Key points are not available for this paper at this time.
Abstract Magnetotelluric (MT) is a geophysical technique for detecting subsurface electrical structures. However, MT data collected in areas with frequent human activity often encounter various types of electromagnetic (EM) noise, which can mask or distort the signals we aim to analyze. Over the past decades, data processing methods based on deep learning has become the focus of multiple disciplines. Training neural networks to identify and handle noise has been proven effective in reducing the impact of noise. Therefore, ensuring the neural network accurately learns the noise and signal characteristics during the training is crucial. Against this background, we propose a multi‐scale feature fusion technique based on the densely connected network and apply it to processing MT data. First, we construct a data set resembling the noise in field data and use it to train the network. Leveraging dense connections, we extract feature maps of EM noise from noisy data and utilize Spatial Pyramid Pooling to integrate feature maps of various scales, enabling the network to capture features of the noise precisely. At the same time, we reduce the computation of feature fusion by introducing the Channel‐wise Squeezed Layer to compress the channels of the feature maps. Ultimately, we apply the trained model to the field noisy data. The results of synthetic and field data demonstrate that our method suppresses low‐amplitude and continuous high‐amplitude noise while preserving low‐frequency valuable signal. Apparent resistivity‐phase curves and polarization direction shows a noticeable improvement in the mid and low‐frequency bands with our method.
Wang et al. (Sun,) studied this question.