Surface segregation in high-entropy alloys from alchemical machine learning: dataset HEA25S

High-entropy alloys (HEAs), containing several metallic elements in near-equimolar proportions, have long been of interest for their unique mechanical properties. More recently, they have emerged as a promising platform for the development of novel heterogeneous catalysts, because of the large design space, and the synergistic effects between their components. In this work we use a machine-learning potential that can model simultaneously up to 25 transition metals (d-block transition metals, excluding Tc, Cd, Re, Os and Hg) to study the tendency of different elements to segregate at the surface of a HEA.
In this record, we provide a dataset HEA25S, containing 10000 bulk HEA structures (Dataset O), 2640 HEA surface slabs (Dataset A), together with 1000 bulk and 1000 surface slabs snapshots from the molecular dynamics (MD) runs (Datasets B and C), and 500 MD snapshots of the 25 elements Cantor-style alloy surface slabs.
We also provide the HEA25-4-NN and HEA25S-4-NN final models, which were used in the study. Full description of both the dataset and the models can be found the reference paper below.

高熵合金（High-entropy alloys, HEAs）因包含若干近等摩尔比的金属元素，其独特的力学性能长期以来备受关注。近年来，得益于广阔的设计空间与组元间的协同效应，高熵合金已成为开发新型多相催化剂的极具潜力的平台。本研究采用可同时建模最多25种过渡金属（d区过渡金属，排除锝Tc、镉Cd、铼Re、锇Os与汞Hg）的机器学习势函数，探究不同元素在高熵合金表面的偏析趋势。
本数据集名为HEA25S，涵盖10000个体相高熵合金结构（数据集O）、2640个高熵合金表面超胞（数据集A），另有1000个体相结构与1000个表面超胞的分子动力学（molecular dynamics, MD）模拟快照（数据集B与C），以及500组25元素康托尔型合金表面超胞的MD模拟快照。
本研究还提供了实验所用的HEA25-4-NN与HEA25S-4-NN最终模型。数据集与模型的完整说明可参见下文的参考文献。

搜集汇总

背景与挑战

背景概述

该数据集专注于高熵合金表面偏析研究，通过机器学习势能模型模拟25种过渡金属，提供包括体相结构、表面板、分子动力学快照在内的多类型数据及预训练模型。数据集支持高熵合金在催化等领域的原子级模拟与设计，具有明确的机器学习和材料科学应用背景。