TL;DR利用晶体表示学习框架 Orbital CrystalNet 预测材料性质,该框架包括原子描述符生成和图形表示学习两个部分,证明了该模型的有效性。
Abstract
Predicting material properties base on micro structure of materials has long
been a challenging problem. Recently many deep learning methods have been
developed for material property prediction. In this study, we