Abstract
Abstract. Crustal thickness is an important factor affecting lithospheric structure and deep geodynamics. In this paper, a deep learning neural network based on a stacked sparse auto-encoder is proposed for the inversion of crustal thickness in eastern Tibet and the western Yangtze craton. First, with the phase velocity of the Rayleigh surface wave as input and the theoretical crustal thickness as output, 12 deep-sSAE neural networks are constructed, which are trained by 380 000 and tested by 120 000 theoretical models. We then invert the observed phase velocities through these 12 neural networks. According to the test error and misfit of other crustal thickness models, the optimal crustal thickness model is selected as the crustal thickness of the study area. Compared with other ways to detect crustal thickness such as seismic wave reflection and receiver function, we adopt a new way for inversion of earth model parameters, and realize that a deep learning neural network based on data driven with the highly non-linear mapping ability can be widely used by geophysicists, and our result has good agreement with high-resolution crustal thickness models. Compared with other methods, our experimental results based on a deep learning neural network and a new Rayleigh wave phase velocity model reveal some details: there is a northward-dipping Moho gradient zone in the Qiangtang block and a relatively shallow north-west–south-east oriented crust at the Songpan–Ganzi block. Crustal thickness around Xi'an and the Ordos basin is shallow, about 35 km. The change in crustal thickness in the Sichuan–Yunnan block is sharp, where crustal thickness is 60 km north-west and 35 km south-east. We conclude that the deep learning neural network is a promising, efficient, and believable geophysical inversion tool.
Highlights
Eastern Tibet and the western Yangtze craton are one of the key areas for understanding the collision process between the Indo-European plate and are an important area for understanding the collision and contact relationship between the Qinghai–Tibet Plateau and the Yangtze craton
We focus on deep learning neural networks to solve the non-linear inverse problem, and apply them to retrieve the crustal thickness for eastern Tibet and the western Yangtze craton from the newest and high-resolution phase velocity maps
To the best of our knowledge, we are the first to introduce deep learning neural networks to learn and invert crustal thickness, and our results show that crustal thickness is strongly non-linear with respect to phase velocity
Summary
Eastern Tibet and the western Yangtze craton are one of the key areas for understanding the collision process between the Indo-European plate and are an important area for understanding the collision and contact relationship between the Qinghai–Tibet Plateau and the Yangtze craton. In the field of geosciences, because of the strong seismic activity, the nature of the two blocks is different, especially the special topography. The altitude of the two blocks suddenly rises from about 500 m in eastern Tibet to 5000 m in the western Yangtze craton. Many studies focus on understanding the crust and upper mantle structure in this region; there have especially been heated debates on crustal thickness. The discontinuity between the crust and the mantle is called Moho discontinuity, which varies greatly on a small scale and is an important factor in geodynamics, including crustal evolution, tectonic activity, gravity correction of the crustal effect, seismic tomography, and geothermal models. Many studies focus on obtaining the depth of Moho discontinuity called crustal thickness by various data and different methods
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
