Machine Learning Energies of 2 Million Elpasolite (ABC2D6) Crystals
Machine Learning Energies of 2 Million Elpasolite (ABC2D6) Crystals
复制标题
DOI：
10.1103/physrevlett.117.135502
复制
发表时间：
2016-09-20
影响因子：
8.6
通讯作者：
Armiento, Rickard
中科院分区：
文献类型：
--
作者：
Faber, Felix A.;Lindmaa, Alexander;Armiento, Rickard
钾长石是无机晶体结构数据库中报道的主要的四元晶体结构(AlNaK2F6原型)。我们开发了一个机器学习模型来计算所有类似于2×10(6)原始ABC(2)D(6)钾铝石晶体的密度泛函理论质量形成能，这些晶体可以由主族元素(直至铋)组成。我们的模型的精度可以系统地提高，对于由10×10(3)晶体组成的训练集，平均绝对误差达到0.1 eV/原子。揭示了重要的成键趋势：氟化物最适合D位的配位，这降低了形成能，而碳则相反。元素A和B的成键贡献平均很小。低生成能是因为A和B是第II族的晚元素，C是晚(I族)元素，D是氟化物。在2×10(6)晶体中，预计凸壳上有90个独特的结构，其中NFAl2Ca6具有特殊的化学计量比和负的Al原子氧化态。
Elpasolite is the predominant quaternary crystal structure (AlNaK2F6 prototype) reported in the Inorganic Crystal Structure Database. We develop a machine learning model to calculate density functional theory quality formation energies of all similar to 2 x 10(6) pristine ABC(2)D(6) elpasolite crystals that can be made up from main-group elements (up to bismuth). Our model's accuracy can be improved systematically, reaching a mean absolute error of 0.1 eV/atom for a training set consisting of 10 x 10(3) crystals. Important bonding trends are revealed: fluoride is best suited to fit the coordination of the D site, which lowers the formation energy whereas the opposite is found for carbon. The bonding contribution of the elements A and B is very small on average. Low formation energies result from A and B being late elements from group II, C being a late (group I) element, and D being fluoride. Out of 2 x 10(6) crystals, 90 unique structures are predicted to be on the convex hull-among which is NFAl2Ca6, with a peculiar stoichiometry and a negative atomic oxidation state for Al.