Predicting Effective Diffusivity of Porous Media from Images by Deep Learning

Simple item page
dc.contributor.authorWu, Haiyien
dc.contributor.authorFang, Wen-Zhenen
dc.contributor.authorKang, Qinjunen
dc.contributor.authorTao, Wen-Quanen
dc.contributor.authorQiao, Ruien
dc.contributor.departmentMechanical Engineeringen
dc.date.accessioned2021-08-04T14:57:05Zen
dc.date.available2021-08-04T14:57:05Zen
dc.date.issued2019-12-31en
dc.date.updated2021-08-04T14:56:53Zen
dc.description.abstractWe report the application of machine learning methods for predicting the effective diffusivity (De) of two-dimensional porous media from images of their structures. Pore structures are built using reconstruction methods and represented as images, and their effective diffusivity is computed by lattice Boltzmann (LBM) simulations. The datasets thus generated are used to train convolutional neural network (CNN) models and evaluate their performance. The trained model predicts the effective diffusivity of porous structures with computational cost orders of magnitude lower than LBM simulations. The optimized model performs well on porous media with realistic topology, large variation of porosity (0.28–0.98), and effective diffusivity spanning more than one order of magnitude (0.1 ≲ De < 1), e.g., >95% of predicted De have truncated relative error of <10% when the true De is larger than 0.2. The CNN model provides better prediction than the empirical Bruggeman equation, especially for porous structure with small diffusivity. The relative error of CNN predictions, however, is rather high for structures with De < 0.1. To address this issue, the porosity of porous structures is encoded directly into the neural network but the performance is enhanced marginally. Further improvement, i.e., 70% of the CNN predictions for structures with true De < 0.1 have relative error <30%, is achieved by removing trapped regions and dead-end pathways using a simple algorithm. These results suggest that deep learning augmented by field knowledge can be a powerful technique for predicting the transport properties of porous media. Directions for future research of machine learning in porous media are discussed based on detailed analysis of the performance of CNN models in the present work.en
dc.description.versionPublished versionen
dc.format.extent12 page(s)en
dc.format.mediumElectronicen
dc.format.mimetypeapplication/pdfen
dc.identifierARTN 20387 (Article number)en
dc.identifier.doihttps://doi.org/10.1038/s41598-019-56309-xen
dc.identifier.eissn2045-2322en
dc.identifier.issn2045-2322en
dc.identifier.issue1en
dc.identifier.orcidQiao, Rui [0000-0001-5219-5530]en
dc.identifier.other10.1038/s41598-019-56309-x (PII)en
dc.identifier.pmid31892713 (pubmed)en
dc.identifier.urihttp://hdl.handle.net/10919/104573en
dc.identifier.volume9en
dc.language.isoenen
dc.publisherNatureen
dc.relation.urihttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000508985300008&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=930d57c9ac61a043676db62af60056c1en
dc.rightsCreative Commons Attribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en
dc.subjectSTRUCTURE-PROPERTY LINKAGESen
dc.subjectPERMEABILITYen
dc.subjectSIMULATIONen
dc.titlePredicting Effective Diffusivity of Porous Media from Images by Deep Learningen
dc.title.serialScientific Reportsen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.otherArticleen
dc.type.otherJournalen
dcterms.dateAccepted2019-11-30en
pubs.organisational-group/Virginia Techen
pubs.organisational-group/Virginia Tech/Engineeringen
pubs.organisational-group/Virginia Tech/Engineering/Mechanical Engineeringen
pubs.organisational-group/Virginia Tech/All T&R Facultyen
pubs.organisational-group/Virginia Tech/Engineering/COE T&R Facultyen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Predicting Effective Diffusivity of Porous Media from Images by Deep Learning.pdf
Size:
4 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

All Faculty Deposits
Scholarly Works, Mechanical Engineering