Breaking the Coupled Cluster Barrier for Machine Learned Potentials of Large Molecules: The Case of 15-atom Acetylacetone

TL;DR

This paper demonstrates a machine learning approach that accurately reproduces coupled-cluster level potential energy surfaces for large molecules, exemplified by acetylacetone, surpassing traditional lower-level methods in barrier height predictions.

Contribution

The study introduces a delta-machine learning method that achieves CCSD(T)-level accuracy for large molecules using limited high-level data, significantly improving PES predictions.

Findings

Achieved CCSD(T)-level barrier height with limited data

Improved tunneling splitting estimates

Validated method on 15-atom acetylacetone

Abstract

Machine-learned potential energy surfaces (PESs) for molecules with more than 10 atoms are typically forced to use lower-level electronic structure methods such as density functional theory and second-order Moller-Plesset perturbation theory (MP2). While these are efficient and realistic, they fall short of the accuracy of the ``gold standard'' coupled-cluster method, especially with respect to reaction and isomerization barriers. We report a major step forward in applying a $\Delta$-machine learning method to the challenging case of acetylacetone, whose MP2 barrier height for H-atom transfer is low by roughly 1.5 kcal/mol relative to the benchmark CCSD(T) barrier of 3.2 kcal/mol. From a database of 2151 local CCSD(T) energies, and training with as few as 430 energies, we obtain a new PES with a barrier of 3.49 kcal/mol in agreement with the LCCSD(T) one of 3.54 kcal/mol and close to the benchmark value. Tunneling splittings due to H-atom transfer are calculated using this new PES, providing improved estimates over previous ones obtained using an MP2-based PES.