Repository logo
 

Research data supporting "MACE-OFF23"


Change log

Authors

Kovacs, David Peter 
Browning, Nicholas J 
Batatia, Ilyes 
Horton, Joshua T 

Description

This repository contains train and test datasets for MACE-OFF23 forcefields.

The core of the training set is the SPICE dataset. 95% of the data were used for training and validation, and 5% for testing. The MACE-OFF23 model is trained to reproduce the energies and forces computed at the ωB97M-D3(BJ)/def2-TZVPPD level of quantum mechanics, as implemented in the PSI4 software [56]. We have used a subset of SPICE that contains the ten chemical elements H, C, N, O, F, P, S, Cl, Br, and I, and has a neutral formal charge. We have also removed the ion pairs subset. Overall, we used about 85% of the full SPICE dataset.

Files are provided in extended xyz format and contain energies and force data in units of eV and eV/Angstrom

Version

Software / Usage instructions

Usage should follow documentation https://mace-docs.readthedocs.io/en/latest/ MACE code is available at https://github.com/ACEsuit/mace

Keywords

DFT, forcefield, machine learning

Publisher

Rights

MIT
Relationships