Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controls

This paper presents a novel surrogate model for modeling subsurface fluid flow with well controls using a physics-informed convolutional recurrent neural network (PICRNN). The model uses a convolutional long-short term memory (ConvLSTM) to capture the spatiotemporal dependencies of the state evoluti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Jungang, Gildin, Eduardo, Killough, John E
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Chen, Jungang
Gildin, Eduardo
Killough, John E
description This paper presents a novel surrogate model for modeling subsurface fluid flow with well controls using a physics-informed convolutional recurrent neural network (PICRNN). The model uses a convolutional long-short term memory (ConvLSTM) to capture the spatiotemporal dependencies of the state evolution dynamics in the porous flow. The ConvLSTM is linked to the state space equations, enabling the incorporation of a discrete-time sequence of well control. The model requires initial state condition and a sequence of well controls as inputs, and predicts the state variables of the system, such as pressure, as output. By minimizing the residuals of reservoir flow state-space equations, the network is trained without the need for labeled data. The model is designed to serve as a surrogate model for predicting future reservoir states based on the initial reservoir state and input engineering controls. Boundary conditions are enforced into the state-space equations so no additional loss term is needed. Three numerical cases are studied, demonstrating the model's effectiveness in predicting reservoir dynamics based on future well/system controls. The proposed model provides a new approach for efficient and accurate prediction of subsurface fluid flow, with potential applications in optimal control design for reservoir engineering.
doi_str_mv 10.48550/arxiv.2305.09056
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2305_09056</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2305_09056</sourcerecordid><originalsourceid>FETCH-LOGICAL-a676-c262b060e7582a4ba165d30c0e7703c546ae74ad49f3fe3f23f87dab692e880b3</originalsourceid><addsrcrecordid>eNotj8lOwzAURb1hgQofwAr_QILrKckSRUxSURGt1GX0Ej-3lpwYOQP070kKqyvdSTqE3K1ZKnOl2APEHzelXDCVsoIpfU3Mx-ncu6ZPXGdDbNHQMnRT8OPgQgeefmIzxojdQHezhiMMSN-DQU_n-pz2GKfgIt25dvSwjOi3G070gN4vV0MMvr8hVxZ8j7f_uiL756d9-Zpsti9v5eMmAZ3ppOGa10wzzFTOQdaw1soI1sxGxkSjpAbMJBhZWGFRWC5snhmodcExz1ktVuT-7_aCWX1F10I8VwtudcEVv0qjUi8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controls</title><source>arXiv.org</source><creator>Chen, Jungang ; Gildin, Eduardo ; Killough, John E</creator><creatorcontrib>Chen, Jungang ; Gildin, Eduardo ; Killough, John E</creatorcontrib><description>This paper presents a novel surrogate model for modeling subsurface fluid flow with well controls using a physics-informed convolutional recurrent neural network (PICRNN). The model uses a convolutional long-short term memory (ConvLSTM) to capture the spatiotemporal dependencies of the state evolution dynamics in the porous flow. The ConvLSTM is linked to the state space equations, enabling the incorporation of a discrete-time sequence of well control. The model requires initial state condition and a sequence of well controls as inputs, and predicts the state variables of the system, such as pressure, as output. By minimizing the residuals of reservoir flow state-space equations, the network is trained without the need for labeled data. The model is designed to serve as a surrogate model for predicting future reservoir states based on the initial reservoir state and input engineering controls. Boundary conditions are enforced into the state-space equations so no additional loss term is needed. Three numerical cases are studied, demonstrating the model's effectiveness in predicting reservoir dynamics based on future well/system controls. The proposed model provides a new approach for efficient and accurate prediction of subsurface fluid flow, with potential applications in optimal control design for reservoir engineering.</description><identifier>DOI: 10.48550/arxiv.2305.09056</identifier><language>eng</language><subject>Computer Science - Learning</subject><creationdate>2023-05</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2305.09056$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2305.09056$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Chen, Jungang</creatorcontrib><creatorcontrib>Gildin, Eduardo</creatorcontrib><creatorcontrib>Killough, John E</creatorcontrib><title>Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controls</title><description>This paper presents a novel surrogate model for modeling subsurface fluid flow with well controls using a physics-informed convolutional recurrent neural network (PICRNN). The model uses a convolutional long-short term memory (ConvLSTM) to capture the spatiotemporal dependencies of the state evolution dynamics in the porous flow. The ConvLSTM is linked to the state space equations, enabling the incorporation of a discrete-time sequence of well control. The model requires initial state condition and a sequence of well controls as inputs, and predicts the state variables of the system, such as pressure, as output. By minimizing the residuals of reservoir flow state-space equations, the network is trained without the need for labeled data. The model is designed to serve as a surrogate model for predicting future reservoir states based on the initial reservoir state and input engineering controls. Boundary conditions are enforced into the state-space equations so no additional loss term is needed. Three numerical cases are studied, demonstrating the model's effectiveness in predicting reservoir dynamics based on future well/system controls. The proposed model provides a new approach for efficient and accurate prediction of subsurface fluid flow, with potential applications in optimal control design for reservoir engineering.</description><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8lOwzAURb1hgQofwAr_QILrKckSRUxSURGt1GX0Ej-3lpwYOQP070kKqyvdSTqE3K1ZKnOl2APEHzelXDCVsoIpfU3Mx-ncu6ZPXGdDbNHQMnRT8OPgQgeefmIzxojdQHezhiMMSN-DQU_n-pz2GKfgIt25dvSwjOi3G070gN4vV0MMvr8hVxZ8j7f_uiL756d9-Zpsti9v5eMmAZ3ppOGa10wzzFTOQdaw1soI1sxGxkSjpAbMJBhZWGFRWC5snhmodcExz1ktVuT-7_aCWX1F10I8VwtudcEVv0qjUi8</recordid><startdate>20230515</startdate><enddate>20230515</enddate><creator>Chen, Jungang</creator><creator>Gildin, Eduardo</creator><creator>Killough, John E</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20230515</creationdate><title>Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controls</title><author>Chen, Jungang ; Gildin, Eduardo ; Killough, John E</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a676-c262b060e7582a4ba165d30c0e7703c546ae74ad49f3fe3f23f87dab692e880b3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Chen, Jungang</creatorcontrib><creatorcontrib>Gildin, Eduardo</creatorcontrib><creatorcontrib>Killough, John E</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Chen, Jungang</au><au>Gildin, Eduardo</au><au>Killough, John E</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controls</atitle><date>2023-05-15</date><risdate>2023</risdate><abstract>This paper presents a novel surrogate model for modeling subsurface fluid flow with well controls using a physics-informed convolutional recurrent neural network (PICRNN). The model uses a convolutional long-short term memory (ConvLSTM) to capture the spatiotemporal dependencies of the state evolution dynamics in the porous flow. The ConvLSTM is linked to the state space equations, enabling the incorporation of a discrete-time sequence of well control. The model requires initial state condition and a sequence of well controls as inputs, and predicts the state variables of the system, such as pressure, as output. By minimizing the residuals of reservoir flow state-space equations, the network is trained without the need for labeled data. The model is designed to serve as a surrogate model for predicting future reservoir states based on the initial reservoir state and input engineering controls. Boundary conditions are enforced into the state-space equations so no additional loss term is needed. Three numerical cases are studied, demonstrating the model's effectiveness in predicting reservoir dynamics based on future well/system controls. The proposed model provides a new approach for efficient and accurate prediction of subsurface fluid flow, with potential applications in optimal control design for reservoir engineering.</abstract><doi>10.48550/arxiv.2305.09056</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2305.09056
ispartof
issn
language eng
recordid cdi_arxiv_primary_2305_09056
source arXiv.org
subjects Computer Science - Learning
title Physics-informed Convolutional Recurrent Surrogate Model for Reservoir Simulation with Well Controls
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-26T16%3A54%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Physics-informed%20Convolutional%20Recurrent%20Surrogate%20Model%20for%20Reservoir%20Simulation%20with%20Well%20Controls&rft.au=Chen,%20Jungang&rft.date=2023-05-15&rft_id=info:doi/10.48550/arxiv.2305.09056&rft_dat=%3Carxiv_GOX%3E2305_09056%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true