Scholarlink

<p>We present MP-ALOE, a dataset of nearly 1 million DFT calculations using the accurate r<sup>2</sup>SCAN 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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

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

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月21日

查看全文
  • Matthew C. Kuner,
  • Aaron D. Kaplan,
  • Kristin A. Persson,
  • Mark Asta,
  • Daryl C. Chrzan

摘要

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.