High-quality, high-information datasets for universal atomistic machine learning

TL;DR

This paper introduces MAD-1.5, a high-quality, consistent, and comprehensive dataset for training universal atomistic machine learning models across the periodic table, enabling high-accuracy simulations.

Contribution

The creation of MAD-1.5, a curated, standardized dataset covering 102 elements with high-level DFT calculations, designed specifically for broad atomistic modeling.

Findings

PET-MAD-1.5 achieves benchmark-level accuracy.

Dataset improves chemical space coverage and consistency.

Outlier removal enhances data quality.

Abstract

The quality, consistency, and information content of training data is often what determines the practical value of machine-learning models for atomistic simulations. Yet, many widely used electronic-structure databases are assembled having materials screening as primary goal rather than robust force-field learning, are limited in their scope to a specific class of chemical compounds, and/or employ inconsistent DFT functionals and settings. Here we introduce MAD-1.5, a highly curated dataset designed explicitly for training broadly applicable atomistic models across the periodic table at high levels of theory. MAD-1.5 extends the MAD dataset with targeted enrichment strategies that improve the coverage of chemical space to 102 elements while keeping the total number of configurations compact. All structures are computed with a single, standardized all-electron DFT workflow using the r$^2$SCAN meta-GGA functional and consistent convergence settings, ensuring uniformity across chemically heterogeneous systems. The dataset encompasses molecules, clusters, bulk crystals, surfaces, and low-dimensional structures, and its quality and consistency are further enhanced by outlier removal using uncertainty quantification. We demonstrate the high accuracy that can be achieved with the proposed dataset by training PET-MAD-1.5, a generally applicable r$^2$SCAN interatomic potential that covers 102 elements in the periodic table and achieves exceptional levels of benchmark accuracy and stability in challenging simulation protocols.