Low-Frequency Magnetotelluric Data Denoising Using Improved Denoising Convolutional Neural Network and Gated Recurrent Unit

• Published in: IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-16
• Main Authors: Li, Guang, Gu, Xianjie, Chen, Chaojian, Zhou, Cong, Xiao, Donghan, Wan, Wei, Cai, Hongzhu
• Format: Article
• Language: English
• Subjects: Algorithms; Anthropogenic factors; Artificial neural networks; Convolutional neural networks; Deep learning; denoising convolutional neural networks (DnCNNs); Dictionaries; Feature extraction; gated recurrent unit (GRU); Glossaries; Information processing; Logic gates; low-frequency signal denoising; Machine learning; Magnetic resonance imaging; Magnetic separation; magnetotellurics (MT); Neural networks; Noise measurement; Noise reduction; Nucleotide sequence; Robustness; Singular value decomposition; Synthetic data
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2024.3374950

The magnetotelluric (MT) signals are susceptible to anthropogenic noise and the existing denoising methods have significant shortcomings in low-frequency situations. To address the problem, we propose an innovative denoising approach. It is different from the existing methods that attempt to achieve signal-to-noise separation through one step. The denoising process is divided into two steps in the proposed approach. The effective low-frequency dominant component and high-frequency component are sequentially extracted through deep learning and dictionary learning. We propose a new deep learning network named DnCNN-GRU, which combines the powerful feature extraction capability of denoising convolutional neural network (DnCNN) and the strong temporal sequence processing ability of gated recurrent unit (GRU), enabling accurate extraction of the low-frequency MT signal. Furthermore, we integrate this network with the K-singular value decomposition (KSVD) dictionary learning to achieve accurate extraction of effective high-frequency components. Tests of synthetic data indicate that our method is the best compared to a series of state-of-the-art (SOTA) algorithms. It is the only method that can completely remove various types and scales of cultural noises while brilliantly preserving both low- and high-frequency signals. In addition, our method is validated on apparent resistivity and phase data and is significantly superior to the commonly used robust estimation method. These results demonstrate that our method can solve the problem mentioned above and can be a substitute for robust estimation or remote reference processing.