Predicting the stability of ternary intermetallics with density functional theory and machine learning.
Predicting the stability of ternary intermetallics with density functional theory and machine learning.
复制标题
DOI：
10.1063/1.5020223
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Jonathan Schmidt;Liming Chen;S. Botti;M. Marques
中科院分区：
文献类型：
--
作者：
Jonathan Schmidt;Liming Chen;S. Botti;M. Marques
我们使用机器学习技术和高通量密度泛函理论计算的组合来探索具有AB 2C 2组成的三元化合物。我们选择了两种最常见的金属间化合物原型，即tI 10-CeAl 2Ga 2和tP 10-FeMo 2B 2结构。我们的研究结果表明，在这些阶段中可能有10倍以上的稳定化合物比以前已知的。它们大多是金属和非磁性的。虽然机器学习的使用将整体计算成本降低了约75%，但其预测能力仍然存在一些限制，特别是对于涉及周期表第二行或磁性元素的化合物。
We use a combination of machine learning techniques and high-throughput density-functional theory calculations to explore ternary compounds with the AB2C2 composition. We chose the two most common intermetallic prototypes for this composition, namely, the tI10-CeAl2Ga2 and the tP10-FeMo2B2 structures. Our results suggest that there may be ∼10 times more stable compounds in these phases than previously known. These are mostly metallic and non-magnetic. While the use of machine learning reduces the overall calculation cost by around 75%, some limitations of its predictive power still exist, in particular, for compounds involving the second-row of the periodic table or magnetic elements.