Highly transferable atomistic machine-learning potentials from curated and compact datasets across the periodic table

Highly transferable atomistic machine-learning potentials from curated and compact datasets across the periodic table
复制标题

DOI：
10.1039/d3dd00046j
复制
发表时间：
2023
期刊：
Digital Discovery
影响因子：
--
通讯作者：
Christopher M. Andolina;W. Saidi
Christopher M. Andolina;W. Saidi
中科院分区：
其他
文献类型：
--
作者：
Christopher M. Andolina;W. Saidi

文献摘要

相似文献

使用密度泛函理论（DFT）数据集训练的机器学习原子势（MLP）允许以接近DFT的精度对复杂材料特性进行建模，同时降低其计算成本。
Machine learning atomistic potentials (MLPs) trained using density functional theory (DFT) datasets allow for the modeling of complex material properties with near-DFT accuracy while imposing a fraction of its computational cost.