Research on noise suppression of magnetotelluric signal based on recurrent neural network
文献类型：期刊论文
| 作者 | Han Ying1,2,3; An ZhiGuo1,2,4 ; Di QingYun1,2,4; Wang ZhongNing1,2,4; Kang LiLi1,2,4
|
| 刊名 | CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION
 |
| 出版日期 | 2023-10-01 |
| 卷号 | 66期号:10页码:4317-4331 |
| 关键词 | Magnetotelluric Recurrent Neural Network (RNN) Strong interference Denoising Machine learning |
| ISSN号 | 0001-5733 |
| DOI | 10.6038/cjg2023R0123 |
| 英文摘要 | As the natural electromagnetic signal is weak, the observation data is highly susceptible to noise interference, which seriously affects the inversion and interpretation results. Traditional denoising methods rely on manual screening of time series and power spectra, resulting in low denoising efficiency and strong subjectivity. In this paper, Recurrent Neural Network (RNN) is used to identify and extract the characteristic noise of magnetotelluric time domain signal, and then reconstruct the magnetotelluric signal. On the basis of a lot of analysis of magnetotelluric time-domain signals, noise is classified and a noisy signal database is built. We trained two neural networks using this database, and choose long-short term memory units to optimize the networks, respectively to screen noisy data segments and extract noise patterns. The simulated and measured data are tested respectively, and the RNN can accurately screen out the noise segment in the magnetotelluric signal. This method avoids the subjectivity of manual operation and improves the work efficiency, and the quality of apparent resistivity and phase curve is significantly improved. |
| WOS关键词 | EMPIRICAL MODE DECOMPOSITION |
| WOS研究方向 | Geochemistry & Geophysics |
| 语种 | 英语 |
| WOS记录号 | WOS:001086914800022 |
| 出版者 | SCIENCE PRESS |
| 源URL | [http://ir.iggcas.ac.cn/handle/132A11/110709]  |
| 专题 | 地质与地球物理研究所_深部资源勘探装备研发 |
| 通讯作者 | An ZhiGuo |
| 作者单位 | 1.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Geol & Geophys, Engn Lab Deep Resources Equipment & Technol, Beijing 100029, Peoples R China 3.China Earthquake Networks Ctr, Beijing 100000, Peoples R China 4.Chinese Acad Sci, Innovat Acad Earth Sci, Beijing 100029, Peoples R China |
| 推荐引用方式 GB/T 7714 | Han Ying,An ZhiGuo,Di QingYun,et al. Research on noise suppression of magnetotelluric signal based on recurrent neural network[J]. CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION,2023,66(10):4317-4331. |
| APA | Han Ying,An ZhiGuo,Di QingYun,Wang ZhongNing,&Kang LiLi.(2023).Research on noise suppression of magnetotelluric signal based on recurrent neural network.CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION,66(10),4317-4331. |
| MLA | Han Ying,et al."Research on noise suppression of magnetotelluric signal based on recurrent neural network".CHINESE JOURNAL OF GEOPHYSICS-CHINESE EDITION 66.10(2023):4317-4331. |
入库方式： OAI收割
来源：地质与地球物理研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。