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

2021-02-16 · Boyu Zhang, Mushen Zhou, Jianzhong Wu, Fuchang Gao

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.

📄 PDF Abstract BibTeX arXiv:2102.11023

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning Graph Neural Network

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction

2020-03-11 · Steph-Yves Louis, Yong Zhao, Alireza Nasiri, Xiran Wong 외

Machine learning (ML) methods have gained increasing popularity in exploring and developing new materials. More specifically, graph neural network (GNN) has been applied in predicting material properties. In this work, w…

Graph Attention Graph Neural Network Property Prediction

DeepCrysTet: A Deep Learning Approach Using Tetrahedral Mesh for Predicting Properties of Crystalline Materials

2023-09-07 · Hirofumi Tsuruta, Yukari Katsura, Masaya Kumagai

Machine learning (ML) is becoming increasingly popular for predicting material properties to accelerate materials discovery. Because material properties are strongly affected by its crystal structure, a key issue is conv…

Graph Neural Network

Predicting and Interpreting Energy Barriers of Metallic Glasses with Graph Neural Networks

2023-12-08 · Haoyu Li, Shichang Zhang, Longwen Tang, Mathieu Bauchy 외

Metallic Glasses (MGs) are widely used materials that are stronger than steel while being shapeable as plastic. While understanding the structure-property relationship of MGs remains a challenge in materials science, stu…

Prediction Representation Learning

Learning Ordering in Crystalline Materials with Symmetry-Aware Graph Neural Networks

2024-09-20 · Jiayu Peng, James Damewood, Jessica Karaguesian, Jaclyn R. Lunger 외

Graph convolutional neural networks (GCNNs) have become a machine learning workhorse for screening the chemical space of crystalline materials in fields such as catalysis and energy storage, by predicting properties from…

Graph neural network framework for energy mapping of hybrid monte-carlo molecular dynamics simulations of Medium Entropy Alloys

2024-11-20 · Mashaekh Tausif Ehsan, Saifuddin Zafar, Apurba Sarker, Sourav Das Suvro 외

Machine learning (ML) methods have drawn significant interest in material design and discovery. Graph neural networks (GNNs), in particular, have demonstrated strong potential for predicting material properties. The pres…