Abstract
We demonstrate that accurate linear force fields
can be built using the Atomic Cluster Ex-
pansion (ACE) framework for molecules. Our
model is built from body ordered symmetric
polynomials which makes it a natural exten-
sion of traditional molecular mechanics force
fields, and the large number of free parameters
allows sufficient flexibility that it reaches the
accuracy typical of recently proposed machine
learning based approaches. We test our model
on the MD17 and ISO17 data sets and also on a
larger, more flexible molecule, and compare to
leading machine learning models as well as re-
fitted empirical force fields. We show that the
linear body ordered ACE model has excellent
transferability for properties beyond raw energy
and force RMSE, both for molecular dynamics
at different temperatures and for configurations
very far from the training set including dihedral
scans and even bond breaking.
Version notes
Corrected the 3BPA training and test splits (previous version contained an empty zip by accident)
Content

Supplementary material

Supporting Information for Linear Atomic Cluster Expansion Force Fields for Organic Molecules: beyond RMSE
Supporting Information for the manuscript.
3BPA benchmark
This folder contains the training and test sets for the 3BPA table in the manuscript.