IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing最新文献

{"title":"Sea Surface Height Inversion Model Based on Multimodal Deep Learning for the Fusion of Heterogeneous FY-3E GNSS-R Data","authors":"Yun Zhang;Ganyao Qin;Shuhu Yang;Yanling Han;Zhonghua Hong","doi":"10.1109/JSTARS.2025.3562741","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3562741","url":null,"abstract":"Sea surface height (SSH) is of great significance in oceanography and meteorology. Traditional physical altimetry methods based on delay–Doppler mapping (DDM) are subject to errors that are difficult to correct computationally. The current deep-learning-based SSH inversion techniques primarily relying on single-modal data are unable to fully leverage the rich feature information from global navigation satellite system reflectometry (GNSS-R) remote sensing data, therefore limiting the potential accuracy improvement. This study proposes a physics-informed multimodal deep-learning framework, physical-informed multimodal heterogeneous altimetry network (PIMFA-Net), to fuse heterogeneous spaceborne GNSS-R data to retrieve SSH. The GNSS-R data are acquired from the GNOS II instrument onboard the Fengyun-3E satellite, which can receive reflected signals from both global positioning system (GPS) and BeiDou navigation satellite system (BDS). GNSS-R parameters are used to construct the PIMFA-Net, which includes cropped DDM images, signal parameters, and system parameters in combination with environmental parameters (wind speed and convective rain rate from the European Centre for Medium-Range Weather Forecast, and SSH derived from physical altimetry models). The global sea surface dataset Danmarks Tekniske Universitet 2018 is used as ground truth for model training and evaluation. Data from 1 to 31 July 2022 are used to train PIMFA-Net, while data from August to October 2022 are used to evaluate the general ability of PIMFA-Net. Results demonstrate that the PIMFA-Net not only improves the accuracy and generalization by integrating heterogeneous data sources but also achieves all-weather, all-day, and wide-area SSH inversion with a precision of less than 40 cm for both GPS and BDS signals. This outcome holds significant potential for applications in marine ecological security monitoring and research.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11979-11995"},"PeriodicalIF":4.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974576","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084792","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":"Improvement for UAV Urban SAR Tomography Based on Cylindrical Wave Model With Elevation Constraints","authors":"Rui Guo;Zishuai Ren;Yuxin Gao;Lianhuan Wei;Yuxiao Qin;Gang Xu","doi":"10.1109/JSTARS.2025.3563718","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563718","url":null,"abstract":"Synthetic aperture radar (SAR) tomography (TomoSAR) technology can solve the layover problem in SAR images and achieve three-dimensional (3D) imaging. Unmanned aerial vehicle (UAV) TomoSAR has developed rapidly in the field of urban surveying and mapping in recent years due to its advantages of flexible deployment, low cost, and ease of large-scale application. However, the low flight altitude of UAVs and the need to reduce the number of observations pose challenges to the classical TomoSAR imaging model based on plane wave geometry. To improve the 3D imaging quality of UAV TomoSAR in urban areas, this article proposes a 3D imaging method based on a cylindrical wave geometry model with refined elevation constraints. This method reconstructs the 3D imaging model to conform to the near-field principle. Meanwhile, the constraint range of the elevation solution space is determined through the proposed layover area labeling under the cylindrical wave model. The experiments with simulation and real data show that the proposed method can accurately recover building structures and exhibits commendable performance in deformation correction and ambiguity suppression.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11401-11415"},"PeriodicalIF":4.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974692","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073117","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":"TFA-Net: A Temporal Feature Aggregation Framework for Tropical Cyclone Intensity Estimation From Satellite Images","authors":"Zhitao Zhao;Zheng Zhang;Qiao Wang;Linli Cui;Ping Tang","doi":"10.1109/JSTARS.2025.3563472","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563472","url":null,"abstract":"Deep learning models have significantly advanced tropical cyclone (TC) intensity estimation from satellite images. While the potential of temporal information for improving TC intensity prediction is recognized, existing methods have not fully leveraged this aspect. To address this, we propose TFA-Net, a deep-learning temporal feature aggregation framework based on a dual-branch Transformer, for TC intensity estimation. To enrich the available data features, our TFA-Net utilizes both image and historical intensity sequences. To enhance feature exchange within and between these sequences, the framework employs global attention tokens and cross-attention modules. Furthermore, to adaptively focus on different temporal lengths, a gated feature fusion module combines models with varying input sequence lengths, allowing TFA-Net to consider both long-term and short-term TC features for improved prediction. Experimental results show that the estimation performance is improved through our model's in-depth consideration of the temporal continuity of TC. Our model achieved a root-mean-square error of 7.21 knots on the TCIR dataset, demonstrating the Transformer's potential for real-time TC intensity estimation by effectively extracting time-series information from satellite imagery.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"12008-12023"},"PeriodicalIF":4.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974485","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084804","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":"Benchmarking Deep Learning for Wetland Mapping in Denmark Using Remote Sensing Data","authors":"Muhammad Rizwan Asif","doi":"10.1109/JSTARS.2025.3563951","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563951","url":null,"abstract":"Wetlands are critical ecosystems providing numerous ecological services, yet they face significant threats from human activities and climate change. Therefore, accurate mapping and monitoring of wetlands are crucial for formulating effective conservation and restoration strategies. While remote sensing combined with deep learning (DL) offers a promising solution, inconsistencies in wetland classification systems—where different regions define wetland types based on their policy frameworks and conservation priorities—limit the applicability of these models. Such inconsistencies make it difficult to assess their limitations in different contexts. Notably, no study has yet leveraged DL for mapping wetlands within Denmark's unique wetland classification system, as defined by the Danish nature conservation framework. Therefore, this article presents a comprehensive benchmark analysis of several DL models for wetland classification in Denmark. We utilize publicly available high-resolution multispectral aerial imagery and digital elevation models (DEMs) and evaluate the performance of three well-established network architectures: Fully Convolutional Network, U-Net, and DeepLabV3. We also assess the impact of incorporating near-infrared and DEM data in addition to traditional optical imagery. The results show that DeepLabV3 model outperforms other models, particularly when additional data layers are included, achieving the highest overall accuracy and F-measure score. Our findings also reveal that while DL models can effectively classify certain wetlands, challenges remain in distinguishing wetland with ecological similarities and in handling noisy labels. This benchmark provides a foundation for future work aimed at improving DL methods for wetland mapping in Denmark.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11953-11962"},"PeriodicalIF":4.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10975079","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084783","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":"Efficient Side-Tuning for Remote Sensing: A Low-Memory Fine-Tuning Framework","authors":"Haichen Yu;Wenxin Yin;Hanbo Bi;Chongyang Li;Yingchao Feng;Wenhui Diao;Xian Sun","doi":"10.1109/JSTARS.2025.3563641","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563641","url":null,"abstract":"Fine-tuning pretrained models for remote sensing tasks often demands substantial computational resources. To reduce memory requirements and training costs, this article proposes a low-memory fine-tuning framework, called efficient side-tuning (EST), for remote sensing downstream tasks. EST attaches a parallel network to the backbone of the model, and only fine-tunes the parameters of the parallel network during the training phase. The proposed EST Block is the main component of the parallel network, which uses the multichannel adapter fusion module, gate layer and depthwise convolution to achieve feature selection and enhancement effects. In the evaluation, on six remote sensing datasets including object detection and semantic segmentation, EST achieved SOTA performance results using only less than 40<inline-formula><tex-math>$%$</tex-math></inline-formula> of the memory expenditure of full fine-tuning, which is better than all current parameter efficient fine-tuning methods. In addition, experiments on backbones of various sizes and classes show that the generalizability of EST is also reliable. EST thus offers a highly efficient and effective approach for efficient transfer learning in remote sensing, unlocking new possibilities for advanced remote sensing applications.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11908-11925"},"PeriodicalIF":4.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974700","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144084803","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":"Study on Coherent Speckle Noise Suppression in the SAR Images Based on Regional Division","authors":"Xingdong Wang;Yudong Wang;Suwei Li","doi":"10.1109/JSTARS.2025.3563613","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563613","url":null,"abstract":"Polar snowmelt detection is of great importance for the study of global climate change, and synthetic aperture radar (SAR) images have been widely used for polar snowmelt detection because of its ability to provide round-the-clock, all-weather snowmelt detection. However, conventional snowmelt detection algorithms based on the SAR images have images that are susceptible to interference from coherent speckle noise, which leads to the problems of false pixel and missed change detection. To solve the above-mentioned problems, this article proposed a coherent speckle noise suppression algorithm for the SAR images based on the measure of heterogeneity. That is, the SAR images are divided into homogeneous regions, edge regions, and isolated strong scattering regions by the measure of heterogeneity, and different construction algorithms are used for different regions, which was applied to the Larsen C ice shelf. The results showed that the construction algorithm in this article achieved better results in noise suppression, structure preservation and detail retention, and the comprehensive performance was better in the homogeneous regions and edge regions, which could reduce the false alarm rate and leakage rate, and provided algorithmic support for the study of polar snowmelt detection.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11703-11715"},"PeriodicalIF":4.7,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974644","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073123","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":"High-Resolution Imaging Method for Vehicle-Mounted FMCW Shallow Ice Radar","authors":"Binbin Li;Bo Zhao;Xuyi Yuan;Jingxue Guo;Xiaojun Liu","doi":"10.1109/JSTARS.2025.3563254","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563254","url":null,"abstract":"The accumulation rate is a key parameter for calculating the surface mass balance of ice sheets and estimating sea level rise. Frequency-modulated continuous wave ice-sounding radar (FMCW-ISR) can be used to detect internal layers of ice sheets, and data of these layers are crucial for calculating the accumulation rate. However, during FMCW-ISR scanning, the same ice layer target may appear multiple times in the data matrix, leading to defocusing in the azimuth direction. In addition, FMCW-ISR systems are typically ultra-wideband, making it difficult to maintain absolute signal linearity throughout the entire sweep period. This nonlinear modulation results in high sidelobe levels, complicating the interpretation of ice layer structures. To address these problems, this article proposes a high-resolution FMCW shallow ice radar imaging method that combines the range migration algorithm (RMA) with nonlinear phase estimation and correction techniques. The proposed method effectively improves azimuth focusing accuracy and reduces sidelobe levels in the range direction, thereby better preserving the clear structure of the internal layers of the ice sheets. Validation using both simulated and measured data demonstrates that the proposed method significantly improves imaging quality, thereby making the layered structure of the shallow ice sheet more distinct.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11512-11524"},"PeriodicalIF":4.7,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973099","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073118","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":"Reconstructing Gap-Free Daily Remote Sensing Reflectance in the Marginal Seas Using the DINEOF Method","authors":"Shuyan Lang;Yuxuan Jiang;Shengqiang Wang;Yongjun Jia;Yi Zhang","doi":"10.1109/JSTARS.2025.3563216","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563216","url":null,"abstract":"Ocean color remote sensing has provided extensive datasets of various bio-optical parameters, which are essential for studying marine biogeochemical processes and ecosystems. However, factors such as the clouding cover, sun glint, and wide sensor viewing angles often result in missing satellite data, which complicates near-real-time ocean monitoring and may introduce errors in time-series analyses due to limited data availability. Remote sensing reflectance <inline-formula><tex-math>$(R_{text{rs}}(lambda ))$</tex-math></inline-formula> constitutes the primary product in ocean color remote sensing, which serves as a source deriving for most bio-optical products. This study aims to reconstruct a daily gap-free <inline-formula><tex-math>$R_{text{rs}}(lambda )$</tex-math></inline-formula> dataset using the data interpolating empirical orthogonal functions method, applied on moderate resolution imaging spectroradiometer (MODIS)-Aqua daily time-series <inline-formula><tex-math>$R_{text{rs}}(lambda )$</tex-math></inline-formula> product, focusing on the Eastern China Seas as a case study. The evaluation demonstrates the reconstructed <inline-formula><tex-math>$R_{text{rs}}(lambda )$</tex-math></inline-formula> data is both feasible and accurate in terms of magnitude and spectral shape. The reconstructed <inline-formula><tex-math>$R_{text{rs}}(lambda )$</tex-math></inline-formula> data were then utilized to derive secondary ocean color products, including the diffuse attenuation coefficient at 490 nm for downwelling irradiance and chlorophyll-<italic>a</i> concentration, which revealed high similarity and accuracy versus those calculated from the original MODIS <inline-formula><tex-math>$R_{text{rs}}(lambda )$</tex-math></inline-formula> data. These findings suggest that the reconstructed daily <inline-formula><tex-math>$R_{text{rs}}(lambda )$</tex-math></inline-formula> data can effectively serve as foundational data for calculating other ocean color satellite products. These gap-free ocean color satellite products produced in this study can be further utilized in oceanographic studies and as inputs for marine ecosystem models to predict marine ecological environments. Future research will focus on <inline-formula><tex-math>$R_{text{rs}}(lambda )$</tex-math></inline-formula> reconstruction using multiple ocean color sensor data and extending the approach to other water regions.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11588-11598"},"PeriodicalIF":4.7,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10973136","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073122","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":"DiffuSAR: Frequency Domain-Aware Diffusion Model for SAR Image Generation","authors":"Zilu Ying;Wenyu Ke;Yikui Zhai;Zhihao Long;Jianhong Zhou;Hufei Zhu;C. L. Philip Chen","doi":"10.1109/JSTARS.2025.3563798","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563798","url":null,"abstract":"In recent years, deep learning-based synthetic aperture radar (SAR) image detection, recognition, and segmentation models achieve remarkable accuracy when trained on large amounts of SAR image samples. However, the acquisition of SAR images tends to be costly. A practical approach to address this issue involves the use of artificially generated training samples to supplement the dataset. Current SAR image generation methods based on generative adversarial networks have issues with generation fidelity and are challenge to converge. Moreover, most of these methods only consider the spatial domain of SAR images without exploring the characteristics of their frequency domain. To tackle the aforementioned problems, we proposed a lightweight frequency domain-aware SAR image generation model based on the denoising diffusion probabilistic model. The proposed generative model is capable of producing highly realistic artificial SAR image samples while converging stably. Meanwhile, our research reveals that high-frequency (HF) components of SAR images play a crucial role in the generation process, and a frequency adjustment module (FAM) based on the fast Fourier transform is implemented in our generation model to prevent interference of HF components by low-frequency components. Tests on the MSTAR dataset highlight our model's advantages in both generation quality and parameter efficiency compared to other cutting-edge image generation models. An additional ablation study also confirms the effectiveness of our proposed FAM, which reduces the Fréchet inception distance by 2.85%, confirming our hypothesis that HF components are more crucial to SAR image generation.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11851-11866"},"PeriodicalIF":4.7,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974573","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144073116","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":"C-Band Radar-Based Improved Snow Depth Estimation (C-RISE) in the Indian Western Himalayas and Colorado Rocky Mountains","authors":"R. Chandra Prabha;Srinivasarao Tanniru;RAAJ Ramsankaran","doi":"10.1109/JSTARS.2025.3563462","DOIUrl":"https://doi.org/10.1109/JSTARS.2025.3563462","url":null,"abstract":"Monitoring snow depth (SD) in mountainous regions is essential for water resource management, climate studies, and disaster predictions. Synthetic aperture radar (SAR)-based remote sensing, with its high spatial resolution and penetration capability, is more suited for such areas. Sentinel-1 backscatter-based SD estimation currently provides the only SAR-derived global SD product. However, this method is still in an early stage of development, with limited understanding of the underlying mechanisms, minimal region-specific evaluations, and lack of consideration of diurnal, seasonal, and regional effects on the backscatter-SD relationship. This study introduces C-band radar-based improved snow depth estimation (C-RISE) to improve Sentinel-1-based SD estimation by integrating diurnal, seasonal, and regional factors, along with auxiliary variables like snow cover duration (SCD) and elevation. Implemented on Google Earth Engine (GEE), the approach is applied to two contrasting regions: the Indian Western Himalayas (IWH), characterized by deep snowpacks, and the Colorado Rocky Mountains (CRM), with shallower snowpacks. The results demonstrate enhanced model accuracy when incorporating these factors. For IWH, the model's performance improved by 9%, achieving an MAE of 77.3 cm and R of 0.7. In CRM, the model's performance primarily benefited from regional zoning, leading to an 8% improvement with MAE of 19.6 cm and R of 0.8. Compared to the Sentinel-1 C-Snow product, the refined models reduced MAE by 17% in IWH and 51% in CRM. These findings advance the understanding of C-band backscatter-based SD estimation, particularly for less-studied regions such as IWH, and demonstrate its potential for improving SD monitoring globally.","PeriodicalId":13116,"journal":{"name":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","volume":"18 ","pages":"11787-11802"},"PeriodicalIF":4.7,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10974466","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144072952","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}