A Hybrid Data-Physics Framework for Reservoir Performance Prediction with Application to H2S Production

IF 3.2 3区 工程技术 Q1 ENGINEERING, PETROLEUM SPE Journal Pub Date : 2023-11-01 DOI:10.2118/218000-pa
Olwijn Leeuwenburgh, Paul J. P. Egberts, Eduardo G. D. Barros, Lukasz P. Turchan, Fahad Dilib, Ole-Petter Lødøen, Wouter J. de Bruin
{"title":"A Hybrid Data-Physics Framework for Reservoir Performance Prediction with Application to H2S Production","authors":"Olwijn Leeuwenburgh, Paul J. P. Egberts, Eduardo G. D. Barros, Lukasz P. Turchan, Fahad Dilib, Ole-Petter Lødøen, Wouter J. de Bruin","doi":"10.2118/218000-pa","DOIUrl":null,"url":null,"abstract":"Summary Model-based reservoir management workflows rely on the ability to generate predictions for large numbers of model and decision scenarios. When suitable simulators or models are not available or cannot be evaluated in a sufficiently short time frame, surrogate modeling techniques can be used instead. In the first part of this paper, we describe extensions of a recently developed open-source framework for creating and training flow network surrogate models, called FlowNet. In particular, we discuss functionality to reproduce historical well rates for wells with arbitrary trajectories, multiple perforated sections, and changing well type or injection phase, as one may encounter in large and complex fields with a long history. Furthermore, we discuss strategies for the placement of additional network nodes in the presence of flow barriers. Despite their flexibility and speed, the applicability of flow network models is limited to phenomena that can be simulated with available numerical simulators. Prediction of poorly understood physics, such as reservoir souring, may require a more data-driven approach. We discuss an extension of the FlowNet framework with a machine learning (ML) proxy for the purpose of generating predictions of H2S production rates. The combined data-physics proxy is trained on historical liquid volume rates, seawater fractions, and H2S production data from a real North Sea oil and gas field, and is then used to generate predictions of H2S production. Several experiments are presented in which the data source, data type, and length of the history are varied. Results indicate that, given a sufficient number of training data, FlowNet is able to produce reliable predictions of conventional oilfield quantities. An experiment performed with the ML proxy suggests that, at least for some production wells, useful predictions of H2S production can be obtained much faster and at much lower computational cost and complexity than would be possible with high-fidelity models. Finally, we discuss some of the current limitations of the approach and options to address them.","PeriodicalId":22252,"journal":{"name":"SPE Journal","volume":"8 6","pages":"0"},"PeriodicalIF":3.2000,"publicationDate":"2023-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"SPE Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2118/218000-pa","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, PETROLEUM","Score":null,"Total":0}
引用次数: 0

Abstract

Summary Model-based reservoir management workflows rely on the ability to generate predictions for large numbers of model and decision scenarios. When suitable simulators or models are not available or cannot be evaluated in a sufficiently short time frame, surrogate modeling techniques can be used instead. In the first part of this paper, we describe extensions of a recently developed open-source framework for creating and training flow network surrogate models, called FlowNet. In particular, we discuss functionality to reproduce historical well rates for wells with arbitrary trajectories, multiple perforated sections, and changing well type or injection phase, as one may encounter in large and complex fields with a long history. Furthermore, we discuss strategies for the placement of additional network nodes in the presence of flow barriers. Despite their flexibility and speed, the applicability of flow network models is limited to phenomena that can be simulated with available numerical simulators. Prediction of poorly understood physics, such as reservoir souring, may require a more data-driven approach. We discuss an extension of the FlowNet framework with a machine learning (ML) proxy for the purpose of generating predictions of H2S production rates. The combined data-physics proxy is trained on historical liquid volume rates, seawater fractions, and H2S production data from a real North Sea oil and gas field, and is then used to generate predictions of H2S production. Several experiments are presented in which the data source, data type, and length of the history are varied. Results indicate that, given a sufficient number of training data, FlowNet is able to produce reliable predictions of conventional oilfield quantities. An experiment performed with the ML proxy suggests that, at least for some production wells, useful predictions of H2S production can be obtained much faster and at much lower computational cost and complexity than would be possible with high-fidelity models. Finally, we discuss some of the current limitations of the approach and options to address them.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
储层动态预测的混合数据-物理框架及其在H2S生产中的应用
基于模型的油藏管理工作流程依赖于为大量模型和决策场景生成预测的能力。当没有合适的模拟器或模型或无法在足够短的时间内进行评估时,可以使用替代建模技术。在本文的第一部分中,我们描述了最近开发的用于创建和训练流网络代理模型的开源框架的扩展,称为FlowNet。特别是,我们讨论了在具有悠久历史的大型复杂油田中可能遇到的任意轨迹、多个射孔段和改变井型或注入阶段的井中重现历史井速的功能。此外,我们还讨论了在存在流障碍的情况下放置额外网络节点的策略。尽管流网络模型具有灵活性和速度,但其适用性仅限于可用数值模拟器模拟的现象。对不太了解的物理现象(如储层酸化)的预测可能需要更多数据驱动的方法。我们讨论了FlowNet框架的扩展与机器学习(ML)代理,目的是生成H2S产量预测。该组合数据物理代理是根据北海实际油气田的历史液体体积率、海水馏分和H2S产量数据进行训练的,然后用于生成H2S产量预测。提出了几个实验,其中数据源、数据类型和历史长度是不同的。结果表明,在给定足够数量的训练数据的情况下,FlowNet能够对常规油田产量进行可靠的预测。使用ML代理进行的一项实验表明,至少对于一些生产井来说,与使用高保真模型相比,可以更快、更低的计算成本和复杂性获得有用的H2S产量预测。最后,我们讨论了该方法当前的一些限制以及解决这些限制的选项。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
SPE Journal
SPE Journal 工程技术-工程:石油
CiteScore
7.20
自引率
11.10%
发文量
229
审稿时长
4.5 months
期刊介绍: Covers theories and emerging concepts spanning all aspects of engineering for oil and gas exploration and production, including reservoir characterization, multiphase flow, drilling dynamics, well architecture, gas well deliverability, numerical simulation, enhanced oil recovery, CO2 sequestration, and benchmarking and performance indicators.
期刊最新文献
Sensitivity Analysis and Comparative Study for Different Detection Modes of Logging-While-Drilling Ultradeep Azimuthal Electromagnetic Tools A Grain Size Profile Prediction Method Based on Combined Model of Extreme Gradient Boosting and Artificial Neural Network and Its Application in Sand Control Design Dynamic Scaling Prediction Model and Application in Near-Wellbore Formation of Ultradeep Natural Gas Reservoirs Injection Temperature Impacts on Reservoir Response during CO2 Storage Virtual Meter with Flow Pattern Recognition Using Deep Learning Neural Networks: Experiments and Analyses
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1