem and a problem of a thin SPM upper layer with a buried conductive body. Afterward, a dispersive complex problem is also solved. The obtained results can be used to evaluate the TDEM performance for the complex magnetic dispersive problems.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Estimating Location and Polarity of Vibroseis Reflections Using Multiscale Phase-Only Correlation","authors":"Peng Fang;Jinhai Zhang","doi":"10.1109/LGRS.2025.3563168","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3563168","url":null,"abstract":"The identification of seismic reflections in vibroseis data is crucial for evaluating subsurface structures. However, precisely localizing these reflections and determining their polarity is challenging. In this study, we propose a robust method for detecting weak reflections and accurately locating reflection spikes as well as their polarity using multiscale phase-only correlation (MPOC). By applying the generalized S-transform, we obtain local phase information from both the vibroseis data and the Klauder wavelet across multiple scales. We then compute the phase-only correlation (POC) between these two signals in the time-frequency domain at different scales and stack all MPOC coefficients to quantify their local phase similarity. This approach achieves high precision in detecting weak reflections and identifying their polarity, even in the presence of noise. Numerical experiments with synthetic and real data confirm the effectiveness of the proposed method, which can also be applied to various sweep sources, such as Martian SHARAD or MARSIS radar data.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974575","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Saied Pirasteh;Muhammad Yasir;Hong Fan;Fernando J. Aguilar;Md Sakaouth Hossain;Huxiong Li
{"title":"Enhanced Landslide Detection Using a Swin Transformer With Multiscale Feature Fusion and Local Information Aggregation Modules","authors":"Saied Pirasteh;Muhammad Yasir;Hong Fan;Fernando J. Aguilar;Md Sakaouth Hossain;Huxiong Li","doi":"10.1109/LGRS.2025.3560990","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3560990","url":null,"abstract":"In recent years, detecting and monitoring landslides have become increasingly critical for disaster management and mitigation efforts. Here, we propose a model for landslide detection utilizing a combination of the Swin Transformer architecture with multiscale feature fusion lateral connection and local information aggregation modules (LIAMs). The Swin Transformer, known for its effectiveness in image understanding tasks, serves as the backbone of our detection system. By leveraging its hierarchical self-attention mechanism, the Swin Transformer can effectively capture both local and global contextual information from input images, facilitating accurate feature representation. To increase the performance of the Swin Transformer specifically for landslide detection, we introduce two additional modules: the multiscale feature fusion lateral connection module (MFFLCM) and the LIAM. The former module enables the integration of features across multiple scales, allowing the model to capture both fine-grained details and broader contextual information relevant to landslide characteristics. Meanwhile, the latter module focuses on aggregating local information within regions of interest, further refining the model’s ability to discriminate between landslide and non-landslide areas. Through extensive test and evaluation of benchmark datasets, our proposed method demonstrates promising results in detecting landslides with high mIoU, <inline-formula> <tex-math>$F1$ </tex-math></inline-formula> score, kappa, precision, and recall 84.2%, 90.7%, 82.6%, 89.9%, and 91.9%, respectively. Moreover, its robustness to variations in terrain and environmental conditions suggests its potential for real-world applications in landslide monitoring and early warning systems. Overall, our study highlights the effectiveness of integrating advanced transformer architectures with tailored modules for addressing complex geospatial challenges like landslide detection.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143931317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"CaPaT: Cross-Aware Paired-Affine Transformation for Multimodal Data Fusion Network","authors":"Jinping Wang;Hao Chen;Xiaofei Zhang;Weiwei Song","doi":"10.1109/LGRS.2025.3560931","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3560931","url":null,"abstract":"This letter proposes a cross-aware paired-affine transformation (CaPaT) network for multimodal data fusion tasks. Unlike existing networks that employ weight-sharing or indirect interaction strategies, the CaPaT introduces a direct feature interaction paradigm that significantly improves the transfer efficiency of feature fusion while reducing the number of model parameters. Specifically, this letter, respectively, splits multimodal data along the channel domain. It synthesizes specific group channels and opposite residual channels as data pairs to generate refined features, achieving direct interaction among multimodal features. Next, a scaling attention module is conducted on the refined feature pair for confidence map generation. Then, this letter multiplies confidence maps by their corresponding feature pairs, determining a more reasonable and significant margin feature representation. Finally, a classifier is conducted on the transformation features to output the final class labels. Experimental results demonstrate that the CaPaT achieves superior classification performance with fewer parameters than state-of-the-art methods.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Low-Overhead Compression-Aware Channel Filtering for Hyperspectral Image Compression","authors":"Wei Zhang;Jiayao Xu;Yueru Chen;Dingquan Li;Wen Gao","doi":"10.1109/LGRS.2025.3562933","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3562933","url":null,"abstract":"Both traditional and learning-based hyperspectral image (HSI) compression methods suffer from significant quality loss at high compression ratios. To address this, we propose a low-overhead, compression-aware channel filtering method. The encoder derives channel filters via least squares regression (LSR) between lossy compressed and original images. The bitstream, containing the compressed image and filters, is sent to the decoder, where the filters enhance image quality. This simple, compression-aware approach is compatible with any existing framework, enhancing quality while introducing only a negligible increase in bitstream size and decoding time, thereby achieving low overhead. Experimental results show consistent rate-distortion gains, reducing compression rates by 10.51% to 39.81% on the GF-5 dataset with minimal decoding and storage overhead.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Building Extraction From Multi-View RGB-H Images With General Instance Segmentation Networks and a Grouping Optimization Algorithm","authors":"Dawen Yu;Hao Cheng","doi":"10.1109/LGRS.2025.3562892","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3562892","url":null,"abstract":"Bird’s-eye-view (BEV) building mapping from remote sensing images is a studying hotspot with broad applications. In recent years, deep learning (DL) has significantly advanced the development of automatic building extraction methods. However, most existing research focuses on segmenting buildings from a single perspective, such as orthophotos, overlooking the rich information of multi-view images. In surveying and mapping, individual building instances need to be separated even when they are adjacent or touching. Since orthophotos cannot capture building walls due to self-occlusion, distinguishing between closely connected buildings in densely built areas becomes challenging. To tackle this issue, we propose a multi-view collaborative pipeline for instance-level building segmentation. This pipeline utilizes a grouping optimization algorithm to merge segmentation results from multiple views, which are predicted by general instance segmentation networks and projected onto the BEV, to produce the final building instance polygons. Both qualitative and quantitative results show that the proposed multi-view collaborative pipeline significantly outperforms the popular orthophoto-based pipeline on the InstanceBuilding dataset.","PeriodicalId":91017,"journal":{"name":"IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society","volume":"22 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}