Received: 26 Jul 2016 – Accepted for review: 31 Aug 2016 – Discussion started: 02 Sep 2016
Abstract. Crustal thickness is an important factor affecting lithosphere structure and therefore 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 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 conclude that deep learning neural network is a promising, believable and inexpensive tool for geophysical inversion.
How to cite. Cheng, X.-Q., Liu, Q.-H., and Li, P. P.: Inverting Rayleigh surface wave velocities for eastern Tibet and western
Yangtze craton crustal thickness based on deep learning neural networks, Nonlin. Processes Geophys. Discuss. [preprint], https://doi.org/10.5194/npg-2016-39, 2016.
In this paper we resolve classic geophysical problem based on newly developed computer and information science. Since many classic geophysical problems are nonlinear, researches treating them as linearity are approximate. When we treat inverting moho depth as full nonlinearity we attain more satisfactory results with lower costs and higher accuracy. Results we have attained can provide important data for discussing origin and development of earthquake, also for distribution of mineral resources.
In this paper we resolve classic geophysical problem based on newly developed computer and...