Automated fault detection without seismic processing

Author:

Araya-Polo Mauricio1,Dahlke Taylor12,Frogner Charlie3,Zhang Chiyuan3,Poggio Tomaso3,Hohl Detlef1

Affiliation:

1. Shell International Exploration and Production Inc.

2. Stanford University.

3. Massachusetts Institute of Technology.

Abstract

For hydrocarbon exploration, large volumes of data are acquired and used in physical modeling-based workflows to identify geologic features of interest such as fault networks, salt bodies, or, in general, elements of petroleum systems. The adjoint modeling step, which transforms the data into the model space, and subsequent interpretation can be very expensive, both in terms of computing resources and domain-expert time. We propose and implement a unique approach that bypasses these demanding steps, directly assisting interpretation. We do this by training a deep neural network to learn a mapping relationship between the data space and the final output (particularly, spatial points indicating fault presence). The key to obtaining accurate predictions is the use of the Wasserstein loss function, which properly handles the structured output — in our case, by exploiting fault surface continuity. The promising results shown here for synthetic data demonstrate a new way of using seismic data and suggest more direct methods to identify key elements in the subsurface.

Publisher

Society of Exploration Geophysicists

Subject

Geology,Geophysics

Reference17 articles.

1. Addison, V., 2016, Artificial intelligence takes shape in oil and gas sector: http://www.epmag.com/artificial-intelligence-takes-shape-oil-gas-sector-846041, accessed 16 January 2017.

2. Bougher, B., and F. Hermann, 2016, AVA classification as an unsupervised machine-learning problem: 86th Annual International Meeting, SEG, Expanded Abstracts, 553–556, http://dx.doi.org/10.1190/segam2016-13874419.1.

3. Dahlke, T., M. Araya-Polo, C. Zhang, and C. Frogner, 2016, Predicting geological features in 3D Seismic Data: Presented at Advances in Neural Information Processing Systems (NIPS) 29, 3D Deep Learning Workshop.

4. A Physics-Driven Neural Networks-Based Simulation System (PhyNNeSS) for Multimodal Interactive Virtual Environments Involving Nonlinear Deformable Objects

5. Application of the Wasserstein metric to seismic signals

Cited by 169 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3