Geomagnetic Data Denoising Based on Deep Residual Shrinkage Network
Zhang Bin, Yang Chao, Zheng Hao-Hao, Yan Jia-Yong, and Ma Chang-Ying,*
1. School of Electronic and Electrical Engineering, East China University of Technology, Nanchang 330013, China.
2. Engineering Research Center of Nuclear Technology Application, East China University of Technology, Ministry of Education, Nanchang, 330013, China.
3. Nanchang Key Laboratory of Intelligent Sensing Technology and Instruments for Geological Hazards, East China University of Technology, Nanchang 330013, China.
4. Xinlian Superconducting Technology Co., Ltd, Shanghai 201800, China.
5. The SinoProbe Laboratory, Chinese Academy of Geological Sciences, Beijing 100094, China.
Abstract Geomagnetic data hold significant value in fields such as earthquake monitoring and deep earth exploration. However, the increasing severity of anthropogenic noise contamination in existing geomagnetic observatory data poses substantial challenges to high-precision computational analysis of geomagnetic data. To overcome this problem, we propose a denoising method for geomagnetic data based on the Residual Shrinkage Network (RSN). We construct a sample library of simulated and measured geomagnetic data develop and train the RSN denoising network. Through its unique soft thresholding module, RSN adaptively learns and removes noise from the data, effectively improving data quality. In experiments with noise-added measured data, RSN enhances the quality of the noisy data by approximately 12 dB on average. The proposed method is further validated through denoising analysis on measured data by comparing results of time-domain sequences, multiple square coherence and geomagnetic transfer functions.
Fund: Deep Earth Probe and Mineral Resources Exploration -National Science and Technology Major Project (2024ZD1000208), SinoProbe Laboratory Fund of Chinese Academy of Geological Sciences (SL202401), Project of the Nuclear Technology Application Engineering Research Center of the Ministry of Education (HJSJYB2021-3), 2022 Fuzhou Science and Technology Plan Project (Research on High Voltage Electrostatic Atomization New Air Sterilization and Purification Technology and Equipment), Jiangxi Province Major Science and Technology Special Project (20233AAE02008), Fuzhou Unveiling and Leading Project (Jiangxi Gandian) - Online Diagnosis and Intelligent Cloud Platform for the Health Status of Transformer and Distribution Equipment.
Corresponding Authors: Ma Chang-Ying (E-mail: hktk-12@163.com).
E-mail: hktk-12@163.com
About author: Zhang Bin. He received a Ph.D. degree from Institute of plasma physics Chinese Academy of Sciences in 2017, and conducted postdoctoral research at CGN Beigu Technology Co., Ltd. from 2019 to 2022.Currently, he works at East China University of technology and is committed to the research of artificial intelligence in the fi elds of geomagnetic signals, physical electronics and new energy.
Cite this article:
. Geomagnetic Data Denoising Based on Deep Residual Shrinkage Network[J]. APPLIED GEOPHYSICS, 2025, 22(3): 820-834.
2025, Vol. 22 
