I use multiscale simulations to understand reaction thermodynamics and kinetics across atomic, molecular, and mesoscale regimes. This approach aims to study complex systems such as heterogeneous catalysis, next generation batteries, and lignin based materials under realistic chemical environments.
I develop hybrid modeling frameworks that combine first-principles methods with data-driven models to overcome the limitations of each approach alone. By integrating physics based insight with flexible learning tools, this research aims to uncover hidden mechanisms in complex energy and environmental systems.
I study model based optimization to identify the best input conditions and control strategies needed to achieve desired system level performance. This work connects predictive modeling with decision making for efficient design and operation of chemical and energy processes.
I explore generative AI models to go beyond conventional prediction tasks by improving extrapolation, discovering new materials, and estimating reaction kinetic parameters in chemically complex systems. This direction aims to expand both the interpretability and the practical design value of computational modeling.