百万级原子间势能数据集，助力通用机器学习势函数研究
MP-ALOE: An r2SCAN dataset for universal machine learning interatomic potentials
- 基于主动学习构建，包含近百万个非平衡结构的DFT计算
- 在极端条件下的热力学、力场和分子动力学测试中表现优异
- 适合开发通用机器学习势函数的研究者使用
我们提出MP-ALOE，一个基于高精度r2SCAN泛函的近百万条密度泛函理论（DFT）计算数据集，涵盖89种元素。该数据集通过主动学习生成，主要包含非平衡结构。我们以MP-ALOE训练了一个机器学习原子间势函数，并在多个基准测试中评估其性能：包括平衡结构的热化学性质预测、远离平衡结构的力场预测、静态极端形变下的物理合理性维持，以及极端温压条件下的分子动力学稳定性。MP-ALOE在所有测试中均表现出色，已公开供社区使用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。