A scientific machine learning framework to understand flash graphene synthesis

Simple item page
dc.citation.firstpage1209en_US
dc.citation.journalTitleDigital Discoveryen_US
dc.citation.lastpage1218en_US
dc.citation.volumeNumber2en_US
dc.contributor.authorSattari, Kianooshen_US
dc.contributor.authorEddy, Lucasen_US
dc.contributor.authorBeckham, Jacob L.en_US
dc.contributor.authorWyss, Kevin M.en_US
dc.contributor.authorByfield, Richarden_US
dc.contributor.authorQian, Longen_US
dc.contributor.authorTour, James M.en_US
dc.contributor.authorLin, Jianen_US
dc.contributor.orgNanoCarbon Centeren_US
dc.contributor.orgWelch Institute for Advanced Materialsen_US
dc.date.accessioned2024-05-08T18:56:13Zen_US
dc.date.available2024-05-08T18:56:13Zen_US
dc.date.issued2023en_US
dc.description.abstractFlash Joule heating (FJH) is a far-from-equilibrium (FFE) processing method for converting low-value carbon-based materials to flash graphene (FG). Despite its promises in scalability and performance, attempts to explore the reaction mechanism have been limited due to the complexities involved in the FFE process. Data-driven machine learning (ML) models effectively account for the complexities, but the model training requires a considerable amount of experimental data. To tackle this challenge, we constructed a scientific ML (SML) framework trained by using both direct processing variables and indirect, physics-informed variables to predict the FG yield. The indirect variables include current-derived features (final current, maximum current, and charge density) predicted from the proxy ML models and reaction temperatures simulated from multi-physics modeling. With the combined indirect features, the final ML model achieves an average R2 score of 0.81 ± 0.05 and an average RMSE of 12.1% ± 2.0% in predicting the FG yield, which is significantly higher than the model trained without them (R2 of 0.73 ± 0.05 and an RMSE of 14.3% ± 2.0%). Feature importance analysis validates the key roles of these indirect features in determining the reaction outcome. These results illustrate the promise of this SML to elucidate FFE material synthesis outcomes, thus paving a new avenue to processing other datasets from the materials systems involving the same or different FFE processes.en_US
dc.identifier.citationSattari, K., Eddy, L., L. Beckham, J., M. Wyss, K., Byfield, R., Qian, L., M. Tour, J., & Lin, J. (2023). A scientific machine learning framework to understand flash graphene synthesis. Digital Discovery, 2(4), 1209–1218. https://doi.org/10.1039/D3DD00055Aen_US
dc.identifier.digitald3dd00055aen_US
dc.identifier.doihttps://doi.org/10.1039/D3DD00055Aen_US
dc.identifier.urihttps://hdl.handle.net/1911/115697en_US
dc.language.isoengen_US
dc.publisherRoyal Society of Chemistryen_US
dc.rightsExcept where otherwise noted, this work is licensed under a Creative Commons Attribution-NonCommercial (CC BY-NC) license. Permission to reuse, publish, or reproduce the work beyond the terms of the license or beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.en_US
dc.rights.urihttps://creativecommons.org/licenses/by-nc/3.0/en_US
dc.titleA scientific machine learning framework to understand flash graphene synthesisen_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:
d3dd00055a.pdf
Size:
940.54 KB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications
Chemistry Publications
Computer Science Publications
Materials Science and NanoEngineering Publications