Bo Zhang;Yaxiong Chen;Weichong Dang;Shengwu Xiong;Xiaoqiang Lu
{"title":"A Spatial and Semantic Alignment Fusion Network for SeaLand Port Segmentation","authors":"Bo Zhang;Yaxiong Chen;Weichong Dang;Shengwu Xiong;Xiaoqiang Lu","doi":"10.1109/JSTARS.2025.3544317","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544317","url":null,"abstract":"To address the issues of complex backgrounds and poor segmentation performance for small ship objects in sea–land port areas, we propose a sea–land port segmentation algorithm based on spatial and semantic alignment fusion. The algorithm utilizes parallel Transformer–convolutional-neural-network (CNN) dual-branch encoders for feature extraction and introduces two modules: spatial alignment fusion and semantic alignment fusion. By the collaborative work of four submodules: spatial feature alignment, spatial feature fusion, semantic feature alignment, and semantic feature fusion, the dual-branch network achieves feature alignment and fusion. The spatial and semantic alignment fusion module efficiently combines local details extracted by the Transformer–CNN dual-branch with global semantic information. This enhances the model's ability to understand and analyze complex sea–land port scenes, effectively addressing low segmentation accuracy of port ship objects and the overlapping and occlusion of port objects. Experimental results demonstrate that the proposed sea–land port segmentation algorithm achieves optimal segmentation accuracy on two publicly available sea–land port segmentation datasets, ISDSD and HRSC2016-SL.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7420-7435"},"PeriodicalIF":4.7,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10897902","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143655070","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}
{"title":"Self-Correlation Network With Triple Contrastive Learning for Hyperspectral Image Classification With Noisy Labels","authors":"Kwabena Sarpong;Mohammad Awrangjeb;Md. Saiful Islam;Islam Helmy","doi":"10.1109/JSTARS.2025.3543764","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3543764","url":null,"abstract":"Data quality is essential for training deep learning models, and recently, the challenge of noisy labels in hyperspectral image (HSI) classification has attracted considerable attention. However, current deep learning approaches typically employ conventional convolution methods that treat all spatial frequency components uniformly, neglecting the exploration of feature-dependent knowledge, significantly affecting learning with noisy labels. Consequently, these methods perform poorly in scenarios with a high noisy-to-clean sample ratio. To address the above drawback, we propose an end-to-end self-correlation framework with triple contrastive learning (SCTCL) for HSI classification with noisy labels. Our SCTCL harnesses maximizing the similarities of the positive pairs of the HSI features by defining cluster-, instance-, and structure-level learnings representing a contrastive loss. First, we construct HSI data pairs through weak and strong data augmentations. Then, we propose a cross-convolutional with a self-correlation network (ConvSCNet) module to extract spatial-spectral feature representation from all augmented samples. Subsequently, we employ instance- and cluster-level contrastive learnings to project the feature matrix in row and column spaces to minimize negative and maximize positive pairs. Furthermore, we incorporate structure-level representation learning to address inconsistencies across different projections. By doing so, we mitigate the classifier from overfitting to noisy labels. We conducted experiments on five publicly available HSI datasets with various noisy-to-clean sample ratios. We consider both symmetric and asymmetric noises. The classification results prove that the proposed SCTCL performs excellently in training HSI with a limited clean sample compared to the state-of-the-art methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7166-7188"},"PeriodicalIF":4.7,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10899862","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143637850","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}
Zhiyuan Xue;Liang Li;Yijiang Nan;Fei Zou;Zongxiang Xu;Tianyuan Yang;Robert Wang
{"title":"A Sinogram Decimation Fast Back-Projection Algorithm for Strip-Map SAR Imaging","authors":"Zhiyuan Xue;Liang Li;Yijiang Nan;Fei Zou;Zongxiang Xu;Tianyuan Yang;Robert Wang","doi":"10.1109/JSTARS.2025.3544259","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544259","url":null,"abstract":"In this article, a novel sinogram decimation fast back-projection (SD-FBP) algorithm for strip-map synthetic aperture radar (SAR) imaging is proposed. We first review the back-projection (BP) and the fast factorized BP (FFBP) algorithms, then analyze the cause of the FFBP imaging degradation theoretically based on the combination of SAR imaging and the sinogram concept of computed tomography, illustrating that the degradation is much more severe for strip-map mode. Based on the SAR sinogram, the SD-FBP algorithm is proposed to mitigate the FFBP degradation for strip-map SAR imaging. The complexity of the SD-FBP is analyzed and compared with that of the FFBP and the Cartesian factorized BP (CFBP). The superiority of the SD-FBP algorithm is validated using the simulation and real spaceborne strip-map SAR data, e.g., Sentinel-1, Gaofen-3, and LuTan-1. The results show that the SD-FBP can tackle the FFBP imaging degradation for strip-map SAR, and runs faster than the FFBP and the CFBP.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6790-6805"},"PeriodicalIF":4.7,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10897897","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143601890","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}
{"title":"Adaptive Fast Refocusing for Ship Targets With Complex Motion in SAR Images","authors":"Xinqi Xu;Xiangguang Leng;Zhongzhen Sun;Xiangdong Tan;Kefeng Ji;Gangyao Kuang","doi":"10.1109/JSTARS.2025.3544248","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544248","url":null,"abstract":"Synthetic aperture radar (SAR) enables all-weather, round-the-clock monitoring of the oceans. Ships are subjected to complex movements by sea winds and waves while traveling, which can cause them to appear heavily defocusing in SAR images. This article introduces an adaptive fast refocusing algorithm (AFRA) designed to refocus defocused ships. This algorithm can adaptively adjust algorithm parameters based on SAR images from different SAR platforms, thereby more accurately determining the optimal rotation interval (ORI), reducing computational cost, and achieving adaptive fast refocusing. First, each azimuth line is represented as a signal with multicomponent linear frequency modulation signal. Second, by using the parameters of the SAR platform, the relationship between azimuth velocity and the optimal rotation order (ORO) is calculated, thereby determining the ORI. Third, the ORO within the ORI is computed using the fractional autocorrelation. Then, each azimuth line is refocused using fractional Fourier transform. Finally, the refocused image is obtained by substituting the raw azimuth lines for the refocused ones. Results from the experiments reveal that the method put forward can successfully counteract the defocusing produced by complex motion. Compared to state-of-the-art leading refocusing algorithm, AFRA takes only approximately 15% the time required to process Hisea-1 data with long synthetic aperture time, 27% of the time required to process Gaofen-3 data with short synthetic aperture time, and still has excellent refocusing effect.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"8559-8572"},"PeriodicalIF":4.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10897797","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143761387","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}
{"title":"Retrieval of Sea Surface Wind Speed From CYGNSS Data in Tropical Cyclone Conditions Using Physics-Guided Artificial Neural Network and Storm-Centric Coordinate Information","authors":"Tong Jia;Jing Xu;Fuzhong Weng;Feixiong Huang","doi":"10.1109/JSTARS.2025.3544200","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544200","url":null,"abstract":"A novel artificial neural network (ANN) model is introduced for the retrieval of tropical cyclone (TC) sea surface wind speed from the Cyclone Global Navigation Satellite System (CYGNSS) Level 1 data. WindSat TC wind data serves as the “truth” information for the ANN training. Compared to conventional machine learning approaches, the proposed model incorporates specialized information including the storm-centric coordinate information of CYGNSS observations and physical-guided scattering azimuth angle. In addition, a feature selection process is employed, utilizing both XGBoost regressor and Pearson correlation coefficient, to identify the most pertinent input variables for wind speed retrieval. The results show that the proposed model with storm-centric coordinate information and first-order cosine form of scattering azimuth angle as additional inputs demonstrates good retrieval performance. It achieves a bias of -0.59 m/s and an root mean square error (RMSE) of 3.43 m/s, corresponding to a decrease of 60.93% and 20.05% compared to the current CYGNSS baseline wind products for young seas with limited fetch (YSLF). Especially above 35 m/s, the proposed model outperforms the CYGNSS YSLF product, illustrating its advantages under high wind speeds. Moreover, the effects of two special inputs on the model performance are explored. It is found that the RMSEs are reduced by about 25.43% and 9.50%, respectively, after incorporating the two specific inputs, suggesting that considering TC-related inputs is more effective than the physics-guided initialization in improving model performance. Our retrieval results provide valuable guidance for improving the use of GNSS-R data for near real-time retrieval of TC winds.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6746-6759"},"PeriodicalIF":4.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10897821","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143594290","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}
Leiyang Zhong;Wenhao Guo;Jiayi Zheng;Liyue Yan;Jizhe Xia;Dejin Zhang;Qingquan Li
{"title":"HPAN: Hierarchical Part-Aware Network for Fine-Grained Segmentation of Street View Imagery","authors":"Leiyang Zhong;Wenhao Guo;Jiayi Zheng;Liyue Yan;Jizhe Xia;Dejin Zhang;Qingquan Li","doi":"10.1109/JSTARS.2025.3544344","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3544344","url":null,"abstract":"Street view imagery (SVI) has become a valuable geospatial data source for urban analysis, offering rich information about urban environments from a human-centric perspective. However, existing segmentation methods face significant challenges due to the inherent complexities of SVI, including scale variations, occlusions, and diverse semantic hierarchies. Drawing inspiration from the hierarchical nature of human visual cognition, this study proposes the hierarchical part-aware network (HPAN) to address these challenges in the fine-grained segmentation of SVI. The HPAN framework integrates four key components: (1) a hierarchical consistency learning module (HCLM), which ensures consistency across different levels of segmentation through novel loss functions; (2) a topology-aware graph matching module (TGMM), designed to model spatial relationships between object parts; (3) an edge-guided feature enhancement module (EFEM), which incorporates fine-grained edge information; and (4) a multilevel joint attention module (MLJAM), which adaptively fuses global scene semantics with local object details. Extensive experiments conducted on the cityscapes panoptic parts dataset demonstrate that HPAN outperforms existing methods across multiple panoptic quality metrics, particularly excelling in part-level segmentation tasks. Further evaluations on the mapillary vistas dataset and the cityscapes dataset validate HPAN's robust semantic segmentation performance across diverse street scenes. Generalization tests on different SVI sources, including challenging scenarios, such as low-light conditions and occluded environments, highlight the model's strong adaptability and effectiveness.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7794-7810"},"PeriodicalIF":4.7,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10897804","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706705","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}
{"title":"Change Detection Based on Image Standardization and Improved Residual Network for Single-Polarization SAR Images","authors":"Mengmeng Wang;Jixian Zhang;Guoman Huang;Lijun Lu;Fenfen Hua","doi":"10.1109/JSTARS.2025.3543591","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3543591","url":null,"abstract":"Deep-learning-based change detection (CD) methods have become an important means of synthetic aperture radar (SAR) images to identify changes. To generate the accurate change map, these methods typically require a high-quality training set. As a frequently adopted way to extract training samples, preclassification has a crucial effect on CD precision. However, preclassification images are often generated using intensity-based CD algorithms that rely on SAR magnitude images without considering phase information. In addition, the statistical characteristics of SAR images are seldom considered. When designing the artificial intelligence CD models, it is expected to account for speckle noise inherent in SAR images while detecting more small-scale changes to obtain a high-accuracy CD map. Thus, we introduce a new CD approach for single-polarization SAR images based on image standardization and the improved residual network (I-ResNet). First, a strategy of fusing the coherent and noncoherent intensity changes for preclassification image generation is introduced to retain large-scale and small-scale changes. The noncoherent change acquisition part of the strategy involves an image standardization algorithm, which is derived from the Gaussian speckle model and is especially effective for images with different statistical characteristics. Then, the I-ResNet model combining the dual-tree complex wavelet transform with residual learning is presented, which aims at taking advantage of the wavelet transform in reducing the influence of speckle noise and ResNet in easy training and preservation of information integrity. Finally, experiments with different SAR image pairs demonstrate that the proposed method produces better CD maps than other related methods.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7756-7768"},"PeriodicalIF":4.7,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892075","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667521","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}
{"title":"CSPPNet: A Convolution and State-Space-Based Photovoltaic Panel Extraction Network Using Gaofen-2 High-Resolution Imagery","authors":"Wenqing Liu;Hongtao Huo;Luyan Ji;Yongchao Zhao;Xiaowen Liu;Jialei Xie","doi":"10.1109/JSTARS.2025.3543490","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3543490","url":null,"abstract":"With the rapid development of photovoltaic (PV) industry, it is crucial to accurately identify PV panels using remote sensing data. However, the existing methods still face problems, such as difficulty in distinguishing PV panels from easily confused ground objects, such as dark buildings, roads, and black plastic, lacking the analysis of the directional characteristics, and inadequate capturing the global dependencies. To address these challenges, a convolution and state-space-based photovoltaic panel extraction network (CSPPNet) is proposed. Specifically, we construct a PV panel index based on visible and near-infrared bands to improve the separability of the PV panels from those easily confused ground objects. Second, considering the unique horizontal characteristics exhibited by the PV panels in remote sensing images, a south-facing orientation prior module is designed to enhance the horizontal features and improve our network in capturing horizontal objects. Finally, the encoder of our network adopts a parallel structure of depthwise separable convolution and state-space module to capture local detailed features and global semantic features of PV panels layer by layer. Furthermore, we build a high-quality dataset [named Photovoltaic Panels in the Eastern and Western Regions of China (PPEWRC)] containing four bands ranging from visible to near-infrared wavelength based on Gaofen-2 satellite images. The experimental results show that our proposed CSPPNet effectively reduces the misjudgment of PV panels, with high completeness and clear edges. The intersection over union, precision, recall, and <italic>F</i>1-score can reach 77.37%, 87.42%, 85.11%, and 86.98%, respectively, on the PPEWRC dataset. Ablation experiments validate the effectiveness of each module and fusion process, providing insights into the sustainable utilization of renewable energy.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7644-7661"},"PeriodicalIF":4.7,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892037","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143654944","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}
{"title":"Subpixel Target Detection in Hyperspectral Imaging Using a Deep Neural Network With a Variable Stepsize Gradient Descent Method","authors":"Edisanter Lo;Damien B. Josset","doi":"10.1109/JSTARS.2025.3543680","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3543680","url":null,"abstract":"The main difficulty in using artificial neural networks, which are designed for classification, to detect a rare subpixel target in hyperspectral imaging is that there is typically only one actual target pixel available for training the neural networks, which require a large sample of actual target pixels to train the target class. The first current detection algorithm for subpixel target detection is based on a single-layer neural network and gradient descent method with variable stepsize to solve the optimization problem, and the second one is based on a multilayer neural network and gradient descent method with variable stepsize. The objective of this article is to extend the current algorithms by developing a detection algorithm for subpixel target detection using a deep neural network with two hidden layers and the gradient descent method with variable stepsize instead of fixed stepsize. Implementing the gradient descent method with variable stepsize can reduce computational cost by improving convergence and speed of convergence. The decision boundary is also analyzed and is linear for the single-layer neural network and nonlinear for the multilayer neural network and deep neural neural network with two hidden layers. Experimental results from two hyperspectral images, one with simulated subpixel target pixels for training and validating the algorithm and the other with simulated subpixel target pixels for training and actual subpixel target pixels for validation, have shown that the proposed algorithm can perform better than conventional algorithms, which are based on generalized likelihood ratio test.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"7707-7727"},"PeriodicalIF":4.7,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10892630","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143667474","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}
{"title":"Deep Learning-Based Interpolation for Ground Penetrating Radar Data Reconstruction","authors":"Ziyang Zhou;Meijia Huang;Hong Xu;Xinyu Yang;Yinpeng Li;Zhuo Jia","doi":"10.1109/JSTARS.2025.3543256","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3543256","url":null,"abstract":"Ground Penetrating Radar (GPR), with its high resolution and real-time monitoring capabilities, is widely used in fields such as underground structure detection, archaeological excavation, environmental monitoring, and engineering surveying. However, the complexity of the subsurface, such as geological heterogeneity and inhomogeneity, can cause signal attenuation or incomplete reflection. In addition, external factors like electromagnetic interference, temperature fluctuations, or other noise can result in data loss or anomalies. To address these challenges, this article proposes a deep learning-based interpolation method for GPR data. Convolutional Neural Networks (CNNs) are used to learn signal patterns from large datasets, enabling the model to predict missing data and restore the integrity and continuity of the GPR data. Deep learning models also capture complex nonlinear features in GPR data, identifying underlying patterns and correlations. In noisy or high-reflection environments, these methods offer more precise interpolation, significantly improving data quality. Experiments on both synthetic and real-world data show that the deep learning method effectively recovers GPR data features, enhances data continuity and integrity, and reduces interpolation errors. The method exhibits strong adaptability and high-precision performance, making it effective in complex underground structures and varying environments. Whether with synthetic or real-world data, deep learning provides a reliable solution for GPR data processing.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"6329-6335"},"PeriodicalIF":4.7,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10891706","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143564203","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}