MP-ALOE: An r2SCAN dataset for universal machine learning interatomic potentials

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuner, Matthew C., Kaplan, Aaron D., Persson, Kristin A., Asta, Mark, Chrzan, Daryl C.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916831951847424
author Kuner, Matthew C.
Kaplan, Aaron D.
Persson, Kristin A.
Asta, Mark
Chrzan, Daryl C.
author_facet Kuner, Matthew C.
Kaplan, Aaron D.
Persson, Kristin A.
Asta, Mark
Chrzan, Daryl C.
contents We present MP-ALOE, a dataset of nearly 1 million DFT calculations using the accurate r2SCAN meta-generalized gradient approximation. Covering 89 elements, MP-ALOE was created using active learning and primarily consists of off-equilibrium structures. We benchmark a machine learning interatomic potential trained on MP-ALOE, and evaluate its performance on a series of benchmarks, including predicting the thermochemical properties of equilibrium structures; predicting forces of far-from-equilibrium structures; maintaining physical soundness under static extreme deformations; and molecular dynamic stability under extreme temperatures and pressures. MP-ALOE shows strong performance on all of these benchmarks, and is made public for the broader community to utilize.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05559
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MP-ALOE: An r2SCAN dataset for universal machine learning interatomic potentials
Kuner, Matthew C.
Kaplan, Aaron D.
Persson, Kristin A.
Asta, Mark
Chrzan, Daryl C.
Materials Science
Artificial Intelligence
Computational Physics
We present MP-ALOE, a dataset of nearly 1 million DFT calculations using the accurate r2SCAN meta-generalized gradient approximation. Covering 89 elements, MP-ALOE was created using active learning and primarily consists of off-equilibrium structures. We benchmark a machine learning interatomic potential trained on MP-ALOE, and evaluate its performance on a series of benchmarks, including predicting the thermochemical properties of equilibrium structures; predicting forces of far-from-equilibrium structures; maintaining physical soundness under static extreme deformations; and molecular dynamic stability under extreme temperatures and pressures. MP-ALOE shows strong performance on all of these benchmarks, and is made public for the broader community to utilize.
title MP-ALOE: An r2SCAN dataset for universal machine learning interatomic potentials
topic Materials Science
Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2507.05559