Machine-learning structural and electronic properties of metal halide perovskites using a hierarchical convolutional neural network
Machine-learning structural and electronic properties of metal halide perovskites using a hierarchical convolutional neural network
复制标题
使用分层卷积神经网络机器学习金属卤化物钙钛矿的结构和电子性质
DOI：
10.1038/s41524-020-0307-8
复制
发表时间：
2020-04-14
影响因子：
9.7
通讯作者：
Castelli, Ivano E.
中科院分区：
文献类型：
--
作者：
Saidi, Wissam A.;Shadid, Waseem;Castelli, Ivano E.
基于机器学习（ML）和深度网络的统计工具的开发正在积极寻求材料设计问题。虽然可以使用量子力学方法准确地确定结构-性质关系，但这些第一原理计算在计算上要求很高，限制了它们在筛选大量候选结构时的使用。在本文中，我们使用卷积神经网络来开发具有数十亿范围材料设计空间的金属卤化物钙钛矿（MHP）的电子特性的预测模型。我们表明，一个设计良好的分层ML方法具有更高的保真度预测性能的MHP相比，直接的方法。在这种架构中，每个神经网络元件在估计过程中具有指定的作用，从预测钙钛矿的复杂特征（例如晶格常数和八面体倾斜角）到缩小感兴趣值的可能范围。使用分层ML方案，得到的MHP的晶格常数，八面体角和带隙的均方根误差分别为0.01埃，5度，和0.02 eV。我们的研究强调了仔细的网络设计和分层方法的重要性，以减轻与不平衡的数据集分布相关的问题，这在材料数据集中总是很常见。
The development of statistical tools based on machine learning (ML) and deep networks is actively sought for materials design problems. While structure-property relationships can be accurately determined using quantum mechanical methods, these first-principles calculations are computationally demanding, limiting their use in screening a large set of candidate structures. Herein, we use convolutional neural networks to develop a predictive model for the electronic properties of metal halide perovskites (MHPs) that have a billions-range materials design space. We show that a well-designed hierarchical ML approach has a higher fidelity in predicting properties of the MHPs compared to straight-forward methods. In this architecture, each neural network element has a designated role in the estimation process from predicting complex features of the perovskites such as lattice constant and octahedral till angle to narrowing down possible ranges for the values of interest. Using the hierarchical ML scheme, the obtained root-mean-square errors for the lattice constants, octahedral angle and bandgap for the MHPs are 0.01 angstrom, 5 degrees, and 0.02 eV, respectively. Our study underscores the importance of a careful network design and a hierarchical approach to alleviate issues associated with imbalanced dataset distributions, which is invariably common in materials datasets.