{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T14:29:55Z","timestamp":1767968995083,"version":"3.49.0"},"reference-count":48,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T00:00:00Z","timestamp":1715299200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/3.0"},{"start":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T00:00:00Z","timestamp":1715299200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Modeling effective transport properties of 3D porous media, such as permeability, at multiple scales is challenging as a result of the combined complexity of the pore structures and fluid physics\u2014in particular, confinement effects which vary across the nanoscale to the microscale. While numerical simulation is possible, the computational cost is prohibitive for realistic domains, which are large and complex. Although machine learning (ML) models have been proposed to circumvent simulation, none so far has simultaneously accounted for heterogeneous 3D structures, fluid confinement effects, and multiple simulation resolutions. By utilizing numerous computer science techniques to improve the scalability of training, we have for the first time developed a general flow model that accounts for the pore-structure and corresponding physical phenomena at scales from Angstrom to the micrometer. Using synthetic computational domains for training, our ML model exhibits strong performance (<jats:italic>R<\/jats:italic>\n                  <jats:sup>2<\/jats:sup> = 0.9) when tested on extremely diverse real domains at multiple scales.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad45af","type":"journal-article","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T22:43:21Z","timestamp":1714517001000},"page":"025039","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Learning a general model of single phase flow in complex 3D porous media"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2404-3975","authenticated-orcid":true,"given":"Javier E","family":"Santos","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9934-9004","authenticated-orcid":true,"given":"Agnese","family":"Marcato","sequence":"additional","affiliation":[]},{"given":"Qinjun","family":"Kang","sequence":"additional","affiliation":[]},{"given":"Mohamed","family":"Mehana","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"O\u2019Malley","sequence":"additional","affiliation":[]},{"given":"Hari","family":"Viswanathan","sequence":"additional","affiliation":[]},{"given":"Nicholas","family":"Lubbers","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,5,10]]},"reference":[{"key":"mlstad45afbib1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"mlstad45afbib2","first-page":"pp 248","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"mlstad45afbib3","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"mlstad45afbib4","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1016\/j.advwatres.2012.07.018","article-title":"X-ray imaging and analysis techniques for quantifying pore-scale structure and processes in subsurface porous medium systems","volume":"51","author":"Wildenschild","year":"2013","journal-title":"Adv. Water Resour."},{"key":"mlstad45afbib5","author":"Mackenzie","year":"2005"},{"key":"mlstad45afbib6","doi-asserted-by":"publisher","first-page":"8530","DOI":"10.1021\/acs.iecr.1c04760","article-title":"From computational fluid dynamics to structure interpretation via neural networks: an application to flow and transport in porous media","volume":"3","author":"Marcato","year":"2022","journal-title":"Indust. Eng. Chem. Res."},{"key":"mlstad45afbib7","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1063\/5.0063904","article-title":"Point-cloud deep learning of porous media for permeability prediction","volume":"33","author":"Kashefi","year":"2021","journal-title":"Phys. Fluids"},{"key":"mlstad45afbib8","first-page":"4","article-title":"ML-LBM: predicting and accelerating steady state flow simulation in porous media with convolutional neural networks","volume":"0123456789","author":"Da Wang","year":"2021","journal-title":"Trans. Porous Med."},{"key":"mlstad45afbib9","doi-asserted-by":"publisher","first-page":"8871","DOI":"10.3390\/en15238871","article-title":"Using machine learning to predict multiphase flow through complex fractures","volume":"15","author":"Ting","year":"2022","journal-title":"Energies"},{"key":"mlstad45afbib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.coelec.2022.101101","article-title":"A 3D convolutional neural network accurately predicts the permeability of gas diffusion layer materials directly from image data","volume":"35","author":"Cawte","year":"2022","journal-title":"Curr. Opin. Electrochem."},{"key":"mlstad45afbib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compositesa.2022.106973","article-title":"Deep learning accelerated prediction of the permeability of fibrous microstructures","volume":"158","author":"Caglar","year":"2022","journal-title":"Composites A"},{"key":"mlstad45afbib12","doi-asserted-by":"publisher","DOI":"10.1016\/j.petrol.2021.109589","article-title":"Permeability prediction of low-resolution porous media images using autoencoder-based convolutional neural network","volume":"208","author":"Zhang","year":"2022","journal-title":"J. Pet. Sci. Eng."},{"key":"mlstad45afbib13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jhydrol.2022.127473","article-title":"Predicting permeability from 3D rock images based on CNN with physical information","volume":"606","author":"Tang","year":"2022","journal-title":"J. Hydrol."},{"key":"mlstad45afbib14","article-title":"Modeling the 4D discharge of lithium-ion batteries with a multiscale time-dependent deep learning framework","volume":"63","author":"Marcato","year":"2023","journal-title":"Energy Storage Mater."},{"key":"mlstad45afbib15","article-title":"lRock-Net: Assessing the Utility of Machine Learning to Initialize 3D Electric Potential Simulations","author":"Chang","year":"2022"},{"key":"mlstad45afbib16","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1016\/j.fmre.2021.12.010","article-title":"Identifying the dominant transport mechanism in single nanoscale pores and 3D nanoporous media","volume":"3","author":"Yin","year":"2022","journal-title":"Fundam. Res."},{"key":"mlstad45afbib17","doi-asserted-by":"publisher","first-page":"55","DOI":"10.2118\/07-10-06","article-title":"Nanoscale gas flow in shale gas sediments","volume":"46","author":"Javadpour","year":"2007","journal-title":"J. Can. Pet. Technol."},{"key":"mlstad45afbib18","first-page":"pp 200","article-title":"The permeability of porous media to liquids and gases","volume":"vol 1941","author":"Klinkenberg","year":"1941"},{"key":"mlstad45afbib19","doi-asserted-by":"publisher","first-page":"16","DOI":"10.2118\/09-08-16-DA","article-title":"Nanopores and apparent permeability of gas flow in mudrocks (Shales and Siltstone)","volume":"48","author":"Javadpour","year":"2009","journal-title":"J. Can. Pet. Technol."},{"key":"mlstad45afbib20","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1016\/j.fuel.2016.05.011","article-title":"Apparent gas permeability in an organic-rich shale reservoir","volume":"181","author":"Song","year":"2016","journal-title":"Fuel"},{"key":"mlstad45afbib21","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1016\/j.coal.2016.03.015","article-title":"Direct simulation of supercritical gas flow in complex nanoporous media and prediction of apparent permeability","volume":"159","author":"Landry","year":"2016","journal-title":"Int. J. Coal Geol."},{"key":"mlstad45afbib22","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1306\/08171111061","article-title":"Spectrum of pore types and networks in mudrocks and a descriptive classification for matrix-related mudrock pores","volume":"96","author":"Loucks","year":"2012","journal-title":"AAPG Bulletin"},{"key":"mlstad45afbib23","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1130\/0091-7613(1999)027<0799:EOPLSF>2.3.CO;2","article-title":"Extent of power-law scaling for natural fractures in rock","volume":"27","author":"Marrett","year":"1999","journal-title":"Geology"},{"key":"mlstad45afbib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.91.033004","article-title":"Generalized lattice Boltzmann model for flow through tight porous media with Klinkenberg\u2019s effect","volume":"91","author":"Chen","year":"2015","journal-title":"Phys. Rev. E"},{"key":"mlstad45afbib25","doi-asserted-by":"publisher","first-page":"1171","DOI":"10.1016\/0042-207X(93)90342-8","article-title":"Experimental data and theoretical modeling of gas flows through metal capillary leaks","volume":"44","author":"Tison","year":"1993","journal-title":"Vacuum"},{"key":"mlstad45afbib26","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s10404-008-0311-7","article-title":"Experiments on rarefied gas flows through tubes","volume":"6","author":"Marino","year":"2009","journal-title":"Microfluid. Nanofluid."},{"key":"mlstad45afbib27","doi-asserted-by":"publisher","first-page":"61","DOI":"10.2138\/rmg.2015.80.04","article-title":"Characterization and analysis of porosity and pore structures","volume":"80","author":"Anovitz","year":"2015","journal-title":"Rev. Mineral. Geochem."},{"key":"mlstad45afbib28","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1306\/08151110188","article-title":"Microstructural investigation of gas shales in two and three dimensions using nanometer-scale resolution imaging","volume":"96","author":"Curtis","year":"2012","journal-title":"AAPG Bulletin"},{"key":"mlstad45afbib29","doi-asserted-by":"publisher","DOI":"10.2118\/131771-MS)","article-title":"Micro-structural studies of gas shales","author":"Sondergeld","year":"2010"},{"key":"mlstad45afbib30","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1007\/s11242-013-0191-5","article-title":"Multiscale, multiphysics network modeling of shale matrix gas flows","volume":"99","author":"Mehmani","year":"2013","journal-title":"Transp. Porous Med."},{"key":"mlstad45afbib31","article-title":"Pore scale study of water adsorption and subsequent methane transport in clay in the presence of wettability heterogeneity","author":"Rui","year":"2020"},{"key":"mlstad45afbib32","doi-asserted-by":"publisher","first-page":"1215","DOI":"10.1016\/j.scib.2018.08.006","article-title":"Seeing permeability from images: fast prediction with convolutional neural networks","volume":"63","author":"Jinlong","year":"2018","journal-title":"Sci. Bulletin"},{"key":"mlstad45afbib33","doi-asserted-by":"publisher","DOI":"10.1016\/j.earscirev.2021.103555","article-title":"Deep learning in pore scale imaging and modeling","volume":"215","author":"Da Wang","year":"2021","journal-title":"Earth-Sci. Rev."},{"key":"mlstad45afbib34","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11242-021-01617-y","article-title":"Computationally efficient multiscale neural networks applied to fluid flow in complex 3D porous media","volume":"140","author":"Santos","year":"2021","journal-title":"Trans. Porous Med."},{"key":"mlstad45afbib35","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1038\/s41597-022-01664-0","article-title":"A dataset of 3D structural and simulated transport properties of complex porous media","volume":"9","author":"Santos","year":"2022","journal-title":"Sci. Data"},{"key":"mlstad45afbib36","article-title":"Digital rocks portal: a repository for porous media images","author":"Prodanovic","year":"2015"},{"key":"mlstad45afbib37","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2022.101097","article-title":"MPLBM-UT: Multiphase LBM library for permeable media analysis","volume":"18","author":"Santos","year":"2022","journal-title":"SoftwareX"},{"key":"mlstad45afbib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2022.107797","article-title":"3D Dataset of binary images: a collection of synthetically created digital rock images of complex media","volume":"40","author":"Santos","year":"2022","journal-title":"Data Brief."},{"key":"mlstad45afbib39","article-title":"Belgian Fieldstone","author":"Bultreys","year":"2020"},{"key":"mlstad45afbib40","article-title":"Luc Van Hoorebeke, and Veerle Cnudde","author":"Bultreys","year":"2018"},{"key":"mlstad45afbib41","article-title":"Saturated solute transport micro-CT dataset in sintered glass and Bentheimer sandstone","author":"Van Offenwert","year":"2019"},{"key":"mlstad45afbib42","article-title":"Decane and brine injected into Estaillades carbonate-steady-state experiments","author":"Spurin","year":"2021"},{"key":"mlstad45afbib43","article-title":"Moura Coal","author":"Armstrong","year":"2017"},{"key":"mlstad45afbib44","article-title":"High resolution x-ray micro-tomography datasets for in-situ effective contact angle analysis in carbonate rocks","author":"Singh","year":"2018"},{"key":"mlstad45afbib45","article-title":"Facebook AI Research a convnet for the 2020s","author":"Liu","year":"2022"},{"key":"mlstad45afbib46","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"mlstad45afbib47","doi-asserted-by":"publisher","DOI":"10.1029\/2021MS002921","article-title":"Benefits of stochastic weight averaging in developing neural network radiation scheme for numerical weather prediction","volume":"14","author":"Song","year":"2022","journal-title":"J. Adv. Mod. Earth Syst."},{"key":"mlstad45afbib48","article-title":"PyTorch: an imperative style, high-performance deep learning library","author":"Paszke","year":"2019"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T09:03:22Z","timestamp":1715331802000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad45af"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,10]]},"references-count":48,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,5,10]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad45af","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,10]]},"assertion":[{"value":"Learning a general model of single phase flow in complex 3D porous media","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-25","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-04-30","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-05-10","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}