应用机器学习解释稳态排水相对渗透率实验

IF 2.1 4区 工程技术 Q3 ENERGY & FUELS
Eric Sonny Mathew, Moussa Tembely, Waleed AlAmeri, Emad W. Al-Shalabi, Abdul Ravoof Shaik
{"title":"应用机器学习解释稳态排水相对渗透率实验","authors":"Eric Sonny Mathew, Moussa Tembely, Waleed AlAmeri, Emad W. Al-Shalabi, Abdul Ravoof Shaik","doi":"10.2118/207877-pa","DOIUrl":null,"url":null,"abstract":"Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.","PeriodicalId":22066,"journal":{"name":"SPE Reservoir Evaluation & Engineering","volume":"18 1","pages":"0"},"PeriodicalIF":2.1000,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Application of Machine Learning to Interpret Steady-State Drainage Relative Permeability Experiments\",\"authors\":\"Eric Sonny Mathew, Moussa Tembely, Waleed AlAmeri, Emad W. Al-Shalabi, Abdul Ravoof Shaik\",\"doi\":\"10.2118/207877-pa\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.\",\"PeriodicalId\":22066,\"journal\":{\"name\":\"SPE Reservoir Evaluation & Engineering\",\"volume\":\"18 1\",\"pages\":\"0\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2023-03-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"SPE Reservoir Evaluation & Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2118/207877-pa\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"SPE Reservoir Evaluation & Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2118/207877-pa","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

摘要

为了确定一套完整的Kr曲线,需要对稳态或非稳态相对渗透率(Kr)实验数据进行细致的解释。在这项工作中,开发了不同的机器学习(ML)模型,以帮助从稳态排水岩心驱替实验运行中更快地估计这些曲线。这些机器学习算法包括梯度增强(GB)、随机森林(RF)、极端梯度增强(XGB)和深度神经网络(DNN),主要关注后两种算法(XGB和DNN)的比较。在现有数学模型的基础上,开发了一个前沿框架,生成了一个大型的Kr和毛细管压力(Pc)曲线数据库。该数据库用于进行数千次岩心驱油模拟运行,代表油水排水稳态实验。这些模拟运行的结果,主要是压降以及其他常规岩心分析数据,用于基于达西定律估计分析Kr曲线。这些分析估计的Kr曲线与先前生成的Pc曲线一起作为特征输入到ML模型中。整个数据集被分成80%用于训练,20%用于测试。采用k-fold交叉验证技术,将80%的训练数据分成10个折叠,以提高模型的准确性。这样,在10个实验中,每个实验使用9个折叠进行训练,其余折叠用于模型验证。一旦模型被训练和验证,它就会在剩下的20%的数据集上进行盲测。机器学习模型学习从训练数据集中捕获核心内部的流体流动行为。在这些ML模型的适用性方面,需要两组实验数据作为输入;第一种是稳态排水岩心驱油实验的解析估计的Kr曲线,另一种是通过离心或注汞毛细管压力(MICP)测量估计的Pc曲线。然后,训练/测试的模型能够根据作为输入的实验结果估计Kr曲线。此外,为了测试机器学习模型在只有一组实验数据可供最终用户使用时的性能,我们训练/测试了一种循环神经网络(RNN)算法,以在没有Pc曲线作为输入的情况下预测Kr曲线。使用决定系数(R2)的值以及模型训练/验证期间计算的损失来评估开发的三种模型(XGB、DNN和RNN)的性能。各自的交叉图以及地面真相与人工智能(AI)预测曲线的比较表明,该模型能够在所有三种被测试的ML技术的历史匹配实验数据上做出准确的预测,误差百分比在0.2%到0.6%之间。这表明,与传统方法相比,基于人工智能的模型在确定Kr曲线方面具有更高的效率和可靠性。开发的ML模型绝不能取代进行排水核心驱油或离心机实验的需要,而是作为现有商业平台的替代方案,用于解释实验数据以预测Kr曲线。开发的ML模型的两个主要优点是它们能够在几分钟内预测Kr曲线,并且最终用户的干预有限。结果还包括经典ML方法、浅神经网络和深度神经网络在预测最终Kr曲线的准确性方面的比较。本文提出的研究是对Mathew等人(2021)提出的最先进框架的扩展。然而,目前研究的两个主要方面是深度学习在Kr曲线预测中的应用和特征工程的应用。后者不仅减少了机器学习模型的训练/测试时间,而且使最终用户能够使用最少的实验数据集获得最终预测。目前研究工作中讨论的各种模型主要集中在排水稳态试验Kr曲线的预测上;然而,这项工作也可以扩展到捕捉渗吸循环。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Application of Machine Learning to Interpret Steady-State Drainage Relative Permeability Experiments
Summary A meticulous interpretation of steady-state or unsteady-state relative permeability (Kr) experimental data is required to determine a complete set of Kr curves. In this work, different machine learning (ML) models were developed to assist in a faster estimation of these curves from steady-state drainage coreflooding experimental runs. These ML algorithms include gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and deep neural network (DNN) with a main focus on and comparison of the two latter algorithms (XGB and DNN). Based on existing mathematical models, a leading-edge framework was developed where a large database of Kr and capillary pressure (Pc) curves were generated. This database was used to perform thousands of coreflood simulation runs representing oil-water drainage steady-state experiments. The results obtained from these simulation runs, mainly pressure drop along with other conventional core analysis data, were used to estimate analytical Kr curves based on Darcy’s law. These analytically estimated Kr curves along with the previously generated Pc curves were fed as features into the ML model. The entire data set was split into 80% for training and 20% for testing. The k-fold cross-validation technique was applied to increase the model’s accuracy by splitting 80% of the training data into 10 folds. In this manner, for each of the 10 experiments, nine folds were used for training and the remaining fold was used for model validation. Once the model was trained and validated, it was subjected to blind testing on the remaining 20% of the data set. The ML model learns to capture fluid flow behavior inside the core from the training data set. In terms of applicability of these ML models, two sets of experimental data were needed as input; the first was the analytically estimated Kr curves from the steady-state drainage coreflooding experiments, while the other was the Pc curves estimated from centrifuge or mercury injection capillary pressure (MICP) measurements. The trained/tested model was then able to estimate Kr curves based on the experimental results fed as input. Furthermore, to test the performance of the ML model when only one set of experimental data is available to an end user, a recurrent neural network (RNN) algorithm was trained/tested to predict Kr curves in the absence of Pc curves as an input. The performance of the three developed models (XGB, DNN, and RNN) was assessed using the values of the coefficient of determination (R2) along with the loss calculated during training/validation of the model. The respective crossplots along with comparisons of ground truth vs. artificial intelligence (AI)-predicted curves indicated that the model is capable of making accurate predictions with an error percentage between 0.2% and 0.6% on history-matching experimental data for all three tested ML techniques. This implies that the AI-based model exhibits better efficiency and reliability in determining Kr curves when compared to conventional methods. The developed ML models by no means replace the need to conduct drainage coreflooding or centrifuge experiments but act as an alternative to existing commercial platforms that are used to interpret experimental data to predict Kr curves. The two main advantages of the developed ML models are their capability of predicting Kr curves within a matter of a few minutes as well as with limited intervention from the end user. The results also include a comparison between classical ML approaches, shallow neural networks, and DNNs in terms of accuracy in predicting the final Kr curves. The research presented here is an extension of the state-of-the-art framework proposed by Mathew et al. (2021). However, the two main aspects of the current study are the application of deep learning for the prediction of Kr curves and the application of feature engineering. The latter not only reduces the training/testing time for the ML models but also enables the end user to obtain the final predictions with the least set of experimental data. The various models discussed in this research work currently focus on the prediction of Kr curves for drainage steady-state experiments; however, the work can be extended to capture the imbibition cycle as well.
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
CiteScore
5.30
自引率
0.00%
发文量
68
审稿时长
12 months
期刊介绍: Covers the application of a wide range of topics, including reservoir characterization, geology and geophysics, core analysis, well logging, well testing, reservoir management, enhanced oil recovery, fluid mechanics, performance prediction, reservoir simulation, digital energy, uncertainty/risk assessment, information management, resource and reserve evaluation, portfolio/asset management, project valuation, and petroleum economics.
×
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