How to represent crystal structures for machine learning: Towards fast prediction of electronic properties
How to represent crystal structures for machine learning: Towards fast prediction of electronic properties
复制标题
DOI：
10.1103/physrevb.89.205118
复制
发表时间：
2014-05-21
影响因子：
3.7
通讯作者：
Gross, E. K. U.
中科院分区：
文献类型：
--
作者：
Schuett, K. T.;Glawe, H.;Gross, E. K. U.
固体的高通量密度泛函计算非常耗时。作为替代方案，我们提出了一种机器学习方法来快速预测固态特性。为了实现这一点，使用局部自旋密度近似计算作为训练集。我们专注于预测费米能级电子态密度的值。我们发现输入数据的传统表示形式（例如库仑矩阵）不适合在周期性固体的情况下训练学习机。我们提出了一种新颖的晶体结构表示，使学习和竞争预测精度在任意晶胞尺寸的不受限制的 spd 系统中成为可能。
High-throughput density functional calculations of solids are highly time-consuming. As an alternative, we propose a machine learning approach for the fast prediction of solid-state properties. To achieve this, local spin-density approximation calculations are used as a training set. We focus on predicting the value of the density of electronic states at the Fermi energy. We find that conventional representations of the input data, such as the Coulomb matrix, are not suitable for the training of learning machines in the case of periodic solids. We propose a novel crystal structure representation for which learning and competitive prediction accuracies become possible within an unrestricted class of spd systems of arbitrary unit-cell size.