期刊
PETROLEUM SCIENCE
卷 19, 期 3, 页码 1019-1030出版社
KEAI PUBLISHING LTD
DOI: 10.1016/j.petsci.2022.01.013
关键词
Seismic inversion; Impedance; Deep learning; Network architecture
资金
- National Natural Science Foundation of China [42050104]
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.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据