Feng's paper published in ACS Applied Materials & Interfaces - Optimizing WS2 Growth with Bayesian Optimization

Feng's paper published in ACS Applied Materials & Interfaces - Optimizing WS2 Growth with Bayesian Optimization

Bayesian Optimization for Controlled Chemical Vapor Deposition Growth of WS2
Bayesian Optimization for Controlled Chemical Vapor Deposition Growth of WS2 © 2024 American Chemical Society

Accelerating 2D Material Synthesis with Machine Learning

Published in ACS Applied Materials & Interfaces, 2024

Our latest research employs Bayesian optimization (BO), a machine learning technique, to optimize the growth of monolayer WS2 through chemical vapor deposition (CVD). By maximizing photoluminescence (PL) intensity, we achieved an impressive 86.6% increase in only 13 rounds of optimization. This work demonstrates the potential of BO to surpass traditional methods like random search, offering faster convergence to optimal growth conditions.

Read more on the impact of ML-driven approaches in advancing 2D materials for next-generation technologies.

Read Full Paper