Several quantum chemistry methods combine wave function theory and density functional theory to obtain a balance between accuracy and efficiency in the predictions of electronic excited states. However, predictions of the photoexcitation of macromolecules and materials remain computationally expensive. In this talk, we present machine learning strategies to improve the efficiency of two methods that combine wave function theory and density functional theory, multiconfiguration pair-density functional theory and a method based on many-body perturbation theory. Instead of mapping between the molecular or materials structures and energy values, we map between key quantities within their respective formalisms.

Accelerate combined wave function and density functional theory approaches for electronic excited states by machine learning

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.