Recent advances in nanoscience have enabled the synthesis of nanomaterials, such as graphene, from low-value or waste materials through flash Joule heating. However, the complex and entangled variables that govern nanocrystal formation in the Joule heating process remain poorly understood. In this work, machine learning (ML) models are constructed to explore the factors that drive the transformation of amorphous carbon into graphene nanocrystals during flash Joule heating. Feature importance assays and decision trees extracted from ML models reveal key factors in the selection of starting materials and the role of stochastic fluctuations in system resistance in flash Joule heating synthesis. Additionally, partial dependence analyses show the importance of energy density as a predictor of crystallinity, implying a progression from reaction-limited to diffusion-limited kinetics as flash Joule heating parameters change. Finally, Bayesian optimization algorithms leverage the models' understanding of Joule heating to automatically improve bulk crystallinity over many reactions. These results illustrate the power of ML as a tool to study complex synthetic processes and enable the synthesis of 2D crystals with desired properties by flash Joule heating.

Machine learning guided flash graphene synthesis

Fall 2022 abstracts, posters, and presentations will launch in mid-September.

ACS Fall 2022

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.