Compression and Reconstruction of Magnetotelluric Data Based on Convolutional Neural Network

Abstract

Magnetotelluric method is one of the important geophysical methods, and its signal acquisition requires more stacking times and longer stacking time. With the development of instruments, the acquisition time becomes longer and the amount of data becomes larger, which brings new challenges to data storage and transmission. Aiming at the above problems, a compression and reconstruction technology of magnetotelluric time series based on convolutional neural network is proposed. This paper introduces two convolutional autoencoders based on convolutional neural networks, which can effectively compress data space, improve transmission efficiency, and have high data reconstruction accuracy. Using the measured magnetotelluric time series, two autoencoder models based on convolutional networks are verified in this paper, which proves the feasibility of convolutional autoencoders in magnetotelluric data compression; the results show that model 2 can better reproduce It constructs the magnetotelluric time series, and has high training efficiency and good generalization ability.