Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery

Abstract

The recently proposed crystal graph convolutional neural network (CGCNN) offers a highly versatile and accurate machine learning (ML) framework by learning material properties directly from graph-like representations of crystal structures ("crystal graphs"). Here, we develop an improved variant of the CGCNN model (iCGCNN) that outperforms the original by incorporating information of the Voronoi tessellated crystal structure, explicit 3-body correlations of neighboring constituent atoms, and an optimized chemical representation of interatomic bonds in the crystal graphs. We demonstrate the accuracy of the improved framework in two distinct illustrations: First, when trained/validated on 180,000/20,000 density functional theory (DFT) calculated thermodynamic stability entries taken from the Open Quantum Materials Database (OQMD) and evaluated on a separate test set of 230,000 entries, iCGCNN achieves a predictive accuracy that is significantly improved, i.e., 20% higher than that of the original CGCNN. Second, when used to assist high-throughput search for materials in the ThCr2Si2 structure-type, iCGCNN exhibited a success rate of 31% which is 310 times higher than an undirected high-throughput search and 2.4 times higher than that of the original CGCNN. Using both CGCNN and iCGCNN, we screened 132,600 compounds with elemental decorations of the ThCr2Si2 prototype crystal structure and identified a total of 97 new unique stable compounds by performing 757 DFT calculations, accelerating the computational time of the high-throughput search by a factor of 130. Our results suggest that the iCGCNN can be used to accelerate high-throughput discoveries of new materials by quickly and accurately identifying crystalline compounds with properties of interest.

References in corpus (16)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• SchNet - a deep learning architecture for molecules and materials
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Big Data of Materials Science - Critical Role of the Descriptor
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Discovery of low thermal conductivity compounds with first-principles anharmonic lattice dynamics calculations and Bayesian optimization
• Predicting Crystal Structures with Data Mining of Quantum Calculations
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Prediction model of band-gap for AX binary compounds by combination of density functional theory calculations and machine learning techniques
• Representation of compounds for machine-learning prediction of physical properties
• Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single and binary component solids
• Robust FCC solute diffusion predictions from ab-initio machine learning methods
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks

Cited by in corpus (33)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Opportunities and Challenges for Machine Learning in Materials Science
• Infusing Theory into Deep Learning for Interpretable Reactivity Prediction
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• AtomSets -- A Hierarchical Transfer Learning Framework for Small and Large Materials Datasets
• Materials Representation and Transfer Learning for Multi-Property Prediction
• Geometric Deep Learning for Molecular Crystal Structure Prediction
• Calibrating DFT formation enthalpy calculations by multi-fidelity machine learning
• Performance of the r${}^2$SCAN functional in transition metal oxides
• Structure motif centric learning framework for inorganic crystalline systems
• Recent progress in the JARVIS infrastructure for next-generation data-driven materials design
• DenseGNN: universal and scalable deeper graph neural networks for high-performance property prediction in crystals and molecules
• Screening and understanding Li adsorption on 2-dimensional metallic materials by learning physics
• Formula graph self-attention network for representation-domain independent materials discovery
• Accelerated chemical space search using a quantum-inspired cluster expansion approach
• Fast and Accurate Prediction of Material Properties with Three-Body Tight-Binding Model for the Periodic Table
• Multi-task graph neural networks for simultaneous prediction of global and atomic properties in ferromagnetic systems
• Optimal pre-train/fine-tune strategies for accurate material property predictions
• Identification of High-Dielectric Constant Compounds from Statistical Design
• Boosting Heterogeneous Catalyst Discovery by Structurally Constrained Deep Learning Models
• Closed-loop Error Correction Learning Accelerates Experimental Discovery of Thermoelectric Materials
• Accelerating Material Property Prediction using Generically Complete Isometry Invariants
• Material Property Prediction using Graphs based on Generically Complete Isometry Invariants
• Self-supervised graph neural networks for accurate prediction of Néel temperature
• Coarse-grained crystal graph neural networks for reticular materials design
• Accelerating structure search using atomistic graph-based classifiers
• Machine-Learning Surrogate Model for Accelerating the Search of Stable Ternary Alloys
• Reducing Self-Interaction Error in Transition-Metal Oxides with Different Exact-Exchange Fractions for Energy and Density
• Neural Structure Fields with Application to Crystal Structure Autoencoders
• Entropy-based Active Learning of Graph Neural Network Surrogate Models for Materials Properties