A comparison of deep learning methods for seismic impedance inversion

Deep learning is widely used for seismic impedance inversion, but few work provides in-depth research and analysis on designing the architectures of deep neural networks and choosing the network hyper-parameters. This paper is dedicated to comprehensively studying on the significant aspects of deep neural networks that affect the inversion results. We experimentally reveal how network hyperparameters and architectures affect the inversion performance, and develop a series of methods which are proven to be effective in reconstructing high-frequency information in the estimated impedance model. Experiments demonstrate that the proposed multi-scale architecture is helpful to reconstruct more high-frequency details than a conventional network. Besides, the reconstruction of high-frequency information can be further promoted by introducing a perceptual loss and a generative adversarial network from the computer vision perspective. More importantly, the experimental results provide valuable references for designing proper network architectures in the seismic inversion problem. (C) 2022 The Authors. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co. Ltd.

Automated summary

This paper comprehensively studies the design of deep neural network architectures and the selection of network hyperparameters in seismic impedance inversion. Experimental results demonstrate that the proposed multi-scale architecture and the introduction of perceptual loss and generative adversarial network are effective in reconstructing high-frequency information. The findings provide valuable references for designing proper network architectures in the seismic inversion problem.