Predicting the Materials Properties Using a 3D Graph Neural Network with Invariant Representation
Predicting the Materials Properties Using a 3D Graph Neural Network with Invariant Representation
复制标题
DOI：
10.1109/access.2022.3181750
复制
发表时间：
2022
期刊：
影响因子：
3.9
通讯作者：
Boyu Zhang-;Mushen Zhou;Jianzhong Wu;Fuchang Gao
中科院分区：
文献类型：
--
作者：
Boyu Zhang-;Mushen Zhou;Jianzhong Wu;Fuchang Gao
物理性质的准确预测是发现和设计新材料的关键。机器学习技术因其大规模筛选的潜力而引起了材料科学界的极大关注。图卷积神经网络（GCNN）由于其在描述三维结构数据方面的灵活性和有效性而成为最成功的机器学习方法之一。现有的GCNN模型大多侧重于拓扑结构，而对三维几何结构过于简化。然而，在材料科学中，原子的三维空间分布对于确定原子状态和原子间作用力至关重要。本文提出了一种具有新颖卷积机制的自适应GCNN，该机制可以同时模拟三维空间中所有相邻原子之间的相互作用。我们将提出的模型应用于两个明显具有挑战性的材料性能预测问题。首先是金属有机框架（mof）中气体吸附的亨利常数，由于其对原子构型的高灵敏度，这是出了名的困难。第二个是固态晶体材料中的离子电导率，由于可用于训练的标记数据很少，这是困难的。新模型在两个数据集上都优于现有的基于图形的模型，这表明关键的三维几何信息确实被捕获了。
Accurate prediction of physical properties is critical for discovering and designing novel materials. Machine learning technologies have attracted significant attention in the materials science community for their potential for large-scale screening. Graph Convolution Neural Network (GCNN) is one of the most successful machine learning methods because of its flexibility and effectiveness in describing 3D structural data. Most existing GCNN models focus on the topological structure but overly simplify the three-dimensional geometric structure. However, in materials science, the 3D-spatial distribution of atoms is crucial for determining the atomic states and interatomic forces. This paper proposes an adaptive GCNN with a novel convolution mechanism that simultaneously models atomic interactions among all neighboring atoms in three-dimensional space. We apply the proposed model to two distinctly challenging materials properties prediction problems. The first is Henry’s constant for gas adsorption in Metal-Organic Frameworks (MOFs), which is notoriously difficult because of its high sensitivity to atomic configurations. The second is the ion conductivity in solid-state crystal materials, which is difficult because of the few labeled data available for training. The new model outperforms existing graph-based models on both data sets, suggesting that the critical three-dimensional geometric information is indeed captured.