A scientific machine learning framework to understand flash graphene synthesis
Kianoosh Sattari, Lucas Eddy, Jacob L. Beckham, Kevin M. Wyss, Richard Byfield, Long Qian, James M. Tour, Jian Lin
Abstract
The SML model was trained on both direct experimental and indirect physics-informed features to predict graphene quality synthesized from Flash Joule heating. With an R 2 of 0.81, the model performs better compared to 0.73 without indirect features.
Topics & Concepts
Flash (photography)GrapheneJoule heatingJoule (programming language)Computer scienceQuality (philosophy)NanotechnologyArtificial intelligenceMaterials sciencePhysicsEngineeringElectrical engineeringQuantum mechanicsComposite materialOpticsEfficient energy useGraphene research and applicationsMachine Learning in Materials ScienceThermal properties of materials