Research on magnetotelluric time series classification based on artificial neural network
YANG Kai1,2(), LIU Cheng1, HE Jing-Long1, Li Han1, YAO Chuan1
1. Xi’an Center of Mineral Resources Survey,China Geological Survey,Xi’an 710100,China 2. School of Geophysics and Geomatics,China University of Geosciences(Wuhan),Wuhan 430074,China
With the development of society,high-quality magnetotelluric signal acquisition is becoming more and more difficult because of various types of human interference are increasingly intensified. Scholars have proposed many corresponding denoising methods for different types of noise to improve data quality. It is impossible to manually interpret each data before denoising due to the huge amount of data. So an efficient noise recognition and classification method is urgently needed. Based on this, artificial neural network is applied in the classification of magnetotelluric time series in this paper. Four types of time series,namely,simulated square wave, power frequency, impulse noise, and measured noiseless data, were used to conduct noise classification training and measured data classification on LSTM、FCN、ResNet、LSTM-FCN and LSTM-ResNet models. The results show that FCN and LSTM-FCN has a relatively good effect on the classification of magnetotelluric time series. Among them, the highest classification accuracy of FCN measured data can reach 99.84%, and the average time for each epoch is 9.6 s. LSTM-FCN has higher classification accuracy than FCN,the highest classification accuracy of measured data sets is nearly 100%, but the average time for each epoch is 24.6 s, and it is easier to overfit than FCN. Overall, LSTM-FCN can achieve higher classification accuracy when the amount of data is relatively small, if the amount of data is large, it is necessary to consider the time cost,using FCN is more appropriate. Finally,the magnetotelluric data containing different types of noise was successfully processed using the magnetotelluric noise processing system which constructed by the LSTM-FCN classification model and the LSTM denoising model.
杨凯, 刘诚, 贺景龙, 李含, 姚川. 基于人工神经网络的大地电磁时序分类研究[J]. 物探与化探, 2024, 48(2): 498-507.
YANG Kai, LIU Cheng, HE Jing-Long, Li Han, YAO Chuan. Research on magnetotelluric time series classification based on artificial neural network. Geophysical and Geochemical Exploration, 2024, 48(2): 498-507.
Sun J, Jin G W, Bai D H, et al. The noise interference of magnetotelluric sounding data[J]. Geophysical and Geochemical Exploration, 2000, 24(2):119-127.
[2]
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.
[2]
Yan J B. Research on theory and method of magnetotelluric signal processing[D]. Changsha: Central South University, 2003.
Cai J H. Research on magnetotelluric signal processing method and application based on Hilbert-Huang transform[D]. Changsha: Central South University, 2010.
Zhou C, Tang J T, Yuan Y, et al. Spatial and temporal distribution characteristics of electromagnetic fields in strong noise area[J]. Journal of Jilin University:Earth Science Edition, 2020, 50(6):1870-1886.
Ge S C, Li B. Review of the characteristics and processing methods of human noise interference in magnetotelluric[J]. Computing Techniques for Geophysical and Geochemical Exploration, 2021, 43(5):609-619.
Yang M C, Chen X D, Cai P, et al. Survey of early time series classification methods[J]. Journal of East China Normal University:Natural Science, 2021(5):115-133.
[8]
沈旭东. 基于深度学习的时间序列算法综述[J]. 信息技术与信息化, 2019(1):71-76.
[8]
Shen X D. A survey of time series algorithms based on deep learning[J]. Information Technology and Informatization, 2019(1):71-76.
[9]
Mehak K. 时间序列分类的端到端深度学习方法[D]. 哈尔滨: 哈尔滨工业大学, 2021.
[9]
Mehak K. End-to-end deep learning method for time series classification[D]. Harbin:Harbin Institute of Technology, 2021.
[10]
Manoj C, Nagarajan N. The application of artificial neural networks to magnetotelluric time-series analysis[J]. Geophysical Journal International, 2003, 153(2):409-423.
doi: 10.1046/j.1365-246X.2003.01902.x
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 L 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.
[14]
Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
doi: 10.1162/neco.1997.9.8.1735
pmid: 9377276
[15]
Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
doi: 10.1109/TPAMI.2016.2572683
pmid: 27244717
[16]
Wang Z G, Yan W Z, Oates T. Time series classification from scratch with deep neural networks:A strong baseline[C]// 2017 International Joint Conference on Neural Networks (IJCNN).Anchorage,AK,USA.IEEE, 2017:1578-1585.
[17]
He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition[C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).Las Vegas,NV,USA.IEEE, 2016:770-778.
Liu C, Zhao X H, Liang N C, et al. Research on lithology identification and classification based on ResNet50 and transfer learning[J]. Computer & Digital Engineering, 2021, 49(12):2526-2530,2578.
[19]
张雅雯. 基于残差网络的时间序列的分类算法研究[D]. 北京: 北京交通大学, 2020.
[19]
Zhang Y W. Research on classification algorithm of time series based on residual network[D]. Beijing: Beijing Jiaotong University, 2020.
[20]
Karim F, Majumdar S, Darabi H, et al. LSTM fully convolutional networks for time series classification[J]. IEEE Access, 2017, 6:1662-1669.
doi: 10.1109/ACCESS.2017.2779939
[21]
Karim F, Majumdar S, Darabi H, et al. Multivariate LSTM-FCNs for time series classification[J]. Neural Networks, 2019, 116:237-245.
doi: S0893-6080(19)30120-0
pmid: 31121421
Wang C, Wang Y, Zheng T, et al. Multi-energy load forecasting in integrated energy system based on ResNet-LSTM network and attention mechanism[J]. Transactions of China Electrotechnical Society, 2022, 37(7):1789-1799.
Ye X Y, Wei Z Y H, Yan H, et al. ECG signal classification based on fusion model of res nte and Bi-LSTM network[J]. Space Medicine & Medical Engineering, 2021, 34(3):244-251.
[24]
Kingma D P, Ba J. Adam:A method for stochastic optimization[J]. ArXiv e-Prints,2014:arXiv:1412.6980.
Yang K, Tang W D, Liu C, et al. Suppression of magnetotelluric square wave noise based on a LSTM recurrent neural network[J]. Geophysical and Geochemical Exploration, 2022, 46(4):925-933.