The Bigger the Better? Accurate Molecular Potential Energy Surfaces from Minimalist Neural Networks
This addresses the need for efficient and reliable PESs in molecular dynamics simulations, offering a novel solution to a known bottleneck in computational chemistry.
The paper tackles the problem of accurately representing molecular potential energy surfaces (PESs) for atomistic simulations by introducing KerNN, a combined kernel/neural network approach that reduces parameters, speeds up training and evaluation by orders of magnitude, and improves extrapolation capabilities while retaining high accuracy.
Atomistic simulations are a powerful tool for studying the dynamics of molecules, proteins, and materials on wide time and length scales. Their reliability and predictiveness, however, depend directly on the accuracy of the underlying potential energy surface (PES). Guided by the principle of parsimony this work introduces KerNN, a combined kernel/neural network-based approach to represent molecular PESs. Compared to state-of-the-art neural network PESs the number of learnable parameters of KerNN is significantly reduced. This speeds up training and evaluation times by several orders of magnitude while retaining high prediction accuracy. Importantly, using kernels as the features also improves the extrapolation capabilities of KerNN far beyond the coverage provided by the training data which solves a general problem of NN-based PESs. KerNN applied to spectroscopy and reaction dynamics shows excellent performance on test set statistics and observables including vibrational bands computed from classical and quantum simulations.