This paper presents a new analysis of the first-order radar cross section (RCS) of highly conductive random surfaces, with a particular focus on the ocean surface characterized by large roughness scales and non-negligible slopes in the high-frequency band. Employing a generalized-function approach, we derive the operator equation governing the electric field over the ocean surface. Building upon previous research and incorporating a vertical-pulsed dipole source, our methodology also accounts for the time-varying nature of ocean surfaces. By introducing explicit factors for height and surface slope into the scattering field expressions, we obtain an enhanced first-order bistatic RCS formulation. This approach alleviates restrictions inherent in traditional perturbation-based methods, particularly under extreme wave conditions, and thus offers improved potential for interpreting remote sensing data of the ocean surface.
{"title":"Single-scattering radar cross section of the ocean surface without the small-slope and height assumptions","authors":"M. Torabi;R. Shahidi;E. W. Gill","doi":"10.1029/2025RS008265","DOIUrl":"https://doi.org/10.1029/2025RS008265","url":null,"abstract":"This paper presents a new analysis of the first-order radar cross section (RCS) of highly conductive random surfaces, with a particular focus on the ocean surface characterized by large roughness scales and non-negligible slopes in the high-frequency band. Employing a generalized-function approach, we derive the operator equation governing the electric field over the ocean surface. Building upon previous research and incorporating a vertical-pulsed dipole source, our methodology also accounts for the time-varying nature of ocean surfaces. By introducing explicit factors for height and surface slope into the scattering field expressions, we obtain an enhanced first-order bistatic RCS formulation. This approach alleviates restrictions inherent in traditional perturbation-based methods, particularly under extreme wave conditions, and thus offers improved potential for interpreting remote sensing data of the ocean surface.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 7","pages":"1-18"},"PeriodicalIF":1.5,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Manoj Saikia;Pankaj Mili;Nilotpal Nath;Bijit Kumar Banerjee;Samiran Patgiri;Subrat Das;Alaka Medhi;Minakshi Devi;A. K. Barbara
A novel Stratosphere-Troposphere (ST) Radar at 212.5 MHz is installed at Gauhati University (GU), Guwahati (26.15°N, 91.66°E), India with the objective to study wind pattern over the region. This paper presents first time validation of this wind profiler data from 300 m to 15 km altitude in comparison with collocated GPS Radiosonde measurements. The radar wind data match very well with radiosonde observations both in magnitude and directions. The correlation coefficient for zonal and meridional winds are found to be 0.94 and 0.95, respectively. The standard deviation of difference between radar and radiosonde data for zonal and meridional wind is 1.87 and 1.90 ms−1, respectively. The ST radar data are further classified as precipitation and non-precipitation cases and compared to radiosonde data. For precipitation cases the correlation coefficients of zonal and meridional wind are found to be 0.94 and 0.94, respectively, whereas the correlation coefficients for zonal and meridional wind in non-precipitation cases are 0.93 and 0.96, respectively. Besides, vertical wind is validated by analyzing its performance during precipitation event. These results align with other operational wind profiler radars, establishing the GU ST Radar as a reliable tool for providing high quality wind data.
{"title":"Comparison and validation of 212.5 MHz Gauhati university stratosphere troposphere radar data with reference to radiosonde observation","authors":"Manoj Saikia;Pankaj Mili;Nilotpal Nath;Bijit Kumar Banerjee;Samiran Patgiri;Subrat Das;Alaka Medhi;Minakshi Devi;A. K. Barbara","doi":"10.1029/2025RS008248","DOIUrl":"https://doi.org/10.1029/2025RS008248","url":null,"abstract":"A novel Stratosphere-Troposphere (ST) Radar at 212.5 MHz is installed at Gauhati University (GU), Guwahati (26.15°N, 91.66°E), India with the objective to study wind pattern over the region. This paper presents first time validation of this wind profiler data from 300 m to 15 km altitude in comparison with collocated GPS Radiosonde measurements. The radar wind data match very well with radiosonde observations both in magnitude and directions. The correlation coefficient for zonal and meridional winds are found to be 0.94 and 0.95, respectively. The standard deviation of difference between radar and radiosonde data for zonal and meridional wind is 1.87 and 1.90 ms<sup>−1</sup>, respectively. The ST radar data are further classified as precipitation and non-precipitation cases and compared to radiosonde data. For precipitation cases the correlation coefficients of zonal and meridional wind are found to be 0.94 and 0.94, respectively, whereas the correlation coefficients for zonal and meridional wind in non-precipitation cases are 0.93 and 0.96, respectively. Besides, vertical wind is validated by analyzing its performance during precipitation event. These results align with other operational wind profiler radars, establishing the GU ST Radar as a reliable tool for providing high quality wind data.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 7","pages":"1-14"},"PeriodicalIF":1.5,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773291","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Modern wireless communication standards require small, high-performing antennas, which are becoming increasingly necessary as technology develops. Simple geometries and traditional dielectric materials limit the bandwidth, efficiency, and flexibility of traditional microstrip antennas, which limits their use in high-frequency applications. This study proposes a novel Elliptic Fractal-Plasmonic Microstrip Antenna that integrates advanced materials and innovative geometries to improve bandwidth, efficiency, and miniaturization. The design includes a Rogers RT/DUROID 5880 lower substrate, aperture coupling with plasmonic effects, and a graphene-based ground plane with an H-slot for enhanced conductivity and flexibility. The upper substrate uses barium titanate to enable miniaturization, while the elliptically shaped patch with nested fractals and slots improves impedance matching and supports multiple resonant frequencies, expanding the operational bandwidth. The proposed model analysis shows outstanding results at terahertz frequencies, with a return loss of —34.4 dB at 10 THz, resonant frequencies of 13.06 THz, 11.65 THz, and 11.86 THz, and impedance bandwidths of 18.06 THz, 16 THz, and 16.5 THz. The input impedance remains stable, and Voltage Standing Wave Ratio values confirm excellent radiation characteristics. These results indicate a significant improvement in bandwidth, efficiency, and miniaturization compared to conventional designs.
{"title":"High-performance compact elliptic fractal-plasmonic microstrip antenna for advanced wireless communication","authors":"Chejarla Raghunathababu;E. Logashanmugam","doi":"10.1029/2025RS008275","DOIUrl":"https://doi.org/10.1029/2025RS008275","url":null,"abstract":"Modern wireless communication standards require small, high-performing antennas, which are becoming increasingly necessary as technology develops. Simple geometries and traditional dielectric materials limit the bandwidth, efficiency, and flexibility of traditional microstrip antennas, which limits their use in high-frequency applications. This study proposes a novel Elliptic Fractal-Plasmonic Microstrip Antenna that integrates advanced materials and innovative geometries to improve bandwidth, efficiency, and miniaturization. The design includes a Rogers RT/DUROID 5880 lower substrate, aperture coupling with plasmonic effects, and a graphene-based ground plane with an H-slot for enhanced conductivity and flexibility. The upper substrate uses barium titanate to enable miniaturization, while the elliptically shaped patch with nested fractals and slots improves impedance matching and supports multiple resonant frequencies, expanding the operational bandwidth. The proposed model analysis shows outstanding results at terahertz frequencies, with a return loss of —34.4 dB at 10 THz, resonant frequencies of 13.06 THz, 11.65 THz, and 11.86 THz, and impedance bandwidths of 18.06 THz, 16 THz, and 16.5 THz. The input impedance remains stable, and Voltage Standing Wave Ratio values confirm excellent radiation characteristics. These results indicate a significant improvement in bandwidth, efficiency, and miniaturization compared to conventional designs.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 7","pages":"1-15"},"PeriodicalIF":1.5,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qian Sun;Shichao Chen;Lirong Wu;Jia Su;Mingliang Tao;Ming Liu
The focus of this paper is the open-set recognition problem of Synthetic Aperture Radar (SAR) targets, and a simple and robust open-set recognition approach is proposed that uses only a simple convolutional neural classification network. The proposed approach constructs the D-SCORE feature and uses the statistical method to model the D-SCORE obtained in the training phase. This allows for the identification of the threshold for distinguishing between known and unknown classes, and ultimately realizes the open-set recognition of SAR targets. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) data set demonstrate the efficacy of the proposed approach in achieving enhanced open-set recognition performance.
{"title":"An open-set recognition approach for SAR targets using only classification scores","authors":"Qian Sun;Shichao Chen;Lirong Wu;Jia Su;Mingliang Tao;Ming Liu","doi":"10.1029/2024RS008211","DOIUrl":"https://doi.org/10.1029/2024RS008211","url":null,"abstract":"The focus of this paper is the open-set recognition problem of Synthetic Aperture Radar (SAR) targets, and a simple and robust open-set recognition approach is proposed that uses only a simple convolutional neural classification network. The proposed approach constructs the D-SCORE feature and uses the statistical method to model the D-SCORE obtained in the training phase. This allows for the identification of the threshold for distinguishing between known and unknown classes, and ultimately realizes the open-set recognition of SAR targets. Experimental results on the moving and stationary target acquisition and recognition (MSTAR) data set demonstrate the efficacy of the proposed approach in achieving enhanced open-set recognition performance.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 7","pages":"1-8"},"PeriodicalIF":1.5,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wireless power transfer (WPT) systems have gained a lot of attention in electric vehicle (EV) charging due to their potential for efficient, contactless energy transfer, offering enhanced convenience and safety compared to traditional plug-in methods. A phase-shifted full bridge inverter and continuous control set model predictive control are the foundations of a suggested primary side control technique for the WPT system. The optimal control variable is then found by converting the controller's gray wolf optimization issue into a problem of minimizing the cost function's value in order to get the best response from the system. According to the findings of the simulation, the control system operates at a frequency of 10 kHz to achieve real-time voltage adjustment, and about 8.6 kW of power is transmitted. Compared with the conventional technique, the power transferred is improved when misalignment is addressed by interference factors. The system, validated through hardware implementation and testing, demonstrated stable output power and voltage regulation with an average efficiency of 95.2%, demonstrating its reliability for real-world EV charging applications. The proposed method enhances double LCC compensated WPT systems' performance, making them suitable for compact, lightweight receiver applications, and enables real-time regulation of system output voltage.
{"title":"Gray optimized adaptive model predictive control for enhanced efficiency and misalignment tolerance in wireless EV charging systems","authors":"T. A. Annai Raina;D. Marshiana","doi":"10.1029/2025RS008228","DOIUrl":"https://doi.org/10.1029/2025RS008228","url":null,"abstract":"Wireless power transfer (WPT) systems have gained a lot of attention in electric vehicle (EV) charging due to their potential for efficient, contactless energy transfer, offering enhanced convenience and safety compared to traditional plug-in methods. A phase-shifted full bridge inverter and continuous control set model predictive control are the foundations of a suggested primary side control technique for the WPT system. The optimal control variable is then found by converting the controller's gray wolf optimization issue into a problem of minimizing the cost function's value in order to get the best response from the system. According to the findings of the simulation, the control system operates at a frequency of 10 kHz to achieve real-time voltage adjustment, and about 8.6 kW of power is transmitted. Compared with the conventional technique, the power transferred is improved when misalignment is addressed by interference factors. The system, validated through hardware implementation and testing, demonstrated stable output power and voltage regulation with an average efficiency of 95.2%, demonstrating its reliability for real-world EV charging applications. The proposed method enhances double LCC compensated WPT systems' performance, making them suitable for compact, lightweight receiver applications, and enables real-time regulation of system output voltage.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 7","pages":"1-22"},"PeriodicalIF":1.5,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144773278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Vazquez Alejos;L. Amaro Losada;M. Rivas-Costa;C. Mosquera;D. Alvarez Outerelo
The present work investigates hierarchical beamforming strategies for millimeter-wave communication systems, focusing on amplitude tapering and sub-array approaches. The research addresses key challenges in Angle of Arrival (AoA) estimation and beam management, essential for next-generation wireless networks. The tapering-based method, implemented on a 4-element linear array, demonstrated precise beamwidth and sidelobe control, enabling hierarchical search strategies with reduced implementation effort. Experimental validation confirmed its effectiveness in identifying transmission directions under line-of-sight conditions; however, its reliance on full-array activation made it less energy-efficient and more sensitive to multipath-induced errors in reflective environments. Conversely, the sub-array approach, applied to an 8-element linear array, showcased enhanced robustness against multipath effects and quantifiable power savings. By activating only a subset of elements at each search level, this method achieved an estimated 42% reduction in average power per configuration and significantly fewer beam evaluations than exhaustive search. Its hierarchical adaptability supported efficient AoA estimation with balanced energy demands. The Rician K-factor analysis validated its suitability for line-of-sight-dominated environments. Comparative results revealed that while tapering achieves high angular resolution, it requires precise amplitude control and is less resilient to multipath. The sub-array technique, though less effective in sidelobe suppression, offers superior scalability, flexibility, and energy efficiency, making it a practical choice for real-world millimeter-wave systems. This work highlights the potential of hierarchical codebook designs in optimizing beamforming performance, training efficiency, execution time, and power consumption for millimeter-wave communications.
{"title":"Hierarchical beamforming strategies for source detection with linear arrays at 26 GHz","authors":"A. Vazquez Alejos;L. Amaro Losada;M. Rivas-Costa;C. Mosquera;D. Alvarez Outerelo","doi":"10.1029/2024RS008215","DOIUrl":"https://doi.org/10.1029/2024RS008215","url":null,"abstract":"The present work investigates hierarchical beamforming strategies for millimeter-wave communication systems, focusing on amplitude tapering and sub-array approaches. The research addresses key challenges in Angle of Arrival (AoA) estimation and beam management, essential for next-generation wireless networks. The tapering-based method, implemented on a 4-element linear array, demonstrated precise beamwidth and sidelobe control, enabling hierarchical search strategies with reduced implementation effort. Experimental validation confirmed its effectiveness in identifying transmission directions under line-of-sight conditions; however, its reliance on full-array activation made it less energy-efficient and more sensitive to multipath-induced errors in reflective environments. Conversely, the sub-array approach, applied to an 8-element linear array, showcased enhanced robustness against multipath effects and quantifiable power savings. By activating only a subset of elements at each search level, this method achieved an estimated 42% reduction in average power per configuration and significantly fewer beam evaluations than exhaustive search. Its hierarchical adaptability supported efficient AoA estimation with balanced energy demands. The Rician K-factor analysis validated its suitability for line-of-sight-dominated environments. Comparative results revealed that while tapering achieves high angular resolution, it requires precise amplitude control and is less resilient to multipath. The sub-array technique, though less effective in sidelobe suppression, offers superior scalability, flexibility, and energy efficiency, making it a practical choice for real-world millimeter-wave systems. This work highlights the potential of hierarchical codebook designs in optimizing beamforming performance, training efficiency, execution time, and power consumption for millimeter-wave communications.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 6","pages":"1-17"},"PeriodicalIF":1.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article comprehensively analyzes and evaluates the influence of all sources of uncertainty on the measurement of complex dielectric constants using the coaxial airline-based transmission reflection method. The research results indicate that within the range of (εr' = 1–30, tanδ = 0.01–1), the measurement uncertainty of dielectric constant is 4.87%, and the measurement uncertainty of dielectric loss tangent is 5.17%. Among them, the inner radius of the specimen has the greatest impact on measurement uncertainty, causing measurement uncertainties of 1.30% and 1.33% for the dielectric constant and dielectric loss tangent, respectively.
{"title":"Uncertainty estimation based on the transmission reflection method for measuring the complex permittivity of materials with coaxial airline","authors":"Guifeng Yang;Shaohua Zhou;Hui Huang;Jianhua Yang","doi":"10.1029/2025RS008239","DOIUrl":"https://doi.org/10.1029/2025RS008239","url":null,"abstract":"This article comprehensively analyzes and evaluates the influence of all sources of uncertainty on the measurement of complex dielectric constants using the coaxial airline-based transmission reflection method. The research results indicate that within the range of (εr' = 1–30, tanδ = 0.01–1), the measurement uncertainty of dielectric constant is 4.87%, and the measurement uncertainty of dielectric loss tangent is 5.17%. Among them, the inner radius of the specimen has the greatest impact on measurement uncertainty, causing measurement uncertainties of 1.30% and 1.33% for the dielectric constant and dielectric loss tangent, respectively.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 6","pages":"1-21"},"PeriodicalIF":1.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents machine learning-based approaches to improve moment estimation for polarimetrie weather radar. A novel weighted multilag estimator (WMLE) is proposed, with adaptively learned weights optimized using deep learning techniques. Two approaches of multilayer perceptron (MLP) and convolutional neural network (CNN) are used to implement WMLE. The performance of WMLE is evaluated using the measurements from the Next-Generation Weather Radar (NEXRAD) system. Experimental results demonstrate that the WMLE significantly improves polarimetric data quality, achieving lower root mean square error and standard deviation compared to conventional 0-Lag and 1-Lag estimators. In addition, the CNN-based estimator surpasses its MLP counterpart by leveraging spatial information in the input data and producing content-aware dynamic adaptive weights. Furthermore, the CNN-based estimator achieves superior radar data quality using data from only 32 pulses, compared with the 0-Lag and 1-Lag estimators using 64 pulses. Moreover, the CNN model demonstrates physical explainability, as its learned weights exhibit meaningful correlations with the characteristics of NEXRAD data.
{"title":"Adaptive moment estimation for polarimetric weather radar using explainable deep learning-based estimators","authors":"Zhe Li;Yuechen Wu;Guifu Zhang","doi":"10.1029/2025RS008266","DOIUrl":"https://doi.org/10.1029/2025RS008266","url":null,"abstract":"This paper presents machine learning-based approaches to improve moment estimation for polarimetrie weather radar. A novel weighted multilag estimator (WMLE) is proposed, with adaptively learned weights optimized using deep learning techniques. Two approaches of multilayer perceptron (MLP) and convolutional neural network (CNN) are used to implement WMLE. The performance of WMLE is evaluated using the measurements from the Next-Generation Weather Radar (NEXRAD) system. Experimental results demonstrate that the WMLE significantly improves polarimetric data quality, achieving lower root mean square error and standard deviation compared to conventional 0-Lag and 1-Lag estimators. In addition, the CNN-based estimator surpasses its MLP counterpart by leveraging spatial information in the input data and producing content-aware dynamic adaptive weights. Furthermore, the CNN-based estimator achieves superior radar data quality using data from only 32 pulses, compared with the 0-Lag and 1-Lag estimators using 64 pulses. Moreover, the CNN model demonstrates physical explainability, as its learned weights exhibit meaningful correlations with the characteristics of NEXRAD data.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 6","pages":"1-15"},"PeriodicalIF":1.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the presence of induced polarization effect in subsea reservoirs, marine controlled-source electromagnetic (MCSEM) data contain induction response and polarization response. The traditional magnitude versus offset (MVO) curve makes it difficult to manually identify the induction-polarization anomalies contaminated by noise, which leads to the reduction of anomaly resolution and affects the accuracy of data interpretation. Machine learning models possess strong feature extraction and classification ability, which can obtain probabilistic anomaly classification results. Therefore, this study proposes an induction-polarization anomaly identification method based on a two-scale feature extraction network (TFEN) combined with XGBoost algorithm. First, MCSEM induction-polarization theoretical data are calculated using the Cole-Cole model, with random noise added to simulate noisy field data. Then, to effectively fuse muli-scale features while maintaining computational efficiency, a TFEN model is constructed. This model employs long short-term memory and dilated convolution to automatically extract the two-scale nonlinear features from induction-polarization data, followed by feature fusion. Finally, the identification of MCSEM induction-polarization data is realized using the XGBoost. The results show that TFEN-XGBoost achieves the highest anomaly identification accuracy compared with Random Forest, TFEN alone, and XGBoost alone. When the MVO curve fails to distinguish induction-polarization anomalies, the TFEN-XGBoost model achieves a recognition accuracy of 95.89% on theoretical data and 88.93% on noisy data sets. This demonstrates that the combined TFEN-XGBoost model can effectively identify induction-polarization anomalies, providing important technical support for oil resource exploration based on MCSEM.
{"title":"MCSEM induction-polarization anomaly identification based on two-scale feature extraction network and XGBoost","authors":"Chunying Gu;Suyi Li;Silun Peng","doi":"10.1029/2024RS008194","DOIUrl":"https://doi.org/10.1029/2024RS008194","url":null,"abstract":"Due to the presence of induced polarization effect in subsea reservoirs, marine controlled-source electromagnetic (MCSEM) data contain induction response and polarization response. The traditional magnitude versus offset (MVO) curve makes it difficult to manually identify the induction-polarization anomalies contaminated by noise, which leads to the reduction of anomaly resolution and affects the accuracy of data interpretation. Machine learning models possess strong feature extraction and classification ability, which can obtain probabilistic anomaly classification results. Therefore, this study proposes an induction-polarization anomaly identification method based on a two-scale feature extraction network (TFEN) combined with XGBoost algorithm. First, MCSEM induction-polarization theoretical data are calculated using the Cole-Cole model, with random noise added to simulate noisy field data. Then, to effectively fuse muli-scale features while maintaining computational efficiency, a TFEN model is constructed. This model employs long short-term memory and dilated convolution to automatically extract the two-scale nonlinear features from induction-polarization data, followed by feature fusion. Finally, the identification of MCSEM induction-polarization data is realized using the XGBoost. The results show that TFEN-XGBoost achieves the highest anomaly identification accuracy compared with Random Forest, TFEN alone, and XGBoost alone. When the MVO curve fails to distinguish induction-polarization anomalies, the TFEN-XGBoost model achieves a recognition accuracy of 95.89% on theoretical data and 88.93% on noisy data sets. This demonstrates that the combined TFEN-XGBoost model can effectively identify induction-polarization anomalies, providing important technical support for oil resource exploration based on MCSEM.","PeriodicalId":49638,"journal":{"name":"Radio Science","volume":"60 6","pages":"1-14"},"PeriodicalIF":1.6,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550154","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"地球科学","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：