Automatic discovery of photoisomerization mechanisms with nanosecond machine learning photodynamics simulations.

Photochemical reactions are widely used by academic and industrial researchers to construct complex molecular architectures mechanisms that often require harsh reaction conditions. Photodynamics simulations provide time-resolved snapshots of molecular excited-state structures required to understand and predict reactivities and chemoselectivities. Molecular excited-states are often nearly degenerate and require computationally intensive multiconfigurational quantum mechanical methods, especially at conical intersections. Non-adiabatic molecular dynamics require thousands of these computations per trajectory, which limits simulations to ∼1 picosecond for most organic photochemical reactions. Westermayr recently introduced a neural-network-based method to accelerate the predictions of electronic properties and pushed the simulation limit to 1 ns for the model system, methylenimmonium cation (CHNH ). We have adapted this methodology to develop the Python-based, Python Rapid Artificial Intelligence Molecular Dynamics (PyRAIMD) software for the - isomerization of -hexafluoro-2-butene and the 4π-electrocyclic ring-closing of a norbornyl hexacyclodiene. We performed a 10 ns simulation for -hexafluoro-2-butene in just 2 days. The same simulation would take approximately 58 years with traditional multiconfigurational photodynamics simulations. We generated training data by combining Wigner sampling, geometrical interpolations, and short-time quantum chemical trajectories to adaptively sample sparse data regions along reaction coordinates. The final data set of the - isomerization and the 4π-electrocyclic ring-closing model has 6207 and 6267 data points, respectively. The training errors in energy using feedforward neural networks achieved chemical accuracy (0.023-0.032 eV). The neural network photodynamics simulations of -hexafluoro-2-butene agree with the quantum chemical calculations showing the formation of the -product and reactive carbene intermediate. The neural network trajectories of the norbornyl cyclohexadiene corroborate the low-yielding -product, which was absent in the quantum chemical trajectories, and revealed subsequent thermal reactions in 1 ns.