使用机器学习编程预测油田性能:来自英国大陆架的比较案例研究

IF 1.9 4区 地球科学 Q3 GEOSCIENCES, MULTIDISCIPLINARY
Ukari Osah, J. Howell
{"title":"使用机器学习编程预测油田性能:来自英国大陆架的比较案例研究","authors":"Ukari Osah, J. Howell","doi":"10.1144/petgeo2022-071","DOIUrl":null,"url":null,"abstract":"Predicting the performance of a subsurface oil field is a large, multivariant problem. Production is controlled and influenced by a wide array of geological and engineering parameters which overlap and interact in ways that are difficult to unravel in a manner that can be predictive. Supervised machine learning is a statistical approach which uses empirical learnings from a training dataset to create models and make predictions about future outcomes. The goal of this study is to test a number of supervised machine learning methods on a dataset of oil fields from the United Kingdom continental shelf (UKCS), in order to assess whether, a) it is possible to predict future oil field performance and b), which methods are the most effective. The study is based on a dataset of 60 fields with 5 controlling parameters, (gross depositional environment, average permeability, net-to-gross, gas-oil ratio and total number of wells) and 2 outcome parameters (recovery factor and maximum field rate) for each. The choice of controlling parameters was based on a PCA of a larger dataset from a wider project database. Five different machine learning algorithms were tested. These include linear regression, robust linear regression, linear kernel support vector regression, cubic kernel support vector regression and boosted trees regression. Overall, 83% of the data was used as a training dataset while 17% was used to test the predictability of the algorithms. Results were compared using R-Squared, Mean Square Error, Root Mean Square Error and Mean Absolute Error. Graphs of predicted responses vs true (actual) responses are also shown to give a visual illustration of model performance. Results of this analysis show that certain methods perform better than others, depending on the outcome variable in question (recovery factor or maximum field rate). The best method for both outcome variables was the support vector regression, where, depending on the kernel function applied, a reliable level of predictability with low error rates were achieved. This demonstrates a strong potential for statistics-based prediction models of reservoir performance.","PeriodicalId":49704,"journal":{"name":"Petroleum Geoscience","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2023-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting Oil Field Performance using Machine Learning Programming: A Comparative Case Study from the UK Continental Shelf\",\"authors\":\"Ukari Osah, J. Howell\",\"doi\":\"10.1144/petgeo2022-071\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Predicting the performance of a subsurface oil field is a large, multivariant problem. Production is controlled and influenced by a wide array of geological and engineering parameters which overlap and interact in ways that are difficult to unravel in a manner that can be predictive. Supervised machine learning is a statistical approach which uses empirical learnings from a training dataset to create models and make predictions about future outcomes. The goal of this study is to test a number of supervised machine learning methods on a dataset of oil fields from the United Kingdom continental shelf (UKCS), in order to assess whether, a) it is possible to predict future oil field performance and b), which methods are the most effective. The study is based on a dataset of 60 fields with 5 controlling parameters, (gross depositional environment, average permeability, net-to-gross, gas-oil ratio and total number of wells) and 2 outcome parameters (recovery factor and maximum field rate) for each. The choice of controlling parameters was based on a PCA of a larger dataset from a wider project database. Five different machine learning algorithms were tested. These include linear regression, robust linear regression, linear kernel support vector regression, cubic kernel support vector regression and boosted trees regression. Overall, 83% of the data was used as a training dataset while 17% was used to test the predictability of the algorithms. Results were compared using R-Squared, Mean Square Error, Root Mean Square Error and Mean Absolute Error. Graphs of predicted responses vs true (actual) responses are also shown to give a visual illustration of model performance. Results of this analysis show that certain methods perform better than others, depending on the outcome variable in question (recovery factor or maximum field rate). The best method for both outcome variables was the support vector regression, where, depending on the kernel function applied, a reliable level of predictability with low error rates were achieved. This demonstrates a strong potential for statistics-based prediction models of reservoir performance.\",\"PeriodicalId\":49704,\"journal\":{\"name\":\"Petroleum Geoscience\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2023-01-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Petroleum Geoscience\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1144/petgeo2022-071\",\"RegionNum\":4,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"GEOSCIENCES, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Petroleum Geoscience","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1144/petgeo2022-071","RegionNum":4,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"GEOSCIENCES, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

地下油田的动态预测是一个大的、多变量的问题。生产受到一系列地质和工程参数的控制和影响,这些参数以难以预测的方式重叠和相互作用。监督式机器学习是一种统计方法,它使用来自训练数据集的经验学习来创建模型并对未来结果进行预测。本研究的目标是在英国大陆架(UKCS)油田的数据集上测试一些有监督的机器学习方法,以评估a)是否有可能预测未来油田的性能,b)哪种方法最有效。该研究基于60个油田的数据集,每个油田有5个控制参数(总沉积环境、平均渗透率、净总比、气油比和井总数)和2个结果参数(采收率和最大产率)。控制参数的选择是基于来自更广泛的项目数据库的更大数据集的PCA。测试了五种不同的机器学习算法。这些方法包括线性回归、鲁棒线性回归、线性核支持向量回归、三核支持向量回归和增强树回归。总体而言,83%的数据用作训练数据集,17%用于测试算法的可预测性。结果采用r平方、均方误差、均方根误差和平均绝对误差进行比较。还显示了预测响应与真实(实际)响应的图表,以直观地说明模型的性能。分析结果表明,某些方法比其他方法表现更好,这取决于所讨论的结果变量(采收率或最大油田速率)。这两个结果变量的最佳方法是支持向量回归,其中,根据所应用的核函数,实现了具有低错误率的可靠可预测性。这表明了基于统计的油藏动态预测模型的巨大潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Predicting Oil Field Performance using Machine Learning Programming: A Comparative Case Study from the UK Continental Shelf
Predicting the performance of a subsurface oil field is a large, multivariant problem. Production is controlled and influenced by a wide array of geological and engineering parameters which overlap and interact in ways that are difficult to unravel in a manner that can be predictive. Supervised machine learning is a statistical approach which uses empirical learnings from a training dataset to create models and make predictions about future outcomes. The goal of this study is to test a number of supervised machine learning methods on a dataset of oil fields from the United Kingdom continental shelf (UKCS), in order to assess whether, a) it is possible to predict future oil field performance and b), which methods are the most effective. The study is based on a dataset of 60 fields with 5 controlling parameters, (gross depositional environment, average permeability, net-to-gross, gas-oil ratio and total number of wells) and 2 outcome parameters (recovery factor and maximum field rate) for each. The choice of controlling parameters was based on a PCA of a larger dataset from a wider project database. Five different machine learning algorithms were tested. These include linear regression, robust linear regression, linear kernel support vector regression, cubic kernel support vector regression and boosted trees regression. Overall, 83% of the data was used as a training dataset while 17% was used to test the predictability of the algorithms. Results were compared using R-Squared, Mean Square Error, Root Mean Square Error and Mean Absolute Error. Graphs of predicted responses vs true (actual) responses are also shown to give a visual illustration of model performance. Results of this analysis show that certain methods perform better than others, depending on the outcome variable in question (recovery factor or maximum field rate). The best method for both outcome variables was the support vector regression, where, depending on the kernel function applied, a reliable level of predictability with low error rates were achieved. This demonstrates a strong potential for statistics-based prediction models of reservoir performance.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Petroleum Geoscience
Petroleum Geoscience 地学-地球科学综合
CiteScore
4.80
自引率
11.80%
发文量
28
审稿时长
>12 weeks
期刊介绍: Petroleum Geoscience is the international journal of geoenergy and applied earth science, and is co-owned by the Geological Society of London and the European Association of Geoscientists and Engineers (EAGE). Petroleum Geoscience transcends disciplinary boundaries and publishes a balanced mix of articles covering exploration, exploitation, appraisal, development and enhancement of sub-surface hydrocarbon resources and carbon repositories. The integration of disciplines in an applied context, whether for fluid production, carbon storage or related geoenergy applications, is a particular strength of the journal. Articles on enhancing exploration efficiency, lowering technological and environmental risk, and improving hydrocarbon recovery communicate the latest developments in sub-surface geoscience to a wide readership. Petroleum Geoscience provides a multidisciplinary forum for those engaged in the science and technology of the rock-related sub-surface disciplines. The journal reaches some 8000 individual subscribers, and a further 1100 institutional subscriptions provide global access to readers including geologists, geophysicists, petroleum and reservoir engineers, petrophysicists and geochemists in both academia and industry. The journal aims to share knowledge of reservoir geoscience and to reflect the international nature of its development.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信