Inverting Rayleigh surface wave velocities for crustal thickness in eastern Tibet and the western Yangtze craton based on deep learning neural networks

Abstract

Abstract. Crustal thickness is an important factor affecting lithosphere structure and deep geodynamics. In this paper, we propose to apply deep learning neural networks called stacked sparse auto-encoder to obtain crustal thickness for eastern Tibet and western Yangtze craton. Firstly taking phase and group velocities of Rayleigh surface wave simultaneously as input and theoretical crustal thickness as output, we construct twelve deep neural networks trained by 70,000 and tested by 30,000 theoretical models. We then invert observed phase and group velocities by these twelve neural networks. Based on test errors and misfits with other crustal thickness models, we select the optimized one as crustal thickness for study areas. Compared with other ways detected crustal thickness such as seismic wave reflection and receiver function, we adopt a new way for inversion of earth model parameters, and realize that deep learning neural network based on data driven with the highly nonlinear mapping ability can be widely used by geophysical inversion method, and our result has good agreement with high-resolution crustal thickness models. We conclude that deep learning neural network is a promising, efficient and believable tool for geophysical inversion.

Semi‐Supervised Surface Wave Tomography With Wasserstein Cycle‐Consistent GAN: Method and Application to Southern California Plate Boundary Region

“…Neural networks‐based supervised deep learning approach has been proposed to solve the 1‐D Vs inversion problem and proven to be effective in cases characterized by repeated inversion of similar dispersion data with respect to the training data set (e.g., Meier et al., 2007). Different from fully connected neural networks (e.g., Cheng et al., 2019; Devilee et al., 1999), CNN can represent more complicated mapping functions for nonlinear inverse problems (Hu et al., 2020). A typical CNN based Vs inversion consists of three steps: (a) A labeled data set that consists of some synthetic dispersion curves labeled by their corresponding 1‐D Vs profiles (e.g., selected from CVM‐H in this study) is generated; (b) Then, a neural network generating model prediction ($${G}_{m}$$) is trained using the labeled data set (Figure 3a).…”

“…The supervised learning such as convolutional neural networks (CNN) based methods have been widely utilized in geophysical studies. The neural networks approach has been proven to be promising in surface wave studies, for instance, extraction of crustal thickness (Cheng et al., 2019; Devilee et al., 1999; Meier et al., 2007) from surface wave data, and automatic surface wave travel time dispersion picking (e.g., Zhang et al., 2020).…”

Deep Learning for Geophysics: Current and Future Trends

“…Volcanic deformation was detected by using a CNN to classify interferometric fringes in wrapped interferograms (Anantrasirichai et al, 2018). The crustal thickness in eastern Tibet and the western Yangtze craton are estimated by Rayleigh surface wave velocities based on DNN (Cheng et al, 2019). The mantle thermal state of simplified model planets was predicted based on DL with an accuracy of 99% for both the mean mantle temperature and the mean surface heat flux compared to the calculated values (Shahnas & Pysklywec, 2020).…”

Deep Learning‐BasedH‐κMethod (HkNet) for Estimating Crustal Thickness andVp/VsRatio From Receiver Functions

“…In seismology, a successful example is the use of deep learning for earthquake detection and phase picking (Jiang et al., 2021; Z. Li, 2021; Mousavi et al., 2020; J. Wang et al., 2019; Wong et al., 2021; Yu & Ma, 2021; L. Zhang et al., 2020; P. C. Zhou et al., 2021; Y. Zhou et al., 2021). However, applications of deep learning methods in seismic structure inversions have been limited thus far, including super resolution images from low resolution by a CycleGAN and crustal thickness estimated from Rayleigh surface wave based on Deep Neural Networks (Cheng et al., 2019; Niu et al., 2020). A convolutional neural network (CNN) can automatically extract the internal features of an image and construct complex non‐mapping relationships.…”