(66a) Physics-Informed and Machine-Learned Methods for Chemical Discovery

The next generation of functional materials for catalysis, energy storage, and nanoelectronics, demands understanding and precise control over electron transfer (ET). My research group will pioneer physics-informed machine learning methods to not only predict ET rates across diverse systems but also inverse-design materials with tailored charge transport properties. By merging quantum mechanical principles with deep learning architectures, my group will develop interpretable, high-throughput frameworks that accelerate the discovery of optimal catalysts, interfaces, and molecular devices. Beyond predictions, my group will also explore dynamic control strategies and bridge fundamental theory with real-world applications.