Assessing the accuracy of fault interpretation using machine-learning techniques when risking faults for CO2 storage site assessment

Author:

Michie Emma A. H.1,Alaei Behzad2,Braathen Alvar1

Affiliation:

1. University of Oslo, Department of Geosciences, Sem Sælands Vei 1, Oslo 0371, Norway.(corresponding author); .

2. University of Oslo, Department of Geosciences, Sem Sælands Vei 1, Oslo 0371, Norway and Earth Science Analytics AS, Strandveien 35, Oslo 1366, Norway..

Abstract

Generating an accurate model of the subsurface for the purpose of assessing the feasibility of a CO2 storage site is crucial. In particular, how faults are interpreted is likely to influence the predicted capacity and integrity of the reservoir; whether this is through identifying high-risk areas along the fault, where fluid is likely to flow across the fault, or by assessing the reactivation potential of the fault with increased pressure, causing fluid to flow up the fault. New technologies allow users to interpret faults effortlessly, and in much quicker time, using methods such as deep learning (DL). These DL techniques use knowledge from neural networks to allow end users to compute areas where faults are likely to occur. Although these new technologies may be attractive due to reduced interpretation time, it is important to understand the inherent uncertainties in their ability to predict accurate fault geometries. Here, we compare DL fault interpretation versus manual fault interpretation, and we can see distinct differences to those faults where significant ambiguity exists due to poor seismic resolution at the fault; we observe an increased irregularity when DL methods are used over conventional manual interpretation. This can result in significant differences between the resulting analyses, such as fault reactivation potential. Conversely, we observe that well-imaged faults indicate a close similarity between the resulting fault surfaces when DL and manual fault interpretation methods are used; hence, we also observe a close similarity between any attributes and fault analyses made.

Funder

Norges Forskningsråd

Publisher

Society of Exploration Geophysicists

Subject

Geology,Geophysics

Reference79 articles.

1. Impact of seismic image quality on fault interpretation uncertainty

2. Fault interpretation in seismic reflection data: an experiment analysing the impact of conceptual model anchoring and vertical exaggeration

3. Seismic Data Interpretation using Digital Image Processing

4. Andrews, J. S., T. G. Fintland, O. A. Helstrup, P. Horsrud, and A. M. Raaen, 2016, Use of unique database of good quality stress data to investigate theories of fracture initiation, fracture propagation and the stress state in the subsurface: 50th US Rock Mechanics/Geomechanics Symposium, American Rock Mechanics Association, ARMA-2016-887.

5. Automated fault detection without seismic processing

Cited by 4 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