Self-supervised learning and prediction of microstructure evolution with convolutional recurrent neural networks

Simple item page
dc.citation.articleNumber100243en_US
dc.citation.issueNumber5en_US
dc.citation.journalTitlePatternsen_US
dc.citation.volumeNumber2en_US
dc.contributor.authorYang, Kaiqien_US
dc.contributor.authorCao, Yifanen_US
dc.contributor.authorZhang, Youtianen_US
dc.contributor.authorFan, Shaoxunen_US
dc.contributor.authorTang, Mingen_US
dc.contributor.authorAberg, Danielen_US
dc.contributor.authorSadigh, Babaken_US
dc.contributor.authorZhou, Feien_US
dc.date.accessioned2021-06-07T20:22:21Zen_US
dc.date.available2021-06-07T20:22:21Zen_US
dc.date.issued2021en_US
dc.description.abstractMicrostructural evolution is a key aspect of understanding and exploiting the processing-structure-property relationship of materials. Modeling microstructure evolution usually relies on coarse-grained simulations with evolution principles described by partial differential equations (PDEs). Here we demonstrate that convolutional recurrent neural networks can learn the underlying physical rules and replace PDE-based simulations in the prediction of microstructure phenomena. Neural nets are trained by self-supervised learning with image sequences from simulations of several common processes, including plane-wave propagation, grain growth, spinodal decomposition, and dendritic crystal growth. The trained networks can accurately predict both short-term local dynamics and long-term statistical properties of microstructures assessed herein and are capable of extrapolating beyond the training datasets in spatiotemporal domains and configurational and parametric spaces. Such a data-driven approach offers significant advantages over PDE-based simulations in time-stepping efficiency and offers a useful alternative, especially when the material parameters or governing PDEs are not well determined.en_US
dc.identifier.citationYang, Kaiqi, Cao, Yifan, Zhang, Youtian, et al.. "Self-supervised learning and prediction of microstructure evolution with convolutional recurrent neural networks." <i>Patterns,</i> 2, no. 5 (2021) Elsevier: https://doi.org/10.1016/j.patter.2021.100243.en_US
dc.identifier.digital1-s2-0-S2666389921000635-mainen_US
dc.identifier.doihttps://doi.org/10.1016/j.patter.2021.100243en_US
dc.identifier.urihttps://hdl.handle.net/1911/110667en_US
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.rightsThis is an open access article under the CC BY-NC-ND licenseen_US
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en_US
dc.titleSelf-supervised learning and prediction of microstructure evolution with convolutional recurrent neural networksen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2-0-S2666389921000635-main.pdf
Size:
2.2 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
Materials Science and NanoEngineering Publications