Solving the Coloring Problem in Half-Heusler Structures: Machine-Learning Predictions and Experimental Validation.
Solving the Coloring Problem in Half-Heusler Structures: Machine-Learning Predictions and Experimental Validation.
复制标题
解决 Half-Heusler 结构中的着色问题：机器学习预测和实验验证。
DOI：
10.1021/acs.inorgchem.9b00987
复制
发表时间：
2019
影响因子：
4.6
通讯作者：
A. Mar
中科院分区：
文献类型：
--
作者：
Alexander S. Gzyl;A. Oliynyk;Lawrence A. Adutwum;A. Mar
半Heusler化合物的结构内的网站偏好已通过机器学习的方法进行了评估。应用支持向量机算法开发一个模型，该模型在179个实验报告的结构和23个仅基于化学组成的描述符上进行训练。该模型具有良好的性能，灵敏度为93%，选择性为96%，准确度为95%。作为数据清理的说明，重新合成并表征了两种被模型标记为具有潜在不正确位点分配的化合物（GdPtSb、HoPdBi）。通过单晶和粉末X射线衍射分析证实了机器学习模型对正确位置分配的预测。这些网站的分配也对应于最低的总能量配置从第一原理计算。
The site preferences within the structures of half-Heusler compounds have been evaluated through a machine-learning approach. A support-vector machine algorithm was applied to develop a model which was trained on 179 experimentally reported structures and 23 descriptors based solely on the chemical composition. The model gave excellent performance, with sensitivity of 93%, selectivity of 96%, and accuracy of 95%. As an illustration of data sanitization, two compounds (GdPtSb, HoPdBi) flagged by the model to have potentially incorrect site assignments were resynthesized and structurally characterized. The predictions of the correct site assignments from the machine-learning model were confirmed by single-crystal and powder X-ray diffraction analysis. These site assignments also corresponded to the lowest total energy configurations as revealed from first-principles calculations.