Evaluation of machine learning methodologies using simple physics based conceptual models for flow in porous media

Daulet Magzymov, Ram R. Ratnakar, Birol Dindoruk, Russell T. Johns

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Scopus citations

Abstract

Machine learning (ML) techniques have drawn much attention in the engineering community due to recent advances in computational techniques and an enabling environment. However, often they are treated as black-box tools, which should be examined for their robustness and range of validity/applicability. This research presents an evaluation of their application to flow/transport in porous media, where exact solutions (obtained from physics-based models) are used to train ML algorithms to establish when and how these ML algorithms fail to predict the first order flow-physics. Exact solutions are used so as not to introduce artifacts from the numerical solutions. To test, validate, and predict the physics of flow in porous media using ML algorithms, one needs a reliable set of data that may not be readily available and/or the data might not be in suitable form (i.e. incomplete/missing reporting, metadata, or other relevant peripheral information). To overcome this, we first generate structured datasets for flow in porous media using simple representative building blocks of flow physics such as Buckley-Leverett, convection-dispersion equations, and viscous fingering. Then, the outcomes from those equations are fed into ML algorithms to examine their robustness and predictive strength of the key features, such as breakthrough time, and saturation and component profiles. In this research, we show that a physics-informed ML algorithm can capture the physical behavior and effects of various physical parameters (even when shocks and sharp gradients are present). Further the ML approach can be utilized to solve inverse problems to estimate physical parameters.

Original languageEnglish (US)
Title of host publicationSociety of Petroleum Engineers - SPE Annual Technical Conference and Exhibition 2021, ATCE 2021
PublisherSociety of Petroleum Engineers (SPE)
ISBN (Electronic)9781613997864
DOIs
StatePublished - 2021
EventSPE Annual Technical Conference and Exhibition 2021, ATCE 2021 - Dubai, United Arab Emirates
Duration: Sep 21 2021Sep 23 2021

Publication series

NameProceedings - SPE Annual Technical Conference and Exhibition
Volume2021-September
ISSN (Electronic)2638-6712

Conference

ConferenceSPE Annual Technical Conference and Exhibition 2021, ATCE 2021
Country/TerritoryUnited Arab Emirates
CityDubai
Period9/21/219/23/21

All Science Journal Classification (ASJC) codes

  • Fuel Technology
  • Energy Engineering and Power Technology

Fingerprint

Dive into the research topics of 'Evaluation of machine learning methodologies using simple physics based conceptual models for flow in porous media'. Together they form a unique fingerprint.

Cite this