Global machine learning potentials for molecular crystals

Ivan Žugec

doi:10.1063/5.0196232

Global machine learning potentials for molecular crystals

2024-04-16

2

OA

AI

DOI：10.1063/5.0196232

Original

Original request for help

Save

Abstract

En 中文

Molecular crystals are difficult to model with accurate first-principles methods due to large unit cells. On the other hand, accurate modeling is required as polymorphs often differ by only 1 kJ/mol. Machine learning interatomic potentials promise to provide accuracy of the baseline first-principles methods with a cost lower by orders of magnitude. Using the existing databases of the density functional theory calculations for molecular crystals and molecules, we train global machine learning interatomic potentials, usable for any molecular crystal. We test the performance of the potentials on experimental benchmarks and show that they perform better than classical force fields and, in some cases, are comparable to the density functional theory calculations.

Keywords:

DATA-EFFICIENT

PATH

DFT

Global machine learning potentials for molecular crystals

Abstract

Journal

Organization