Npj Comput. Mater.: 材料特性预测—原子线图神经网络
图神经网络 (GNN) 对模拟复杂系统具有巨大的潜力,它可以绕过需要高计算成本的薛定谔方程求解,更快地预测固体、分子和蛋白质等系统的性质。目前,基于GNN 架构,人们开发了一系列模型用于预测材料特性,如SchNet、CGCNN、MEGNet、iCGCNN、OrbNet等等。这些模型将分子或晶体材料表示为一个图形,每个组成原子都有一个节点,边缘对应于原子间键,使用元素特性作为节点特征,原子间距离和/或键价作为边缘特征,通过基于局部化学环境的多层图卷积更新节点特征,从而隐式地反映多体相互作用。然而,许多重要的材料特性(如带隙等电子结构特性) 对键角、局部几何变形等结构特征高度敏感,这些模型将无法有效地描述这些多体相互作用。
Graph neural networks (GNN) have been shown to provide substantial performance improvements for atomistic material representation and modeling compared with descriptor-based machine learning models. While most existing GNN models for atomistic predictions are based on atomic distance information, they do not explicitly incorporate bond angles, which are critical for distinguishing many atomic structures. Furthermore, many material properties are known to be sensitive to slight changes in bond angles. We present an Atomistic Line Graph Neural Network (ALIGNN), a GNN architecture that performs message passing on both the interatomic bond graph and its line graph corresponding to bond angles. We demonstrate that angle information can be explicitly and efficiently included, leading to improved performance on multiple atomistic prediction tasks. We ALIGNN models for predicting 52 solid-state and molecular properties available in the JARVIS-DFT, Materials project, and QM9 databases. ALIGNN can outperform some previously reported GNN models on atomistic prediction tasks by up to 85% in accuracy with better or comparable model training speed.
扩展阅读
npj: 自动化实验设计—新型贝叶斯优化npj: 有物理头脑的贝叶斯网络—太阳能电池工艺的创新优化
npj:高光谱扫描探针显微成像—高斯过程建模npj: 扫描探针显微镜插上机器学习的翅膀——材料探幽更为便捷