Excited-State Wave Functions and Energies Predicted by Machine Learning Based on Graph Neural Networks

Accurate and efficient simulation of photoinduced dynamics in materials remains a significant challenge due to the computational cost of excited-state electronic structure calculations and the necessity to account for excitonic effects. In this work, we present a machine learning (ML)-accelerated approach to nonadiabatic molecular dynamics simulations that incorporates excitonic effects by predicting excited-state wave functions via configuration interaction coefficients and excitation energies using a graph neural network (GNN) architecture. The GNN model leverages molecular orbital information from ground-state calculations to construct input graphs, enabling efficient and accurate prediction of relevant excited-state wave functions and energies required for ab initio-based fewest-switches surface hopping simulations. Benchmarking on a zinc phthalocyanine-fullerene (ZnPc-C₆₀) donor-acceptor system reveals that these ML-predicted properties agree closely with those obtained from linear-response time-dependent density functional theory calculations while boosting the computational efficiency significantly. The ML-accelerated simulations reproduce excited-state dynamics with high fidelity, demonstrating the methodological capability to study complex photodynamical processes in large systems. This work provides a general and scalable framework for efficient excited-state dynamics simulations in materials where excitonic effects play a vital role.