IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society最新文献_第10页

Physically Guided Deep Unsupervised Inversion for 1-D Magnetotelluric Models

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-13 DOI: 10.1109/LGRS.2025.3528767

Paul Goyes-Peñafiel;Umair Bin Waheed;Henry Arguello

{"title":"Physically Guided Deep Unsupervised Inversion for 1-D Magnetotelluric Models","authors":"Paul Goyes-Peñafiel;Umair Bin Waheed;Henry Arguello","doi":"10.1109/LGRS.2025.3528767","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528767","url":null,"abstract":"The global demand for unconventional energy sources such as geothermal energy and white hydrogen requires new exploration techniques for precise subsurface structure characterization and potential reservoir identification. The magnetotelluric (MT) method is crucial for these tasks, providing critical information on the distribution of subsurface electrical resistivity at depths ranging from hundreds to thousands of meters. However, traditional iterative algorithm-based inversion methods require the adjustment of multiple parameters, demanding time-consuming and exhaustive tuning processes to achieve proper cost function minimization. Recent advances have incorporated deep learning algorithms for MT inversion, primarily based on supervised learning, and large labeled datasets are needed for training. This work utilizes TensorFlow operations to create a differentiable forward MT operator, leveraging its automatic differentiation capability. Moreover, instead of solving for the subsurface model directly, as classical algorithms perform, this letter presents a new deep unsupervised inversion algorithm guided by physics to estimate 1-D MT models. Instead of using datasets with the observed data and their respective model as labels during training, our method employs a differentiable modeling operator that physically guides the cost function minimization, making the proposed method solely dependent on observed data. Therefore, the optimization algorithm updates the network weights to minimize the data misfit. We test the proposed method with field and synthetic data at different acquisition frequencies, demonstrating that the resistivity models obtained are more accurate than those calculated using other techniques. Our implementation is available at <uri>https://github.com/PAULGOYES/MT_guided1DInversion.git</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":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105572","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}

引用次数: 0

Surface Suspended Particulate Matter Flux in the Northern Gulf of Mexico From Satellite Observations

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-13 DOI: 10.1109/LGRS.2025.3528833

Wei Shi;Menghua Wang;Bulusu Subrahmanyam

{"title":"Surface Suspended Particulate Matter Flux in the Northern Gulf of Mexico From Satellite Observations","authors":"Wei Shi;Menghua Wang;Bulusu Subrahmanyam","doi":"10.1109/LGRS.2025.3528833","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528833","url":null,"abstract":"The satellite observations of suspended particulate matter (SPM) from the Visible Infrared Imaging Radiometer Suite (VIIRS) and ocean currents from satellite altimetry merged product are used to demonstrate the capability to monitor the SPM flux and characterize and quantify the change of the SPM flux between 2018 and 2023 in the northern Gulf of Mexico (GOM). The sediment was transported out of both the northern GOM and Mississippi River Estuary regions with a peak in the spring season. The zonal alongshore SPM flux dominates the SPM flux, while the meridional SPM flux off the northern GOM is insignificant. In fact, the alongshore SPM flux becomes eastward in summer, while it is westward in the other seasons. Significantly, different SPM fluxes in the northern GOM were found in the 2019 flood year and 2018 drought year. In Mississippi River flood in 2019, the westward zonal SPM flux off Mississippi River Estuary region doubled, and the net SPM flux reached ~100 kg<inline-formula> <tex-math>$cdot~{mathrm {m}}^{-1}cdot~{mathrm {s}}^{-1}$ </tex-math></inline-formula>. On the contrary, the SPM flux in the spring 2018 was significantly weaker than that in the normal year. With combination of gap-free satellite ocean color and satellite altimetry ocean current observations, the SPM flux computation can also be extended to the other world major river estuarine and coastal regions to study the sediment dynamics and further address the ocean physical, biogeochemical, and geological processes in these regions.","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":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105588","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}

引用次数: 0

SAIR-YOLO: An Improved YOLOv8 Network for Sea–Air Background IR Small-Object Detection

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-13 DOI: 10.1109/LGRS.2025.3528947

Yue Yang;Haoyan Wang;Peijie Pang

{"title":"SAIR-YOLO: An Improved YOLOv8 Network for Sea–Air Background IR Small-Object Detection","authors":"Yue Yang;Haoyan Wang;Peijie Pang","doi":"10.1109/LGRS.2025.3528947","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528947","url":null,"abstract":"The performance of IR small-object detection algorithms determines the detection capability and reliability of electrooptic tracking devices in complex environments. For IR images with sea-air backgrounds, reflections on surface waves increase background thermal noise that might occlude or alter small objects, complicating their detection. Additionally, clouds and waves complicate background texture, also reducing object detectability. In this study, we propose a new sea-air background IR (SAIR) detection model on the basis of the YOLOv8 network, called SAIR-YOLO, with three major improvements. First, an asymptotic multiscale feature fusion network gradually integrates different-scale features to mitigate the semantic gap between nonadjacent features while reducing the influence of sea-air background noise on feature representation. Second, a strengthened detection head discriminates irrelevant background features and focuses network attention on the objects. Third, a hybrid intersection-over-union (IoU) loss function improves detection performance, by focusing on shape similarities, and expands the effective regression range. Experimental results yield average SAIR-YOLO precisions of 80.2%, 84.4%, and 96.4% for three distinct datasets: a custom dataset and the SIRST-V2 and NUDT-SIRST publicly available datasets. This represents improvements of 7.0%, 4.9%, and 0.7%, respectively, on the YOLOv8 model.","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":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105589","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}

引用次数: 0

MPFNet: A Multiscale Phase Filtering Network for Interferometric SAR

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-13 DOI: 10.1109/LGRS.2025.3529083

Tao Sun;Zhen Wang;Zegang Ding;Jian Zhao;Kaiwen Zhu;Zhizhou Chen;Han Li

{"title":"MPFNet: A Multiscale Phase Filtering Network for Interferometric SAR","authors":"Tao Sun;Zhen Wang;Zegang Ding;Jian Zhao;Kaiwen Zhu;Zhizhou Chen;Han Li","doi":"10.1109/LGRS.2025.3529083","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3529083","url":null,"abstract":"Phase filtering is one of the core signal processing steps in interferometric synthetic aperture radar (InSAR). In recent years, InSAR phase filtering algorithms have evolved from traditional solutions to deep learning (DL) methods, significantly improving the processing efficiency. However, most DL-based phase filtering techniques originate from optical filtering methods, and these methods inevitably entail a tradeoff between noise suppression and detail preservation. To resolve this contradiction and fully take into account the characteristics of InSAR phase, a multiscale phase filtering network (MPFNet) based on multilook information fusion is proposed. First, the network adopts the multiscale structure to balance noise suppression and detail preservation, where the multiscale information is obtained through multilook interferograms of varying numbers of looks. Second, drawing on the mechanism of super-resolution, the network incorporates the residual feature distillation blocks (RFDBs) to restore the scale of interferograms. Finally, in response to the demand for complex phase filtering, a loss function based on cosine similarity is constructed, which avoids the discontinuity at <inline-formula> <tex-math>$pm pi $ </tex-math></inline-formula> affecting the filtering results. Computer simulation and experiments based on real InSAR data verified the effectiveness of the proposed method.","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":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105551","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}

引用次数: 0

A Dual-Branch Architecture for Adaptive Loss Multitask Mapping Based on AI4Arctic Sea Ice Challenge Dataset

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-13 DOI: 10.1109/LGRS.2025.3528621

Tiantian Feng;Yushi Yang;Peng Jiang;Xiaomin Liu;Lu An

{"title":"A Dual-Branch Architecture for Adaptive Loss Multitask Mapping Based on AI4Arctic Sea Ice Challenge Dataset","authors":"Tiantian Feng;Yushi Yang;Peng Jiang;Xiaomin Liu;Lu An","doi":"10.1109/LGRS.2025.3528621","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528621","url":null,"abstract":"Automated sea ice mapping is increasingly critical for global climate change research and Arctic shipping route planning. In this article, a dual-branch deep learning architecture with channel attention is proposed for multisource sea ice mapping, incorporating an adaptive multitask loss function weighting mechanism. The Ready-To-Train (RTT) AI4Arctic Sea Ice Challenge dataset is used to evaluate the performance of the proposed model. Experimental results demonstrate that compared with the current state-of-the-art model, the proposed model achieves a 1.03% improvement in the combined score. Specifically, the stage of development (SOD) <inline-formula> <tex-math>$F1$ </tex-math></inline-formula> score increases by 1.33%, the floe size (FLOE) <inline-formula> <tex-math>$F1$ </tex-math></inline-formula> score improves by 4.39%, whereas <inline-formula> <tex-math>$R^{2}$ </tex-math></inline-formula> for sea ice concentration (SIC) decreases by 1.35%. Finally, ablation experiments are conducted to validate the effectiveness of the proposed model and the adaptive multitask loss function.","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":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105679","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}

引用次数: 0

Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Global-to-Local Enhanced Channel Attention

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-13 DOI: 10.1109/LGRS.2025.3528442

Yuanyuan Dang;Hao Li;Bing Liu;Xianhe Zhang

{"title":"Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Global-to-Local Enhanced Channel Attention","authors":"Yuanyuan Dang;Hao Li;Bing Liu;Xianhe Zhang","doi":"10.1109/LGRS.2025.3528442","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528442","url":null,"abstract":"Cross-domain few-shot learning (FSL) has garnered significant attention in hyperspectral image classification (HSIC). However, current transfer learning (TL) approaches often struggle to effectively capture both global and local spectral-spatial dependencies, particularly under substantial domain shifts. To address these challenges, we propose a novel approach incorporating a spectral–spatial enhanced channel attention (SECA), which dynamically extracts multiscale global-to-local feature relationships. In addition, we introduce correlation alignment (CORAL) loss to explicitly reduce distributional discrepancies between domains, thus enhancing the cross-domain transferability of the model. To achieve a balance between efficiency and accuracy, the proposed framework integrates a lightweight inverted residual (IR) module. Experimental results on multiple benchmark hyperspectral image (HSI) datasets demonstrate that our method outperforms state-of-the-art techniques, offering superior classification accuracy, robustness, and domain adaptability.","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":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143360898","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}

引用次数: 0

Seismic Facies Interpretation Based on Super-Resolution Learning

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-13 DOI: 10.1109/LGRS.2025.3528958

Lingyun Guo;Guohe Li;Kuangfeng Gong

{"title":"Seismic Facies Interpretation Based on Super-Resolution Learning","authors":"Lingyun Guo;Guohe Li;Kuangfeng Gong","doi":"10.1109/LGRS.2025.3528958","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528958","url":null,"abstract":"With the advancement of computer technology, deep semantic segmentation-based automatic seismic interpretation has made significant progress. Semantic segmentation methods often require high-resolution (HR) input to achieve accurate classification results. However, seismic images often suffer from low-resolution (LR) quality. Reconstructing HR seismic images from LR ones and performing accurate automated seismic interpretation are crucial for assessing subsequent oil and gas reservoirs. In this letter, we propose a multitask seismic facies interpretation network based on super-resolution (SR) learning, named SR semantic segmentation network (SRSS-Net). It consists of two subnetwork branches: the SR Reconstruction branch, which effectively reconstructs seismic images from LR inputs, and the SR semantic segmentation branch, which interprets seismic facies at an SR level. We first introduce the basic theory of SR reconstruction, and then detail the network structure and optimization strategy of SRSS-Net. For implementation, we apply SRSS-Net to the Netherlands F3 Dataset and the New Zealand Parihaka Dataset. The results indicate that it achieves favorable seismic facies interpretation results even with LR inputs.","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":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105555","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}

引用次数: 0

PEGNet: An Enhanced Ship Detection Model for Dense Scenes and Multiscale Targets

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-10 DOI: 10.1109/LGRS.2025.3528221

Xiao Tang;Jingyu Zhang;Yunzhi Xia;Kun Cao;Chang Zhang

{"title":"PEGNet: An Enhanced Ship Detection Model for Dense Scenes and Multiscale Targets","authors":"Xiao Tang;Jingyu Zhang;Yunzhi Xia;Kun Cao;Chang Zhang","doi":"10.1109/LGRS.2025.3528221","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528221","url":null,"abstract":"In recent years, synthetic aperture radar (SAR) ship detection has seen significant improvements due to the rapid development of deep learning. However, when ship targets are densely arranged or exhibit multiscale variations, there are still issues such as significant differences in aspect ratios, resulting in false alarms, missed detections, and low detection accuracy. To overcome these challenges, this letter introduces a novel detection model, PEGNet, based on Faster R-CNN. First, to identify ship targets at different scales, the path aggregation feature pyramid network (PAFPN) was integrated into the feature fusion structure, which enhances the network’s feature representation and robustness. Second, efficient multiscale attention (EMA) was employed to strengthen detection accuracy by reducing noise interference and enhancing feature stability. Third, the guided anchoring region proposal network (GA-RPN) was introduced to produce anchors that more accurately reflect the actual positions and scales of targets, which improves localization precision and lowers the missed detection rate. The performance of PEGNet was tested on the SSDD and high-resolution SAR images dataset (HRSID) datasets, achieving mAP scores of 71.1% and 67.9%, respectively. Compared to the baseline network, this represents improvements of 2.5% and 7.6%. This result highlights the method’s superior performance compared to other 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":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143361099","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}

引用次数: 0

Fusion of Bi-Temporal Zhuhai-1 Orbita Hyperspectral and Multiseason Sentinel-2 Remote Sensing Imagery for Semantic Change Detection Based on Dual-Path 3DCNN-LSTM

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-10 DOI: 10.1109/LGRS.2025.3528020

Dawei Wen;Yaokun Jiang;Deng Chen;Yuan Tian

{"title":"Fusion of Bi-Temporal Zhuhai-1 Orbita Hyperspectral and Multiseason Sentinel-2 Remote Sensing Imagery for Semantic Change Detection Based on Dual-Path 3DCNN-LSTM","authors":"Dawei Wen;Yaokun Jiang;Deng Chen;Yuan Tian","doi":"10.1109/LGRS.2025.3528020","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528020","url":null,"abstract":"Remote sensing imagery plays a crucial role in monitoring Earth’s surface changes. With the advancement of computational power, convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been increasingly applied in change detection tasks. This letter proposes a novel approach, the dual-path 3-D convolutional RNN, which integrates 3-D CNNs and long short-term memory (3DCNN-LSTM) to fuse bi-temporal Zhuhai-1 Orbita hyperspectral and multiseason Sentinel-2 remote sensing imagery for semantic change detection. The proposed method extracts joint spectral-spatial features using 3-D convolution layers. Subsequently, bi-temporal features and multiseason features are spliced as one time sequence and fed to one LSTM modules (referred to as Str1). In another strategy (Str2), multisource features are fed separately to two LSTM modules and fused in fully connected layers. Experiments demonstrate that Str1 and Str2 achieve better performance than Siamese convolutional multiple-layers RNN (SiamCRNN). Str1 obtained the overall accuracy (OA) of 99.12%, kappa coefficient (KC) of 98.77%, and <inline-formula> <tex-math>${F}1$ </tex-math></inline-formula> score of 98.91%, achieving improvements of 4.81%, 6.7%, and 6.51%, respectively, compared to SiamCRNN.","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":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105568","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}

引用次数: 0

LSCMNet: A Lightweight Segmentation Network Based on Co-Occurring Matrix for Seismic Image

IEEE geoscience and remote sensing letters : a publication of the IEEE Geoscience and Remote Sensing Society Pub Date : 2025-01-10 DOI: 10.1109/LGRS.2025.3528036

Linqian Fan;Wenkai Lu;Yonghao Wang

{"title":"LSCMNet: A Lightweight Segmentation Network Based on Co-Occurring Matrix for Seismic Image","authors":"Linqian Fan;Wenkai Lu;Yonghao Wang","doi":"10.1109/LGRS.2025.3528036","DOIUrl":"https://doi.org/10.1109/LGRS.2025.3528036","url":null,"abstract":"Seismic image segmentation is important in geological interpretation. In recent years, numerous studies have leveraged texture features to analyze seismic images. However, traditional texture feature extraction methods are computationally intensive and cannot be updated through back-propagation. To address these challenges, we propose a model named lightweight segmentation network based on co-occurring matrix (LSCMNet). The overall architecture of LSCMNet employs an asymmetric encoder–decoder structure. The encoder mainly consists of a lightweight bottleneck that integrates the parametric co-occurrence matrix (CM) model based on the convolutional neural network (CNN) for segmentation (S-PCMCNN) module, along with channel shuffle and split for feature fusion, enhancing the model representational capacity. The pyramid decoder encompasses a spatial attention mechanism. This design significantly reduces the parameters while maintaining accuracy in seismic image segmentation. In the application of igneous rocks, an ablation experiment was conducted to validate the effectiveness of the S-PCMCNN module. Moreover, compared with other classical segmentation models, LSCMNet demonstrates superior segmentation accuracy in few-shot scenarios while having fewer parameters and floating point operations (FLOPs).","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":"2025-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143105573","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}

引用次数: 0