A dual-cutoff machine-learned potential for condensed organic systems obtained via uncertainty-guided active learning

TL;DR

This paper introduces a machine-learned potential with a dual descriptor for organic systems, trained via active learning, achieving high accuracy in predicting densities, vibrational frequencies, and heat capacities in condensed phases.

Contribution

It develops a dual-cutoff, uncertainty-guided active learning approach for creating an efficient and accurate MLP for organic condensed systems, combining short- and long-range interactions.

Findings

Densities within 4% of experimental values

Vibrational frequencies with RMS error < 1 THz

Heat capacities within 11% of experiments

Abstract

Machine-learned potentials (MLPs) trained on ab initio data combine the computational efficiency of classical interatomic potentials with the accuracy and generality of the first-principles method used in the creation of the respective training set. In this work, we implement and train a MLP to obtain an accurate description of the potential energy surface and property predictions for organic compounds, as both single molecules and in the condensed phase. We devise a dual descriptor, based on the atomic cluster expansion (ACE), that couples an information-rich short-range description with a coarser long-range description that captures weak intermolecular interactions. We employ uncertainty-guided active learning for the training set generation, creating a dataset that is comparatively small for the breadth of application and consists of alcohols, alkanes, and an adipate. Utilizing that MLP, we calculate densities of those systems of varying chain lengths as a function of temperature, obtaining a discrepancy of less than 4% compared with experiment. Vibrational frequencies calculated with the MLP have a root mean square error of less than 1 THz compared to DFT. The heat capacities of condensed systems are within 11% of experimental findings, which is strong evidence that the dual descriptor provides an accurate framework for the prediction of both short-range intramolecular and long-range intermolecular interactions.