# Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces

## TL;DR

This paper develops a machine learning-based method to accurately model small molecules' potential energy surfaces and forces, enabling detailed molecular dynamics simulations with near-quantum accuracy.

## Contribution

It introduces the symmetrized gradient-domain machine learning (sGDML) approach for constructing high-accuracy force fields from limited data, applicable to small molecules.

## Key findings

- sGDML accurately reproduces high-level ab initio forces
- The method captures complex electronic interactions without restrictions
- Molecular dynamics reveal new insights into small molecule behavior

## Abstract

We present the construction of molecular force fields for small molecules (less than 25 atoms) using the recently developed symmetrized gradient-domain machine learning (sGDML) approach [Chmiela et al., Nat. Commun. 9, 3887 (2018); Sci. Adv. 3, e1603015 (2017)]. This approach is able to accurately reconstruct complex high-dimensional potential-energy surfaces from just a few 100s of molecular conformations extracted from ab initio molecular dynamics trajectories. The data efficiency of the sGDML approach implies that atomic forces for these conformations can be computed with high-level wavefunction-based approaches, such as the "gold standard" CCSD(T) method. We demonstrate that the flexible nature of the sGDML model recovers local and non-local electronic interactions (e.g. H-bonding, proton transfer, lone pairs, changes in hybridization states, steric repulsion and $n\to\pi^*$ interactions) without imposing any restriction on the nature of interatomic potentials. The analysis of sGDML molecular dynamics trajectories yields new qualitative insights into dynamics and spectroscopy of small molecules close to spectroscopic accuracy.