Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
复制标题

DOI:
10.1103/physrevlett.120.145301
复制
发表时间:
2018-04-06
影响因子:
8.6
通讯作者:
Grossman, Jeffrey C.
Grossman, Jeffrey C.
中科院分区:
物理与天体物理1区
文献类型:
--
作者:
Xie, Tian;Grossman, Jeffrey C.

文献摘要

被引文献

相似文献

使用机器学习方法来加速晶体材料的设计通常需要手动构建特征向量或复杂的原子坐标转换来输入晶体结构,这要么将模型限制在某些晶体类型,要么使其难以提供化学见解。在这里,我们开发了一个晶图卷积神经网络框架,可以直接从晶体中原子的连接学习材料的性质,提供了晶体材料的通用和可解释的表示。通过104个数据点的训练,我们的方法提供了对具有不同结构类型和组成的八种不同性质的晶体的密度泛函理论计算性质的高精度预测。此外,我们的框架是可解释的,因为人们可以从局部化学环境中提取对全球性质的贡献。通过一个钙钛矿的例子,我们展示了如何利用这些信息来发现材料设计的经验规则。
The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 104 data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.