Transfer-learned potential energy surfaces: Toward microsecond-scale molecular dynamics simulations in the gas phase...

The rise of machine learning has greatly influenced the field of computational chemistry and atomistic molecular dynamics simulations in particular. One of its most exciting prospects is the development of accurate, full-dimensional potential energy surfaces (PESs) for molecules and clusters, which, however, often require thousands to tens of thousands of ab initio data points restricting the community to medium sized molecules and/or lower levels of theory (e.g., density functional theory). Transfer learning, which improves a global PES from a lower to a higher level of theory, offers a data efficient alternative requiring only a fraction of the high-level data (on the order of 100 are found to be sufficient for malonaldehyde). This work demonstrates that even with Hartree-Fock theory and a double-zeta basis set as the lower level model, transfer learning yields coupled-cluster single double triple [CCSD(T)]-level quality for H-transfer barrier energies, harmonic frequencies, and H-transfer tunneling splittings. Most importantly, finite-temperature molecular dynamics simulations on the sub-μs time scale in the gas phase are possible and the infrared spectra determined from the transfer-learned PESs are in good agreement with the experiment. It is concluded that routine, long-time atomistic simulations on PESs fulfilling CCSD(T)-standards become possible.