CG-DAE: A noise suppression method for two-dimensional transient electromagnetic data based on deep learning

Abstract

The transient electromagnetic method (TEM) is a geophysical exploration method that can efficiently acquire subsurface electrical parameters. For airborne, towed, and other mobile platforms TEM systems, large data volumes, and the traditional one-dimensional denoising method with low efficiency and low signal-to-noise ratio (SNR) of late-time are the main bottlenecks limiting its reliable application. To address this problem, this paper proposes a neural network structure suitable for two-dimensional (2D) TEM data processing. The proposed structure combines a classical convolutional neural network denoising autoencoder with a gated recurrent neural network autoencoder, called the CNN-GRU dual autoencoder (CG-DAE). This method can directly input 2D TEM response data as images into the network for processing, which greatly improves data processing efficiency compared to single-time-channel processing. The simulation experiments verified the effectiveness of CG-DAE. After using CG-DAE denoising, the SNR of the late-time (0.2 ms∼1 ms) signals is improved to nearly 29 dB, the 2D anomaly layer position is clear, and the relative error (RE) between the denoised data and the corresponding clean data is less than 1.41%, while the RE of the late-time signals can be reduced to 3.68%. The proposed method can lay the foundation for fast processing of TEM data based on mobile platforms such as airborne and towed.