Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

2017/10/31 by Tian Xie, Jeffrey C. Grossman · 12 citations
Physics and Astronomy · #cond-mat.mtrl-sci

paper · pdf · doi:10.1103/physrevlett.120.145301

published as Phys. Rev. Lett. 120, 145301 (2018) · 6+9 pages, 3+6 figures

arxiv created 2018/04/06 · arxiv updated 2018/04/10

Abstract

The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 10⁴ data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.

Cited by

• BatteryMat: a hierarchical machine-learning and DFT framework for average-voltage screening of lithium-ion cathode materials
• InvDesMobility: a reliability-gated first-principles feedback framework for closed-loop materials discovery
• Predicting Spin-Crossover Behavior in Metal-Organic Frameworks from Limited and Noisy Data Using Quantile Active Learning
• Spatial statistics for screening molecular structures
• Interpretable, Physics-Informed Learning Reveals Sulfur Adsorption and Poisoning Mechanisms in 13-Atom Icosahedra Nanoclusters
• Scalable Data-Driven Basis Selection for Linear Machine Learning Interatomic Potentials
• MetaMolGen: A Neural Graph Motif Generation Model for De Novo Molecular Design
• Predicting Methane Adsorption in Metal-Substituted MOFs: A Comparative Study between Density Functional Theory and Machine Learning
• Deep transfer learning with graph neural networks for the selection of manufacturing processes
• Zero-shot Autonomous Microscopy for Scalable and Intelligent Characterization of 2D Materials
• MatterTune: An Integrated, User-Friendly Platform for Fine-Tuning Atomistic Foundation Models to Accelerate Materials Simulation and Discovery
• MatWheel: Addressing Data Scarcity in Materials Science Through Synthetic Data

Related

• Deep learning in-depth analysis of crystal graph convolutional neural networks: A new era in materials discovery and its applications
• Large-scale machine-learning-assisted exploration of the whole materials space
• CrysGNN : Distilling pre-trained knowledge to enhance property prediction for crystalline materials
• Graph Neural Networks Based Deep Learning for Predicting Structural and Electronic Properties
• LLM-Prop: Predicting Physical And Electronic Properties Of Crystalline Solids From Their Text Descriptions