IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society最新文献

{"title":"Collaborative Spectral–Spatial Representation Learning for Hyperspectral and LiDAR Classification Under Limited Samples","authors":"Jia Li;Lin Zhao;Yuanjie Dai;Minhui Zhao;Minghao Li;Jianhui Wu","doi":"10.1109/LGRS.2025.3559913","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3559913","url":null,"abstract":"Hyperspectral images (HSIs) offer exceptional precision in distinguishing features due to their broad spectral dimensions. However, their high dimensionality gives rise to a phenomenon known as the “dimensional curse,” characterized by data sparsity in high-dimensional feature spaces. This issue is further exacerbated by the limited number of labeled samples, rendering it challenging to effectively define the decision boundary and increasing risk of overfitting. To address the challenges, we propose a spectral-spatial representation learning (SSRL) framework based on HSI and light detection and ranging (LiDAR) data, which enhances the generalization of spectral features while reducing dimensionality through the optimization of spectral-wise information. Meanwhile, a local-global spatial feature fusion mechanism is designed for LiDAR spatial features to further alleviating the sparsity of spectral features and to effectively recognize complex land cover. The method fully leverages the complementary strengths of HSI and LiDAR data through self-supervised contrastive learning, effectively mitigates the challenge posed by data properties. Extensive experiments were conducted on three widely used HSI-LiDAR datasets, and the results demonstrate that the proposed algorithm outperforms state-of-art methods in classification accuracy.","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":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865266","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":"Shipborne HFSWR Sea Clutter Suppression Method Based on MultiDomain Information Synergy","authors":"Jiangnan Zhong;Haibo Yu;Ling Zhang;Gangsheng Li;Q. M. Jonathan Wu","doi":"10.1109/LGRS.2025.3559903","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3559903","url":null,"abstract":"Due to the integrated effect of many factors including nonuniform wave motion and shipboard platform motion, the echo signals received by shipborne high-frequency surface wave radar (HFSWR) often suffer from issues such as sea clutter spreading. A large number of targets are submerged by sea clutter, creating a non-detectable zone. To address this problem, a novel sea clutter suppression method based on multidomain information synergy is proposed. The proposed method first identifies the broadening region of sea clutter by its characteristics. The multidomain spectrum is then constructed using a narrow beam forming method. Afterward, the Laplace kernel function is employed to screen the sea clutter regions to obtain the plausible region of interest (PROI). Ultimately, we integrate all PROIs and obtain sea clutter suppression results. Field data from shipborne HFSWR and validation results from the automatic identification system (AIS) demonstrate that the proposed method can effectively suppress sea clutter, increase the signal-to-clutter ratio (SCR), and achieve better target detection performance.","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":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870917","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":"NSC-SSNet: A Self-Supervised Network With Neighborhood Subsampling and Calibration Constraints for Sonar Image Denoising","authors":"Yapei Zhang;Yancheng Liu;Yanhao Wang;Fei Yu","doi":"10.1109/LGRS.2025.3560072","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3560072","url":null,"abstract":"Sonar imaging systems play a crucial role in several marine applications. However, complex underwater environment introduces scattering noise, significantly degrading sonar image quality and hindering performance for downstream tasks. Although several self-supervised denoising methods have emerged to address the lack of clean reference images, they often fail to effectively capture both local and global structural information, thus showing suboptimal performance on sonar images. To address these challenges, we propose NSC-SSNet, a self-supervised network with neighborhood subsampling and calibration constraints for sonar image denoising. In particular, NSC-SSNet adopts an end-to-end self-supervised framework that operates in the denoising and calibration stages. By leveraging neighborhood subsampling and calibration constraints, it effectively extracts latent features of clean images from noisy input. Moreover, it simultaneously captures local and global associations between pixels by incorporating additional terms in the loss function to improve image quality while denoising. Extensive experiments on real-world sonar image datasets demonstrate that NSC-SSNet outperforms existing self-supervised denoising methods in terms of both noise removal and quality enhancement.","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":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871078","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":"Exploring Influencing Factors for Differences in Integral and Complete Urban Surface Temperatures","authors":"Jiashuo Li;Xiujuan Dai;Dandan Wang;Yunhao Chen;Zhenyuan Zhu","doi":"10.1109/LGRS.2025.3559323","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3559323","url":null,"abstract":"Complete urban surface temperature (UST) (<inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula>) takes into account the total active surface areas and is used to estimate the surface temperature over a 3-D rough surface such as cities. Direct calculations of <inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula> require temperatures of each surface of the urban canopy, which are hard to obtain in actual remote sensing observations. Moreover, solid-angle integral temperature (<inline-formula> <tex-math>$T_{text {SI}}$ </tex-math></inline-formula>) calculated using multiangle remote sensing observations has great potential for approaching <inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula>. However, due to varying mechanisms, some differences remain between them. This study uses temperatures of urban facets in 3-D (TUF-3D) and surface-sensor-sun urban model (SUM) models to compute integral temperatures for multiple view angles over various urban forms and investigates the differences between <inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula> and <inline-formula> <tex-math>$T_{text {SI}}$ </tex-math></inline-formula> and the influencing factors. The difference is minimized at VZA <inline-formula> <tex-math>$=48^{circ }$ </tex-math></inline-formula>–70° and VAA <inline-formula> <tex-math>$=0^{circ }$ </tex-math></inline-formula>–360°, and the mean absolute error (MAE) is 0.67 K. Urban canopy geometry (UCG) and solar zenith angles (SZAs) are the important influencing factors. Compared with <inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula>, <inline-formula> <tex-math>$T_{text {SI}}$ </tex-math></inline-formula> underestimates the proportion of the wall. The MAE between <inline-formula> <tex-math>$T_{text {SI}}$ </tex-math></inline-formula> and <inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula> decreases as the wall fraction in the integral domain increases but increases when the wall fraction exceeds a threshold. The upper limit of the optimal integral domain (OID) is basically 70° and the lower limit hovers around 48°, moving away from and then approaching the zenith as the SZA increases. This study evaluates the influencing factors for differences in <inline-formula> <tex-math>$T_{text {SI}}$ </tex-math></inline-formula> and <inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula>. It offers a simple and high-accuracy method for approaching <inline-formula> <tex-math>$T_{textrm {c}}$ </tex-math></inline-formula> which can be used to facilitate research in urban energy balance and urban climate.","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":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879514","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":"VDXNet: A Novel Lightweight Deep Learning Model for Vehicle Detection With Aerial Images","authors":"Ali Khan;Somaiya Khan;Mohammed A. M. Elhassan;Izhar Ahmed Khan;Hai Deng;Mohammed Alsuhaibani","doi":"10.1109/LGRS.2025.3558423","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3558423","url":null,"abstract":"In intelligent transportation systems (ITSs), real-time vehicle detection based on aerial images is crucial for effective traffic monitoring and decision-making. However, detecting small vehicles with varying orientations in complex backgrounds remains technically challenging, as existing models often struggle to balance the requirements of detection accuracy and computational efficiency. In this letter, we introduce the vehicle detection eXtended network (VDXNet), a lightweight model that is capable of achieving high detection performance while minimizing computational complexity. VDXNet incorporates the novel residual cross depth fusion (RxDF) module to enhance feature extraction in the backbone. Furthermore, it uses newly proposed lightweight feature pyramid pooling (LiteFPP) and channel reduction downsampling (CRDown) modules to support multiscale detection and spatial dimensionality reduction. These innovations streamline the model’s neck, reducing complexity while ensuring accurate detection of vehicles across diverse scales, angles, and backgrounds. Evaluations on the UCAS-AOD, VEDAI, UAV-ROD, and UAVDT datasets demonstrate that VDXNet achieves substantial reductions in model complexity, with 1.608M parameters (a decrease of 37.72%) and 5.9 GFLOPs (a decrease of 6.35%) compared with the YOLO11n model. Despite these efficiency gains, VDXNet also improves mAP by 0.52%, achieving 96.3% mAP on the UCAS_AOD 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":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143845537","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":"Determination of the Hemispherical Equivalent Angle for Surface Upward Longwave Radiation","authors":"Xi Zhang;Biao Cao;Qiang Na;Limeng Zheng;Ziyi Yang;Boxiong Qin;Zunjian Bian;Yongming Du;Hua Li;Qing Xiao;Qinhuo Liu","doi":"10.1109/LGRS.2025.3558980","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3558980","url":null,"abstract":"Surface upward longwave radiation (SULR) is an indicator reflecting the thermal condition of the Earth’s surface and a key variable in the surface radiation budget. It is widely employed in hydrology, ecology, meteorology, and environmental fields. Current SULR remote sensing retrieval methods assume the Earth’s surface is Lambertian, i.e., the surface thermal radiation is isotropic. However, ground, airborne, and satellite-scale studies show the brightness temperature differences are up to 10 K in different directions for complex land surfaces. The ignorance of thermal anisotropy limits the accuracy of current SULR products. Therefore, it is essential to perform hemispherical integration of SULR under conditions of thermal anisotropy. The hemispherical integrated SULR can be approximated by a directional SULR at hemispherical equivalent angle (HEA). However, the current HEA for SULR is between 44.0° and 55.0°. To make it clearer, the Vinnikov-Chen kernel-driven model (KDM) is extensively adopted to simulate 3645600 samples for HEA determination. Results show that the range of HEA is 46.6°–47.8° (with an average HEA equal to 47.0°). The HEA is independent of the KDM coefficients and solar azimuth angle (SAA), but slightly changes with solar zenith angle (SZA) and hotspot width. Furthermore, the validation of HEA using a series of 3-D radiative transfer simulations shows the mean absolute error (MAE) is 0.00–1.36 W/m2. This study provides a new insight to the HEA, which will benefit to SULR estimation.","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":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143870994","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":"Decoupled Dynamic Spatial–Temporal Graph Neural Network for Sea Surface Temperature Prediction","authors":"Kundong Jin;Xiaoyu He;Jinkun Yang;Rong Jin;Feng Fu","doi":"10.1109/LGRS.2025.3558739","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3558739","url":null,"abstract":"Accurate sea surface temperature (SST) prediction is essential for advancing the understanding of marine ecosystems and global climate dynamics. SST variations arise from a dynamic interplay of multiple factors. Specifically, we model changes in SST as a combination of diffusion processes, representing the spread of thermal energy across the ocean, and inherent signals that capture localized and intrinsic patterns of temperature variation. This perspective recognizes that SST is influenced not only by diffusion but also by factors such as ocean currents, seasonal cycles, and localized climatic events. Thus, we propose decoupled dynamic spatial-temporal graph neural network (DDSTGNN), a novel model designed to decouple diffusion and inherent SST signals using data-driven methods. The model incorporates an estimation gate and a residual decomposition mechanism to effectively achieve this separation. In addition, it integrates a dynamic graph learning module to model the evolving spatial and temporal dependencies of SST networks. Extensive experiments on two real-world SST datasets demonstrate that DDSTGNN outperforms state-of-the-art methods, highlighting its superior ability to model spatial-temporal SST 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":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871074","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":"3DInception-U: Lightweight Network for 3-D Magnetotelluric Inversion Based on Inception Module","authors":"Zhiliang Zhan;Weiwei Ling;Kejia Pan;Chaofei Liu;Jiajing Zhang;Yuan Sun;Jingtian Tang;Wenbo Xiao","doi":"10.1109/LGRS.2025.3558938","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3558938","url":null,"abstract":"In the field of geophysical exploration, the application of deep learning techniques has garnered significant attention. This letter proposes a new deep learning model for 3-D magnetotelluric inversion, named 3DInception-U. In this model, we integrate the inception module into the network architecture and combine the concatenation layer with a U-Net structure. This model has two advantages: First, the inception module, along with the deep concatenation layer, enhances the network’s capability for feature extraction and representation, and second, the skip connections in the U-Net facilitate information propagation, enabling the design of a network with fewer parameters but better performance. We produced 10 000 3-D complex samples for training by Gaussian random fields (GRFs) and compared 3DInception-U with existing 3-D magnetotelluric (MT) inversion models and applied it to real geological interpretation. The results demonstrate that this network architecture achieves good inversion accuracy and robustness.","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":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865280","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":"Spatial Nonstationarity in DL-Based Crop Phenological Analysis","authors":"Pattathal V. Arun;Kuldeep Chaurasia;Soorya Suresh;Arnon Karnieli","doi":"10.1109/LGRS.2025.3558852","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3558852","url":null,"abstract":"Vegetation index (VI) curves, derived from multitemporal satellite images, are being widely employed to model the crop-specific phenological events. The current study analyzed a novel approach to mitigate the effect of violating the independent and identically distributed (i.i.d.) assumption in classifying the VI curves. Even though deep learning (DL)-based classification methods have produced cutting-edge outcomes, the correlation of spatially adjacent samples is not generally considered. The proposed approach dynamically transformed the VI curves to a graph representation, where the nodes correspond to the curves. Graph convolutional operations along with Kolmogorov-Arnold network (KAN) were then used to learn the embedded representations, based on the labeled samples in the proximity. The collaborative learning of graph-formulation and classification facilitated the consideration of non-i.i.d. nature of the VI curve samples. The proposed and benchmark methods were analyzed using the VI curves collected over three farms, covering multiple crops, including wheat, barley, and potato crops. The use of similarity computation based on dynamic time warping and interpolated convolution, in addition to the consideration of sample correlation, resulted in significant accuracy improvement as compared to the baseline approaches.","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":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892550","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":"Extending InSAR2InSAR to Sentinel-1 Data","authors":"Carla Geara;Colette Gelas;Louis de Vitry;Elise Colin;Florence Tupin","doi":"10.1109/LGRS.2025.3558363","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3558363","url":null,"abstract":"Interferometric synthetic aperture radar (SAR) parameters’ estimation is a very important and challenging problem. The InSAR2InSAR method previously proposed is one of the few self-supervised methods which aims to estimate InSAR parameters. This method has proven to outperform state-of-the-art methods on simulated synthetic data. However, it has to be extended on real data. In this letter, we demonstrate that Sentinel-1 images acquired in the interferometric wide (IW) swath mode possess the necessary properties to train and apply InSAR2InSAR effectively. In this letter, we demonstrate the ability of InSAR2InSAR to process across-track Sentinel-1 interferometric images with state-of-the-art performances.","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":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143852461","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}