Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework

Optimal injector selection is a key oilfield development endeavor that can be computationally costly. Methods proposed in the literature to reduce the number of function evaluations are often designed for pattern level analysis and do not scale easily to full field analysis. These methods are rarely...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Anand Selveindran, Zeinab Zargar, Seyed Mahdi Razavi, Ganesh Thakur
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	injection optimization waterflooding CO<sub>2</sub> EOR CO<sub>2</sub> storage machine learning proxy modelling Technology T
Acceso en línea:	https://doaj.org/article/4dc48245a16b45718cc048a38c2bb1b3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4dc48245a16b45718cc048a38c2bb1b3
record_format	dspace
spelling	oai:doaj.org-article:4dc48245a16b45718cc048a38c2bb1b32021-11-25T17:27:22ZFast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework10.3390/en142276281996-1073https://doaj.org/article/4dc48245a16b45718cc048a38c2bb1b32021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/22/7628https://doaj.org/toc/1996-1073Optimal injector selection is a key oilfield development endeavor that can be computationally costly. Methods proposed in the literature to reduce the number of function evaluations are often designed for pattern level analysis and do not scale easily to full field analysis. These methods are rarely applied to both water and miscible gas floods with carbon storage objectives; reservoir management decision making under geological uncertainty is also relatively underexplored. In this work, several innovations are proposed to efficiently determine the optimal injector location under geological uncertainty. A geomodel ensemble is prepared in order to capture the range of geological uncertainty. In these models, the reservoir is divided into multiple well regions that are delineated through spatial clustering. Streamline simulation results are used to train a meta-learner proxy. A posterior sampling algorithm evaluates injector locations across multiple geological realizations. The proposed methodology was applied to a producing field in Asia. The proxy predicted optimal injector locations for water and CO<sub>2</sub> EOR and storage floods within several seconds (94–98% R<sup>2</sup> scores). Blind tests with geomodels not used in training yielded accuracies greater than 90% (R<sup>2</sup> scores). Posterior sampling selected optimal injection locations within minutes compared to hours using numerical simulation. This methodology enabled the rapid evaluation of injector well location for a variety of flood projects. This will aid reservoir managers to rapidly make field development decisions for field scale injection and storage projects under geological uncertainty.Anand SelveindranZeinab ZargarSeyed Mahdi RazaviGanesh ThakurMDPI AGarticleinjection optimizationwaterfloodingCO<sub>2</sub> EORCO<sub>2</sub> storagemachine learningproxy modellingTechnologyTENEnergies, Vol 14, Iss 7628, p 7628 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	injection optimization waterflooding CO<sub>2</sub> EOR CO<sub>2</sub> storage machine learning proxy modelling Technology T
spellingShingle	injection optimization waterflooding CO<sub>2</sub> EOR CO<sub>2</sub> storage machine learning proxy modelling Technology T Anand Selveindran Zeinab Zargar Seyed Mahdi Razavi Ganesh Thakur Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework
description	Optimal injector selection is a key oilfield development endeavor that can be computationally costly. Methods proposed in the literature to reduce the number of function evaluations are often designed for pattern level analysis and do not scale easily to full field analysis. These methods are rarely applied to both water and miscible gas floods with carbon storage objectives; reservoir management decision making under geological uncertainty is also relatively underexplored. In this work, several innovations are proposed to efficiently determine the optimal injector location under geological uncertainty. A geomodel ensemble is prepared in order to capture the range of geological uncertainty. In these models, the reservoir is divided into multiple well regions that are delineated through spatial clustering. Streamline simulation results are used to train a meta-learner proxy. A posterior sampling algorithm evaluates injector locations across multiple geological realizations. The proposed methodology was applied to a producing field in Asia. The proxy predicted optimal injector locations for water and CO<sub>2</sub> EOR and storage floods within several seconds (94–98% R<sup>2</sup> scores). Blind tests with geomodels not used in training yielded accuracies greater than 90% (R<sup>2</sup> scores). Posterior sampling selected optimal injection locations within minutes compared to hours using numerical simulation. This methodology enabled the rapid evaluation of injector well location for a variety of flood projects. This will aid reservoir managers to rapidly make field development decisions for field scale injection and storage projects under geological uncertainty.
format	article
author	Anand Selveindran Zeinab Zargar Seyed Mahdi Razavi Ganesh Thakur
author_facet	Anand Selveindran Zeinab Zargar Seyed Mahdi Razavi Ganesh Thakur
author_sort	Anand Selveindran
title	Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework
title_short	Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework
title_full	Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework
title_fullStr	Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework
title_full_unstemmed	Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework
title_sort	fast optimization of injector selection for waterflood, co<sub>2</sub>-eor and storage using an innovative machine learning framework
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4dc48245a16b45718cc048a38c2bb1b3
work_keys_str_mv	AT anandselveindran fastoptimizationofinjectorselectionforwaterfloodcosub2subeorandstorageusinganinnovativemachinelearningframework AT zeinabzargar fastoptimizationofinjectorselectionforwaterfloodcosub2subeorandstorageusinganinnovativemachinelearningframework AT seyedmahdirazavi fastoptimizationofinjectorselectionforwaterfloodcosub2subeorandstorageusinganinnovativemachinelearningframework AT ganeshthakur fastoptimizationofinjectorselectionforwaterfloodcosub2subeorandstorageusinganinnovativemachinelearningframework
_version_	1718412348240166912

Fast Optimization of Injector Selection for Waterflood, CO<sub>2</sub>-EOR and Storage Using an Innovative Machine Learning Framework

Ejemplares similares