Deep Neural Networks for Accurate Predictions of Garnet Stability

Abstract

Predicting the stability of crystals is one of the central problems in materials science. Today, density functional theory (DFT) calculations are the computational tool of choice to obtain energies of crystals with quantitative accuracy. Despite algorithmic and computing advances, DFT calculations remain comparatively expensive and scale poorly with system size. Here we show that deep neural networks utilizing just two descriptors - the Pauling electronegativity and ionic radii - can predict the DFT formation energies of C3A2D3O12 garnets with extremely low mean absolute errors of 7-8 meV/atom, an order of magnitude improvement over previous machine learning models and well within the limits of DFT accuracy. Further extension to mixed garnets with little loss in accuracy can be achieved using a binary encoding scheme that introduces minimal increase in descriptor dimensionality. Our results demonstrate that generalizable deep-learning models for quantitative crystal stability prediction can be built on a small set of chemically-intuitive descriptors. Such models provide the means to rapidly transverse vast chemical spaces to accurately identify stable compositions, accelerating the discovery of novel materials with potentially superior properties.

4 figures

References in corpus (3)

• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Representation of compounds for machine-learning prediction of physical properties
• Predicting the thermodynamic stability of perovskite oxides using machine learning models

Cited by in corpus (33)

• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• A Perspective on Conventional High-Temperature Superconductors at High Pressure: Methods and Materials
• Opportunities and Challenges for Machine Learning in Materials Science
• Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials
• An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
• Paradigm shift in electron-based crystallography via machine learning
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• The role of decomposition reactions in assessing first-principles predictions of solid stability
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Uncertainty Prediction for Machine Learning Models of Material Properties
• Accelerating amorphous polymer electrolyte screening by learning to reduce errors in molecular dynamics simulated properties
• The Materials Simulation Toolkit for Machine Learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research
• Predicting electronic structures at any length scale with machine learning
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Calibrating DFT formation enthalpy calculations by multi-fidelity machine learning
• A universal model for the formation energy prediction of inorganic compounds
• ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data
• Machine Learning based prediction of noncentrosymmetric crystal materials
• Database-driven High-Throughput Calculations and Machine Learning Models for Materials Design
• Machine learning for impurity charge-state transition levels in semiconductors from elemental properties using multi-fidelity datasets
• Machine-learning correction to density-functional crystal structure optimization
• Accelerating Material Property Prediction using Generically Complete Isometry Invariants
• Material Property Prediction using Graphs based on Generically Complete Isometry Invariants
• Coarse-grained crystal graph neural networks for reticular materials design
• Machine learning the electronic structure of matter across temperatures
• Efficient dataset generation for machine learning perovskite alloys
• Ab initio machine learning in chemical compound space
• Machine learning for accelerated bandgap prediction in strain-engineered quaternary III-V semiconductors
• Inverse Design of Potential Singlet Fission Molecules using a Transfer Learning Based Approach
• Predicting band gaps and band-edge positions of oxide perovskites using DFT and machine learning
• Active learning and element embedding approach in neural networks for infinite-layer versus perovskite oxides
• Screening of potential double perovskite materials for photovoltaic applications using agglomerative hierarchical clustering
• Formation Energy Prediction of Material Crystal Structures using Deep Learning