A machine learning framework for rapid forecasting and history matching in unconventional reservoirs
Abstract We present a novel workflow for forecasting production in unconventional reservoirs using reduced-order models and machine-learning. Our physics-informed machine-learning workflow addresses the challenges to real-time reservoir management in unconventionals, namely the lack of data (i.e., t...
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/19a3100ba9fc42afae2d745226851b22 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:19a3100ba9fc42afae2d745226851b22 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:19a3100ba9fc42afae2d745226851b222021-11-08T10:48:43ZA machine learning framework for rapid forecasting and history matching in unconventional reservoirs10.1038/s41598-021-01023-w2045-2322https://doaj.org/article/19a3100ba9fc42afae2d745226851b222021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01023-whttps://doaj.org/toc/2045-2322Abstract We present a novel workflow for forecasting production in unconventional reservoirs using reduced-order models and machine-learning. Our physics-informed machine-learning workflow addresses the challenges to real-time reservoir management in unconventionals, namely the lack of data (i.e., the time-frame for which the wells have been producing), and the significant computational expense of high-fidelity modeling. We do this by applying the machine-learning paradigm of transfer learning, where we combine fast, but less accurate reduced-order models with slow, but accurate high-fidelity models. We use the Patzek model (Proc Natl Acad Sci 11:19731–19736, https://doi.org/10.1073/pnas.1313380110 , 2013) as the reduced-order model to generate synthetic production data and supplement this data with synthetic production data obtained from high-fidelity discrete fracture network simulations of the site of interest. Our results demonstrate that training with low-fidelity models is not sufficient for accurate forecasting, but transfer learning is able to augment the knowledge and perform well once trained with the small set of results from the high-fidelity model. Such a physics-informed machine-learning (PIML) workflow, grounded in physics, is a viable candidate for real-time history matching and production forecasting in a fractured shale gas reservoir.Shriram SrinivasanDaniel O’MalleyMaruti K. MudunuruMatthew R. SweeneyJeffrey D. HymanSatish KarraLuke FrashJ. William CareyMichael R. GrossGeorge D. GuthrieTimothy CarrLiwei LiHari S. ViswanathanNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-15 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Shriram Srinivasan Daniel O’Malley Maruti K. Mudunuru Matthew R. Sweeney Jeffrey D. Hyman Satish Karra Luke Frash J. William Carey Michael R. Gross George D. Guthrie Timothy Carr Liwei Li Hari S. Viswanathan A machine learning framework for rapid forecasting and history matching in unconventional reservoirs |
| description |
Abstract We present a novel workflow for forecasting production in unconventional reservoirs using reduced-order models and machine-learning. Our physics-informed machine-learning workflow addresses the challenges to real-time reservoir management in unconventionals, namely the lack of data (i.e., the time-frame for which the wells have been producing), and the significant computational expense of high-fidelity modeling. We do this by applying the machine-learning paradigm of transfer learning, where we combine fast, but less accurate reduced-order models with slow, but accurate high-fidelity models. We use the Patzek model (Proc Natl Acad Sci 11:19731–19736, https://doi.org/10.1073/pnas.1313380110 , 2013) as the reduced-order model to generate synthetic production data and supplement this data with synthetic production data obtained from high-fidelity discrete fracture network simulations of the site of interest. Our results demonstrate that training with low-fidelity models is not sufficient for accurate forecasting, but transfer learning is able to augment the knowledge and perform well once trained with the small set of results from the high-fidelity model. Such a physics-informed machine-learning (PIML) workflow, grounded in physics, is a viable candidate for real-time history matching and production forecasting in a fractured shale gas reservoir. |
| format |
article |
| author |
Shriram Srinivasan Daniel O’Malley Maruti K. Mudunuru Matthew R. Sweeney Jeffrey D. Hyman Satish Karra Luke Frash J. William Carey Michael R. Gross George D. Guthrie Timothy Carr Liwei Li Hari S. Viswanathan |
| author_facet |
Shriram Srinivasan Daniel O’Malley Maruti K. Mudunuru Matthew R. Sweeney Jeffrey D. Hyman Satish Karra Luke Frash J. William Carey Michael R. Gross George D. Guthrie Timothy Carr Liwei Li Hari S. Viswanathan |
| author_sort |
Shriram Srinivasan |
| title |
A machine learning framework for rapid forecasting and history matching in unconventional reservoirs |
| title_short |
A machine learning framework for rapid forecasting and history matching in unconventional reservoirs |
| title_full |
A machine learning framework for rapid forecasting and history matching in unconventional reservoirs |
| title_fullStr |
A machine learning framework for rapid forecasting and history matching in unconventional reservoirs |
| title_full_unstemmed |
A machine learning framework for rapid forecasting and history matching in unconventional reservoirs |
| title_sort |
machine learning framework for rapid forecasting and history matching in unconventional reservoirs |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/19a3100ba9fc42afae2d745226851b22 |
| work_keys_str_mv |
AT shriramsrinivasan amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT danielomalley amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT marutikmudunuru amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT matthewrsweeney amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT jeffreydhyman amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT satishkarra amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT lukefrash amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT jwilliamcarey amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT michaelrgross amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT georgedguthrie amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT timothycarr amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT liweili amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT harisviswanathan amachinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT shriramsrinivasan machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT danielomalley machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT marutikmudunuru machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT matthewrsweeney machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT jeffreydhyman machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT satishkarra machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT lukefrash machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT jwilliamcarey machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT michaelrgross machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT georgedguthrie machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT timothycarr machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT liweili machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs AT harisviswanathan machinelearningframeworkforrapidforecastingandhistorymatchinginunconventionalreservoirs |
| _version_ |
1718442592574636032 |