Suppression of magnetotelluric square wave noise based on a LSTM recurrent neural network
YANG Kai1,2(), TANG Wei-Dong1, LIU Cheng1, HE Jing-Long1, YAO Chuan1
1. Xi'an Center of Mineral Resources Survey, China Geological Survey, Xi'an 710000, China 2. Institute of Geophysics & Geomatics, China University of Geosciences (Wuhan), Wuhan 430074, China
Denoising is an important part of magnetotelluric data processing. To enrich and develop the denoising method of magnetotelluric time series, this study introduced the LSTM network-one of the recurrent neural networks-into the square wave noise processing of the magnetotelluric time series. Different from previous studies, the measured magnetotelluric time series without human interference superimposed on simulated square wave noise were used as the input of the LSTM network, and the noise-free original time series were used as the target output of the network. After training for 1,500 epochs, the normalized cross-correlation coefficient between the time series extracted from the simulated noise signals by the network and the original time series reached 0.9718, indicating that the network has effectively learned the characteristics of the noise-free magnetotelluric time series. Finally, the denoising test results of measured square wave noise signals show that the proposed method can effectively suppress the interference of square wave noise and improve the estimation quality of impedance. This study provides a new idea for the processing of magnetotelluric time series based on deep learning.
杨凯, 唐卫东, 刘诚, 贺景龙, 姚川. 基于LSTM循环神经网络的大地电磁方波噪声抑制[J]. 物探与化探, 2022, 46(4): 925-933.
YANG Kai, TANG Wei-Dong, LIU Cheng, HE Jing-Long, YAO Chuan. Suppression of magnetotelluric square wave noise based on a LSTM recurrent neural network. Geophysical and Geochemical Exploration, 2022, 46(4): 925-933.
Tang J T, Xu Z M, Xiao X, et al. Effect rules of strong noise on magnetotelluric (MT) sounding in Luzong ore cluster area[J]. Chinese Journal of Geophysics, 2012, 55(12):4147-4159.
[3]
严家斌. 大地电磁信号处理理论及方法研究[D]. 长沙: 中南大学, 2003.
[3]
Yan J B. The study on theory and method of magnetotelluric signal processing[D]. Changsha: Central South University, 2003.
Cai J H, Tang J T, Wang X C. Human noise elimination for magnetotelluric data based on empirical mode decomposition[J]. Journal of Central South University:Science and Technology, 2011, 42(6):1786-1790.
Tang J T, Li J, Xiao X, et al. Mathematical morphology filtering and noise suppression of magnetotelluric sounding data[J]. Chinese Journal of Geophysics, 2012, 55(5):1784-1793.
Tang J T, Liu X, Zhou C. Simulation of square waveform de-noising research of magnetotelluric with a remote reference[J]. Computing Techniques for Geophysical and Geochemical Exploration, 2014, 36(5):513-520.
Wang H, Wei W B, Jin S, et al. Removal of magnetotelluric noise based on synchronous time series relationship[J]. Chinese Journal of Geophysics, 2014, 57(2):531-545.
Wang H, Yan J Y, Fu G M, et al. Current status and application prospect of deep learning in geophysics[J]. Progress in Geophysics, 2020, 35(2):642-655.
Li R Y, Zhang H Q, Wu Z. Online sequential extreme learning machine for transient electromagnetic nonlinear inversion[J]. Geophysical and Geochemical Exploration, 2021, 45(4):1048-1054.
Wang Y C, Liu L T, Xu H Z. The identification of gravity anomaly body based on the convolutional neural network[J]. Geophysical and Geochemical Exploration, 2020, 44(2):394-400.
Han W X, Zhou Y T, Chi Y. Deep learning convolutional neural networks for random noise attenuation in seismic data[J]. Geophysical Prospecting for Petroleum, 2018, 57(6):862-869.
Wang H, Jiang H, Wang L, et al. Magnetotelluric inversion using artificial neural network[J]. Journal of Central South University:Science and Technology, 2015, 46(5):1707-1714.
Zhao W J, Liu Y X, Tao D Q, et al. Prediction of magnetic body top based on BP neural network[J]. Oil Geophysical Prospecting, 2020, 55(5):1139-1148.
[16]
Manoj C, Nagarajan N. The application of artificial neural networks to magnetotelluric time-series analysis[J]. Geophysical Journal International, 2003, 152(2):409-423.
Xu T T, Wang Z X, Xiao Z W, et al. Magnetotelluric power frequency interference suppression based on LSTM recurrent neural network[J]. Progress in Geophysics, 2020, 35(5):2016-2022.
Wang S H, He N F. Feasibility analysis of the LSTM based denoising to MT time series[C]// The 9th Conference of Geophysical Technology,Chinese Geophysical Society—Abstracts of Symposium on Full-Space Geophysical Exploration and Intelligent Sensing, 2021.
Wang K X, Huang Q H, Wu S H. Application of long short-term memory neural network in geoelectric field data processing[J]. Chinese Journal of Geophysics, 2020, 63(8):3015-3024.
[20]
Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
pmid: 9377276
[21]
Kingma D, Ba J. Adam:A method for stochastic optimization[J]. Computer Science, 2014(12).doi: 10.48550/arXiv.1412.6980.
doi: 10.48550/arXiv.1412.6980
[22]
Uhm J, Heo J, Min D J, et al. Imaging strategies to interpret 3-D noisy audio-magnetotelluric data acquired in Gyeongju South Korea:data processing and inversion[J]. Geophysical Journal International, 2021, 225(2):744-758.
doi: 10.1093/gji/ggab002
[23]
Yang Y, Wang X, Han J, et al. Magnetotelluric transfer function distortion assessment using Nyquist diagrams[J]. Journal of Applied Geophysics, 2019, 160:218-228.
doi: 10.1016/j.jappgeo.2018.11.018
Wang S M, Wang J Y. Analysis on statistic characteristics of Magnetotelluric signal[J]. Acta Seismologica Sinica, 2004, 26(6):669-674.
[25]
Neukirch M, Garcia X. Nonstationary magnetotelluric data processing with instantaneous parameter[J]. Journal of Geophysical Research:Solid Earth, 2014, 119(3):1634-1654.
doi: 10.1002/2013JB010494