Material synthesis and design from first principle calculations and machine learning
Material synthesis and design from first principle calculations and machine learning
复制标题
DOI：
10.1016/j.commatsci.2015.11.013
复制
发表时间：
2016-02-01
影响因子：
3.3
通讯作者：
Tanaka, Yuzuru
中科院分区：
文献类型：
--
作者：
Takahashi, Keisuke;Tanaka, Yuzuru
基于第一原理计算和机器学习，可以直接预测所需的材料合成和设计。材料大数据是基于密度泛函理论构建的，其中考虑了每一种可能的元素组合，然后将其用作支持向量机的训练集。普通材料的预测材料性能成功地与实验数据相匹配。此外，还可以预测基于所需材料特性的材料组合。因此，所提出的工作流程成为材料数据库和设计材料之间的桥梁。该方法可以从材料大数据中进行有效的材料挖掘，并可能揭示未发现的所需材料。这种方法还可以从材料大数据中挖掘目标材料，揭示未发现的所需材料，并在实验中执行目标材料合成。(C)2015 Elsevier B.V.版权所有。
Desired material synthesis and design can be directly predicted on the basis of first principle calculations and machine learning. Material big data is constructed based on density functional theory where every possible element combinations are considered and then used as training sets for support vector machines. The predicted material properties for common materials are successfully matched with experimental data. In addition, material combinations based on desired material properties are also able to be predicted. Thus, the proposed work flow becomes the bridge between the material database and designing materials. The approach enables efficient material mining from material big data and could potentially reveal undiscovered desired materials. This approach could also potentially enable targeted material mining from material big data, the unveiling of undiscovered desired materials, and the execution of targeted material synthesis in experiment. (C) 2015 Elsevier B.V. All rights reserved.