Pub Date : 2024-11-25DOI: 10.1109/LGRS.2024.3505855
Ruida Chen;Yicheng Jiang;He Ni;Yun Zhang
In spaceborne inverse synthetic aperture radar (ISAR) imaging of space targets, the high-speed motion of the radar and target can make the intrapulse motion not negligible. It can cause the range dimension matched filtering error, resulting in image defocusing. In traditional ISAR imaging scenarios, existing analysis and methods only focus on the high-speed motion of the target, without considering the radar, which is not suitable for spaceborne ISAR imaging of space targets. In this letter, the intrapulse motion of spaceborne ISAR imaging of space targets is analyzed in detail, and the corresponding compensation method based on modified phase difference (MPD) is proposed. First, the specific expression of the signal’s time delay considering the intrapulse motion is derived. Then, the range-dimension matched filtering error is analyzed, and the condition of ignoring the intrapulse motion is also obtained. This condition can be used to judge whether the intrapulse motion can be ignored in practical processing. According to the error analysis, an intrapulse motion compensation method based on MPD is proposed. This method does not need to estimate the motion parameters of the radar and target. The coefficient used to construct the compensation term can be directly estimated from the echo signal. Finally, the corresponding spaceborne ISAR imaging method with intrapulse motion compensation for space targets is proposed. Isolated scatterer and satellite electromagnetic calculation data experiments using the orbital data verify the effectiveness of the proposed method.
{"title":"Spaceborne ISAR Imaging of Space Target With Intrapulse Motion Compensation Based on Modified Phase Difference","authors":"Ruida Chen;Yicheng Jiang;He Ni;Yun Zhang","doi":"10.1109/LGRS.2024.3505855","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505855","url":null,"abstract":"In spaceborne inverse synthetic aperture radar (ISAR) imaging of space targets, the high-speed motion of the radar and target can make the intrapulse motion not negligible. It can cause the range dimension matched filtering error, resulting in image defocusing. In traditional ISAR imaging scenarios, existing analysis and methods only focus on the high-speed motion of the target, without considering the radar, which is not suitable for spaceborne ISAR imaging of space targets. In this letter, the intrapulse motion of spaceborne ISAR imaging of space targets is analyzed in detail, and the corresponding compensation method based on modified phase difference (MPD) is proposed. First, the specific expression of the signal’s time delay considering the intrapulse motion is derived. Then, the range-dimension matched filtering error is analyzed, and the condition of ignoring the intrapulse motion is also obtained. This condition can be used to judge whether the intrapulse motion can be ignored in practical processing. According to the error analysis, an intrapulse motion compensation method based on MPD is proposed. This method does not need to estimate the motion parameters of the radar and target. The coefficient used to construct the compensation term can be directly estimated from the echo signal. Finally, the corresponding spaceborne ISAR imaging method with intrapulse motion compensation for space targets is proposed. Isolated scatterer and satellite electromagnetic calculation data experiments using the orbital data verify 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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777731","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}
Pub Date : 2024-11-25DOI: 10.1109/LGRS.2024.3506034
Muhammad Ahmad;Muhammad Usama;Manuel Mazzara;Salvatore Distefano
Hyperspectral imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in deep learning (DL) and Transformer architectures for HSI classification, challenges such as computational efficiency and the need for extensive labeled data persist. This letter introduces WaveMamba, a novel approach that integrates wavelet transformation with the spatial-spectral Mamba (SSMamba) architecture to enhance HSI classification. WaveMamba captures both local texture patterns and global contextual relationships in an end-to-end trainable model. The Wavelet-based enhanced features are then processed through the state-space architecture to model spatial-spectral relationships and temporal dependencies. The experimental results indicate that WaveMamba surpasses existing models, achieving an accuracy improvement of 4.5% on the University of Houston dataset and a 2.0% increase on the Pavia University dataset.
{"title":"WaveMamba: Spatial-Spectral Wavelet Mamba for Hyperspectral Image Classification","authors":"Muhammad Ahmad;Muhammad Usama;Manuel Mazzara;Salvatore Distefano","doi":"10.1109/LGRS.2024.3506034","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3506034","url":null,"abstract":"Hyperspectral imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in deep learning (DL) and Transformer architectures for HSI classification, challenges such as computational efficiency and the need for extensive labeled data persist. This letter introduces WaveMamba, a novel approach that integrates wavelet transformation with the spatial-spectral Mamba (SSMamba) architecture to enhance HSI classification. WaveMamba captures both local texture patterns and global contextual relationships in an end-to-end trainable model. The Wavelet-based enhanced features are then processed through the state-space architecture to model spatial-spectral relationships and temporal dependencies. The experimental results indicate that WaveMamba surpasses existing models, achieving an accuracy improvement of 4.5% on the University of Houston dataset and a 2.0% increase on the Pavia University 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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844476","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}
Traditional ground-penetrating radar (GPR) inversion techniques, while capable of providing high-resolution subsurface imaging, suffer from issues, such as heavy reliance on initial models, high computational demands, and sensitivity to noise and data incompleteness. In contrast, deep-learning-based methods excel in feature extraction and model fitting. However, as a data-driven algorithm, the practical application of convolutional neural networks (CNNs) is limited by the quantity of labeled samples. To reduce the dependence of CNN-based GPR inversion methods on observational data and labels, this project proposes an inversion method based on closed-loop CNNs (CL-CNNs). This approach improves inversion accuracy and reduces the ill-posedness of GPR inversion by modeling both the forward and inverse GPR processes. The CL structure increases the number of features that CNNs can learn from limited labeled samples, while the mutual inversion constraints between the forward and inverse subnetworks help alleviate the ill-posedness of the inversion problem, making the inversion results more consistent with geological principles. Research using synthetic data demonstrates that this method outperforms traditional approaches, as evidenced by enhanced structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR), and a significantly lower mean-squared error (mse), highlighting its advanced performance compared with traditional open-loop CNNs (OL-CNNs). Furthermore, applying this method to real measurement data further validates its effectiveness and practical applicability in engineering contexts, emphasizing its significant practical value.
{"title":"Enhanced Ground-Penetrating Radar Inversion With Closed-Loop Convolutional Neural Networks","authors":"Meijia Huang;Jieyong Liang;Ziyang Zhou;Xuelei Li;Zhijun Huo;Zhuo Jia","doi":"10.1109/LGRS.2024.3505594","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505594","url":null,"abstract":"Traditional ground-penetrating radar (GPR) inversion techniques, while capable of providing high-resolution subsurface imaging, suffer from issues, such as heavy reliance on initial models, high computational demands, and sensitivity to noise and data incompleteness. In contrast, deep-learning-based methods excel in feature extraction and model fitting. However, as a data-driven algorithm, the practical application of convolutional neural networks (CNNs) is limited by the quantity of labeled samples. To reduce the dependence of CNN-based GPR inversion methods on observational data and labels, this project proposes an inversion method based on closed-loop CNNs (CL-CNNs). This approach improves inversion accuracy and reduces the ill-posedness of GPR inversion by modeling both the forward and inverse GPR processes. The CL structure increases the number of features that CNNs can learn from limited labeled samples, while the mutual inversion constraints between the forward and inverse subnetworks help alleviate the ill-posedness of the inversion problem, making the inversion results more consistent with geological principles. Research using synthetic data demonstrates that this method outperforms traditional approaches, as evidenced by enhanced structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR), and a significantly lower mean-squared error (mse), highlighting its advanced performance compared with traditional open-loop CNNs (OL-CNNs). Furthermore, applying this method to real measurement data further validates its effectiveness and practical applicability in engineering contexts, emphasizing its significant practical value.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777664","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}
Elastic parameters such as compressional-wave velocity and shear-wave velocity are essential for characterizing and predicting oil-gas reservoirs. However, the current commonly used shear-wave velocity prediction methods have problems such as weak generalization of empirical formulas and difficulty in obtaining some rock parameters in various rock physics models. We proposed a deep learning network based on the self-attention mechanism to predict shear-wave velocity. First, we need to extract the spatial and temporal features of well logging data using convolutional neural network (CNN) and gated recurrent unit (GRU), respectively. However, the spatial and temporal features exhibit different correlations in the depth direction due to the gradual variation of sedimentary layers. Thus, we fuse the self-attention mechanism with the deep learning network to enhance the network’s sensitivity to crucial spatiotemporal features. Finally, we take the tight sandstone reservoir of Tarim Basin as the research object to estimate shear-wave velocity using CNN, GRU network, and our optimized method. The results show that the CNN-GRU fusion network based on the self-attention mechanism network we proposed is better than the other two networks in the prediction accuracy and generalization degree.
{"title":"Shear-Wave Velocity Prediction by CNN-GRU Fusion Network Based on the Self-Attention Mechanism","authors":"Yahua Yang;Junfeng Zhao;Huanfu Du;Xingyao Yin;Tengfei Chen","doi":"10.1109/LGRS.2024.3506017","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3506017","url":null,"abstract":"Elastic parameters such as compressional-wave velocity and shear-wave velocity are essential for characterizing and predicting oil-gas reservoirs. However, the current commonly used shear-wave velocity prediction methods have problems such as weak generalization of empirical formulas and difficulty in obtaining some rock parameters in various rock physics models. We proposed a deep learning network based on the self-attention mechanism to predict shear-wave velocity. First, we need to extract the spatial and temporal features of well logging data using convolutional neural network (CNN) and gated recurrent unit (GRU), respectively. However, the spatial and temporal features exhibit different correlations in the depth direction due to the gradual variation of sedimentary layers. Thus, we fuse the self-attention mechanism with the deep learning network to enhance the network’s sensitivity to crucial spatiotemporal features. Finally, we take the tight sandstone reservoir of Tarim Basin as the research object to estimate shear-wave velocity using CNN, GRU network, and our optimized method. The results show that the CNN-GRU fusion network based on the self-attention mechanism network we proposed is better than the other two networks in the prediction accuracy and generalization degree.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142798001","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}
Pub Date : 2024-11-25DOI: 10.1109/LGRS.2024.3505193
Enze Zhu;Zhan Chen;Dingkai Wang;Hanru Shi;Xiaoxuan Liu;Lei Wang
Semantic segmentation of high-resolution remote sensing images is vital in downstream applications such as land-cover mapping, urban planning, and disaster assessment. Existing Transformer-based methods suffer from the constraint between accuracy and efficiency, while the recently proposed Mamba is renowned for being efficient. Therefore, to overcome the dilemma, we propose UNetMamba, a UNet-like semantic segmentation model based on Mamba. It incorporates a Mamba segmentation decoder (MSD) that can efficiently decode the complex information within high-resolution images, and a local supervision module (LSM), which is train-only but can significantly enhance the perception of local contents. Extensive experiments demonstrate that UNetMamba outperforms the state-of-the-art (SOTA) methods with mIoU increased by 0.87% on LoveDA and 0.39% on ISPRS Vaihingen while achieving high efficiency through the lightweight design, less memory footprint, and reduced computational cost. The source code is available at https://github.com/EnzeZhu2001/UNetMamba .
{"title":"UNetMamba: An Efficient UNet-Like Mamba for Semantic Segmentation of High-Resolution Remote Sensing Images","authors":"Enze Zhu;Zhan Chen;Dingkai Wang;Hanru Shi;Xiaoxuan Liu;Lei Wang","doi":"10.1109/LGRS.2024.3505193","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505193","url":null,"abstract":"Semantic segmentation of high-resolution remote sensing images is vital in downstream applications such as land-cover mapping, urban planning, and disaster assessment. Existing Transformer-based methods suffer from the constraint between accuracy and efficiency, while the recently proposed Mamba is renowned for being efficient. Therefore, to overcome the dilemma, we propose UNetMamba, a UNet-like semantic segmentation model based on Mamba. It incorporates a Mamba segmentation decoder (MSD) that can efficiently decode the complex information within high-resolution images, and a local supervision module (LSM), which is train-only but can significantly enhance the perception of local contents. Extensive experiments demonstrate that UNetMamba outperforms the state-of-the-art (SOTA) methods with mIoU increased by 0.87% on LoveDA and 0.39% on ISPRS Vaihingen while achieving high efficiency through the lightweight design, less memory footprint, and reduced computational cost. The source code is available at \u0000<uri>https://github.com/EnzeZhu2001/UNetMamba</uri>\u0000.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810203","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}
Pub Date : 2024-11-25DOI: 10.1109/LGRS.2024.3505912
Moran Ju;Tengkai Mao;Mulin Li;Buniu Niu;Si-Nian Jin
In the field of synthetic aperture radar (SAR) image analysis, the main challenges include the difficulty of eliminating the effects of ambient noise, the variability of objects, and the distinction between targets and nontargets. To address these issues, we propose a novel detection model, VFMDet, based on brain-inspired visual filtering mechanism. The model comprises two primary components: a brain-inspired filtering module and a SAR ship detection module. The former contains a bottom-up filtering module responsible for low-level feature extraction, an up-bottom filtering module responsible for high-level feature extraction, and a brain-inspired fusion module responsible for fusing the original image with the filtered feature map. In the SAR ship detection process, to accurately regress the orientation of the ship, we introduce a five-point coding scheme in polar coordinate system. Meanwhile, we introduce a Gaussian heatmap strategy (GHS) that utilizes limited covariance and a Gaussian heatmap loss to solve the problem caused by large-scale variation and dense arrangement of ship target. Finally, we design a multitask loss to help the model complete the end-to-end training. We conducted experiments on the rotating SAR ship detection dataset (RSSDD) and the rotating ship detection dataset (RSDD), and the mean average precision (mAP) improved by 0.27% and 0.89%, respectively, compared with the detection results of the best SAR image rotating object detection model.
{"title":"VFMDet: A Visual Filtering Mechanism-Based SAR Ship Detection Model for Complex Environment","authors":"Moran Ju;Tengkai Mao;Mulin Li;Buniu Niu;Si-Nian Jin","doi":"10.1109/LGRS.2024.3505912","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505912","url":null,"abstract":"In the field of synthetic aperture radar (SAR) image analysis, the main challenges include the difficulty of eliminating the effects of ambient noise, the variability of objects, and the distinction between targets and nontargets. To address these issues, we propose a novel detection model, VFMDet, based on brain-inspired visual filtering mechanism. The model comprises two primary components: a brain-inspired filtering module and a SAR ship detection module. The former contains a bottom-up filtering module responsible for low-level feature extraction, an up-bottom filtering module responsible for high-level feature extraction, and a brain-inspired fusion module responsible for fusing the original image with the filtered feature map. In the SAR ship detection process, to accurately regress the orientation of the ship, we introduce a five-point coding scheme in polar coordinate system. Meanwhile, we introduce a Gaussian heatmap strategy (GHS) that utilizes limited covariance and a Gaussian heatmap loss to solve the problem caused by large-scale variation and dense arrangement of ship target. Finally, we design a multitask loss to help the model complete the end-to-end training. We conducted experiments on the rotating SAR ship detection dataset (RSSDD) and the rotating ship detection dataset (RSDD), and the mean average precision (mAP) improved by 0.27% and 0.89%, respectively, compared with the detection results of the best SAR image rotating object detection 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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142821203","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}
Pub Date : 2024-11-25DOI: 10.1109/LGRS.2024.3505216
Qingyun Yan;Mingbo Hu;Shuanggen Jin;Weimin Huang
This study introduces a method for filling the data gaps in the International Soil Moisture Network (ISMN) by soil moisture (SM) estimated using data from the Cyclone Global Navigation Satellite System (CYGNSS). The estimation process leverages the random forest (RF) algorithm, incorporating CYGNSS-derived products along with soil and surface parameters as input features. This research was conducted based on the daily SM data from the ISMN for the entire years of 2019 and 2020, which served as training and test datasets. Comparison experiments were performed to highlight the limitations of existing methods and SM products for gap filling in ISMN SM data. Subsequently, the optimal retrieval model was deployed to estimate SM for the duration of the study, thereby filling the gaps within the ISMN dataset. The SM results after gap filling showed strong consistency with measured SM, achieving an R-squared ( $R^{2}$ ) of 0.7930 and a root-mean-square error (RMSE) of 0.0492 cm3/cm3. These results indicate that CYGNSS-based SM inversion is a promising approach to enhance the completeness of the ISMN dataset.
{"title":"Gap Filling for ISMN Time Series Using CYGNSS Data","authors":"Qingyun Yan;Mingbo Hu;Shuanggen Jin;Weimin Huang","doi":"10.1109/LGRS.2024.3505216","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505216","url":null,"abstract":"This study introduces a method for filling the data gaps in the International Soil Moisture Network (ISMN) by soil moisture (SM) estimated using data from the Cyclone Global Navigation Satellite System (CYGNSS). The estimation process leverages the random forest (RF) algorithm, incorporating CYGNSS-derived products along with soil and surface parameters as input features. This research was conducted based on the daily SM data from the ISMN for the entire years of 2019 and 2020, which served as training and test datasets. Comparison experiments were performed to highlight the limitations of existing methods and SM products for gap filling in ISMN SM data. Subsequently, the optimal retrieval model was deployed to estimate SM for the duration of the study, thereby filling the gaps within the ISMN dataset. The SM results after gap filling showed strong consistency with measured SM, achieving an R-squared (\u0000<inline-formula> <tex-math>$R^{2}$ </tex-math></inline-formula>\u0000) of 0.7930 and a root-mean-square error (RMSE) of 0.0492 cm3/cm3. These results indicate that CYGNSS-based SM inversion is a promising approach to enhance the completeness of the ISMN 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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777663","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}
The estimation of the derivatives is an important part of potential field data processing and interpretation. In literature, a lot of methods have been presented to estimate the derivatives accurately and stably. However, existing methods still have some limitations. For example, the derivative estimation of high-noise data is unstable, and the determination of some parameters is difficult. To solve the problems of the classical methods mentioned above, a stable method for estimating the derivatives of potential field data based on deep learning is proposed. The proposed method constructs the network based on U-Net and builds a nonlinear mapping relationship between the noisy data and the derivatives of potential field data. After training with the designed datasets, the proposed network achieved the ability to eliminate the influence of noise and intelligently estimate the derivatives of potential field data. The proposed method is tested on synthetic data and real data in the Goiás Alkaline Province, Brazil, taking estimating the vertical derivatives of gravity anomaly as examples. The results indicate that the proposed method generates stable and accurate derivatives with the noisy data.
{"title":"A Stable Method for Estimating the Derivatives of Potential Field Data Based on Deep Learning","authors":"Yandong Liu;Jun Wang;Weichen Li;Fang Li;Yuan Fang;Xiaohong Meng","doi":"10.1109/LGRS.2024.3505873","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505873","url":null,"abstract":"The estimation of the derivatives is an important part of potential field data processing and interpretation. In literature, a lot of methods have been presented to estimate the derivatives accurately and stably. However, existing methods still have some limitations. For example, the derivative estimation of high-noise data is unstable, and the determination of some parameters is difficult. To solve the problems of the classical methods mentioned above, a stable method for estimating the derivatives of potential field data based on deep learning is proposed. The proposed method constructs the network based on U-Net and builds a nonlinear mapping relationship between the noisy data and the derivatives of potential field data. After training with the designed datasets, the proposed network achieved the ability to eliminate the influence of noise and intelligently estimate the derivatives of potential field data. The proposed method is tested on synthetic data and real data in the Goiás Alkaline Province, Brazil, taking estimating the vertical derivatives of gravity anomaly as examples. The results indicate that the proposed method generates stable and accurate derivatives with the noisy 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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142789120","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}
Weather radar echo extrapolation is one of the essential means for weather nowcasting. It has been considerably inspired over the last decade by deep learning. However, the internal similarity of the echo evolution process has little been exploited. To investigate this merit, a deep contrastive model with an encoder–projector structure is proposed in this letter, which projects the subsequences sampled from the same evolution process into the neighborhood of latent space by contrastive learning. Thus, the internal evolution similarity of the input echo sequence itself can be discovered and exploited for promoting prediction. To make the training smoother, we also adopt a cumulative sampling strategy that follows a simple-to-hard manner. Experimental results on two real-world radar datasets demonstrate the superiority of our model in comparison to state-of-the-art. The effectiveness of the sampling strategy and extrapolation ability on limited input is also analyzed and verified. Training code and pretrained models are available at https://github.com/tolearnmuch/ESCL .
{"title":"A Deep Contrastive Model for Radar Echo Extrapolation","authors":"Qian Li;Jinrui Jing;Leiming Ma;Lei Chen;Shiqing Guo;Hanxing Chen;Tianying Wang;Yechao Xu","doi":"10.1109/LGRS.2024.3505897","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505897","url":null,"abstract":"Weather radar echo extrapolation is one of the essential means for weather nowcasting. It has been considerably inspired over the last decade by deep learning. However, the internal similarity of the echo evolution process has little been exploited. To investigate this merit, a deep contrastive model with an encoder–projector structure is proposed in this letter, which projects the subsequences sampled from the same evolution process into the neighborhood of latent space by contrastive learning. Thus, the internal evolution similarity of the input echo sequence itself can be discovered and exploited for promoting prediction. To make the training smoother, we also adopt a cumulative sampling strategy that follows a simple-to-hard manner. Experimental results on two real-world radar datasets demonstrate the superiority of our model in comparison to state-of-the-art. The effectiveness of the sampling strategy and extrapolation ability on limited input is also analyzed and verified. Training code and pretrained models are available at \u0000<uri>https://github.com/tolearnmuch/ESCL</uri>\u0000.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844390","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}
Pub Date : 2024-11-25DOI: 10.1109/LGRS.2024.3505416
Dong Ren;Dongxu Wang;Hang Sun;Shun Ren;Wenbin Wang
Remote sensing rural building detection holds substantial practical value for the scientific management and unified planning of rural land. However, most existing methods struggle to achieve desirable feature representations due to the similarities and imbalances between underconstruction buildings (UBs) and completed buildings (CBs), as well as interference from background noise, which results in high rates of false positives and false negatives. To address these issues, we propose multiconstrained heterogeneous deep network (MHDN) for remote sensing rural building detection. Specifically, we propose a grid-based CNN-GNN hybrid (GCGH) model that incorporates the sparse connectivity graph into the CNN backbone to model global feature correlations for more robust feature representations. Furthermore, a cross-image multiscale contrastive constraint (CMCC) branch is introduced to supervise network training alongside the detection loss, which facilitates detector learning in the presence of category imbalance. Experimental results on our proposed dataset demonstrate that our MHDN outperforms state-of-the-art object detection methods. The code and dataset are available at https://github.com/Dongxu-Wang/MHDN .
{"title":"Multiconstrained Heterogeneous Deep Network for Remote Sensing Rural Building Detection","authors":"Dong Ren;Dongxu Wang;Hang Sun;Shun Ren;Wenbin Wang","doi":"10.1109/LGRS.2024.3505416","DOIUrl":"https://doi.org/10.1109/LGRS.2024.3505416","url":null,"abstract":"Remote sensing rural building detection holds substantial practical value for the scientific management and unified planning of rural land. However, most existing methods struggle to achieve desirable feature representations due to the similarities and imbalances between underconstruction buildings (UBs) and completed buildings (CBs), as well as interference from background noise, which results in high rates of false positives and false negatives. To address these issues, we propose multiconstrained heterogeneous deep network (MHDN) for remote sensing rural building detection. Specifically, we propose a grid-based CNN-GNN hybrid (GCGH) model that incorporates the sparse connectivity graph into the CNN backbone to model global feature correlations for more robust feature representations. Furthermore, a cross-image multiscale contrastive constraint (CMCC) branch is introduced to supervise network training alongside the detection loss, which facilitates detector learning in the presence of category imbalance. Experimental results on our proposed dataset demonstrate that our MHDN outperforms state-of-the-art object detection methods. The code and dataset are available at \u0000<uri>https://github.com/Dongxu-Wang/MHDN</uri>\u0000.","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":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142810453","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：