arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.11023cond-mat.mtrl-scics.AI
收藏

基于局部不变描述子的三维图神经网络预测材料性能

Predicting Material Properties Using a 3D Graph Neural Network with Invariant Local Descriptors

Boyu Zhang, Mushen Zhou, Jianzhong Wu, Fuchang Gao

摘要:

物理性质的准确预测对于发现和设计新材料至关重要。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)是最成功的机器学习方法之一,因为它在描述3D结构数据方面的灵活性和有效性。现有的GCNN模型大多关注于拓扑结构,但过度简化了三维几何结构。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力至关重要。本文提出了一种具有新卷积机制的自适应GCNN,该机制同时对三维空间中所有相邻原子之间的原子相互作用进行建模。我们将所提出的模型应用于预测材料性能的两个具有明显挑战性的问题。第一个是金属有机框架(MOFs)中气体吸附的亨利常数,这是众所周知的困难,因为它对原子构型的高度敏感性。第二个是固态晶体材料中的离子电导率,这是困难的,因为很少有标记的数据可用于训练。新模型在这两个数据集上的表现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。

英文摘要:

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 neighbor atoms in three-dimensional space. We apply the proposed model to two distinctly challenging problems on predicting material properties. 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 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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑