Insightful classification of crystal structures using deep learning

Abstract

Computational methods that automatically extract knowledge from data are critical for enabling data-driven materials science. A reliable identification of lattice symmetry is a crucial first step for materials characterization and analytics. Current methods require a user-specified threshold, and are unable to detect average symmetries for defective structures. Here, we propose a machine-learning-based approach to automatically classify structures by crystal symmetry. First, we represent crystals by calculating a diffraction image, then construct a deep-learning neural-network model for classification. Our approach is able to correctly classify a dataset comprising more than 100 000 simulated crystal structures, including heavily defective ones. The internal operations of the neural network are unraveled through attentive response maps, demonstrating that it uses the same landmarks a materials scientist would use, although never explicitly instructed to do so. Our study paves the way for crystal-structure recognition of - possibly noisy and incomplete - three-dimensional structural data in big-data materials science.

Nature Communications, in press (2018)

References in corpus (5)

• Deep Learning in Neural Networks: An Overview
• Big Data of Materials Science - Critical Role of the Descriptor
• Machine-learning based interatomic potential for amorphous carbon
• How van der Waals interactions determine the unique properties of water
• A RESTful API for exchanging Materials Data in the AFLOWLIB.org consortium

Cited by in corpus (50)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Data-driven materials science: status, challenges and perspectives
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Physics-inspired structural representations for molecules and materials
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Autonomous discovery in the chemical sciences part I: Progress
• An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties
• Atom-Density Representations for Machine Learning
• Paradigm shift in electron-based crystallography via machine learning
• Neural Network-based Classification of Crystal Symmetries from X-Ray Diffraction Patterns
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Crystallography companion agent for high-throughput materials discovery
• Unsupervised machine learning via transfer learning and k-means clustering to classify materials image data
• Using a machine learning approach to determine the space group of a structure from the atomic pair distribution function (PDF)
• Learning physical properties of liquid crystals with deep convolutional neural networks
• Accelerating Finite-temperature Kohn-Sham Density Functional Theory with Deep Neural Networks
• NOMAD 2018 Kaggle Competition: Solving Materials Science Challenges Through Crowd Sourcing
• Deformation potential extraction and computationally efficient mobility calculations in silicon from first principles
• Characterizing stochastic time series with ordinal networks
• Determining liquid crystal properties with ordinal networks and machine learning
• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Constrained non-negative matrix factorization enabling real-time insights of $\text{in situ}$ and high-throughput experiments
• Machine Learning based prediction of noncentrosymmetric crystal materials
• Formula graph self-attention network for representation-domain independent materials discovery
• Tracking perovskite crystallization via deep learning-based feature detection on 2D X-ray scattering data
• Machine learning identifies scale-free properties in disordered materials
• Artifact Identification in X-ray Diffraction Data using Machine Learning Methods
• On classification approaches for crystallographic symmetries of noisy 2D periodic patterns
• AtomVision: A machine vision library for atomistic images
• Auto-resolving the atomic structure at van der Waals interfaces using a generative model
• Machine learning in the study of phase transition of two-dimensional complex plasmas
• Materials Fingerprinting Classification
• Crystal structure identification with 3D convolutional neural networks with application to high-pressure phase transitions in SiO${}_2$
• Machine Learning Recognition of hybrid lead halide perovskites and perovskite-related structures out of X-ray diffraction patterns
• Advancing descriptor search in materials science: feature engineering and selection strategies
• Spatial mapping of disordered 2D materials: the conductance Sudoku
• Automated Real-Space Lattice Extraction for Atomic Force Microscopy Images
• Learning the Crystal Structure Genome for Property Classification
• Novel applications of Generative Adversarial Networks (GANs) in the analysis of ultrafast electron diffraction (UED) images
• Decoding the conductance of disordered nanostructures: a quantum inverse problem
• Improving Demand Forecasting in Open Systems with Cartogram-Enhanced Deep Learning
• Nonequilibrium thermodynamics of self-supervised learning
• Robust recognition and exploratory analysis of crystal structures via Bayesian deep learning
• Visualizing key features in X-ray images of epoxy resins for improved material classification using singular value decomposition of deep learning features
• Unsupervised Machine-Learning Pipeline for Data-Driven Defect Detection and Characterisation: Application to Displacement Cascades
• Estimation Enhancing in Optoelectronic Property: A Novel Approach Using Orbital Interaction Parameters and Tight-Binding
• Decoratypes: An Extensible Crystal Taxonomy for Machine Learning-Guided Materials Discovery
• Physics Aware Representation Learning on Electronic Charge Density for Materials Property Prediction
• STEM Diffraction Pattern Analysis with Deep Learning Networks