Fang Liu, Ph.D.
Abstract
Machine learning (ML) and big data play increasingly critical roles in chemical discovery. However, datasets (both computational and experimental) and ML models remain scarce for solvated molecules and molecule assemblies. My group leverages GPU-accelerated quantum chemistry and machine learning to address these gaps. We developed AutoSolvate, an open-source toolkit, and launched AutoSolvateWeb, a chatbot-assisted, cloud-based platform, that enable efficient generation of datasets for solvated molecules and Δ-ML model training. For molecular assemblies, we developed a size-transferable machine-learned exciton model that reduces computational costs by tens of thousands of folds without sacrificing accuracy. As a proof of concept, we successfully trained an ML model to detect material phase transitions in situ using angle-resolved photoemission spectroscopy (ARPES).
When: September 5, 2025
Where: North Classroom 1130
Time: 11:00 am - 12:00pm