Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals

Abstract

Historically, materials discovery has been driven by a laborious trial-and-error process. The growth of materials databases and emerging informatics approaches finally offer the opportunity to transform this practice into data- and knowledge-driven rational design. By using data from the AFLOW repository for high-throughput ab-initio calculations, we have generated Quantitative Materials Structure-Property Relationship (QMSPR) models to predict eight critical electronic and thermomechanical materials properties, such as the metal/insulator classification, band gap energy, bulk and shear moduli, Debye temperature, and heat capacity. The prediction accuracy obtained with these QMSPR models approaches training data for virtually any stoichiometric inorganic crystalline material. The success and universality of these models is attributed to the construction of new materials descriptors---referred to as the universal Property-Labeled Materials Fragments (PLMF). The representation requires only minimal structural input and affords straightforward model interpretation in terms of simple heuristic design rules that guide rational materials design. This study demonstrates the power of materials informatics to dramatically accelerate the search for new materials.

14 pages, 7 figures

References in corpus (7)

• AFLOW: An automatic framework for high-throughput materials discovery
• Big Data of Materials Science - Critical Role of the Descriptor
• High-Throughput Computational Screening of thermal conductivity, Debye temperature and Grüneisen parameter using a quasi-harmonic Debye Model
• Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
• Structure prediction based on ab initio simulated annealing for boron nitride
• A high-throughput ab initio review of platinum-group alloy systems
• Phonon heat conduction in layered anisotropic crystals

Cited by in corpus (93)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• SchNet - a deep learning architecture for molecules and materials
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Less is more: sampling chemical space with active learning
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Data-driven materials science: status, challenges and perspectives
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• A Perspective on Conventional High-Temperature Superconductors at High Pressure: Methods and Materials
• Machine learning modeling of superconducting critical temperature
• Machine learning for electronically excited states of molecules
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Machine Learning Enabled Computational Screening of Inorganic Solid Electrolytes for Dendrite Suppression with Li Metal Anode
• Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry
• A critical examination of compound stability predictions from machine-learned formation energies
• Deep Neural Networks for Accurate Predictions of Garnet Stability
• FAIR data enabling new horizons for materials research
• Machine Learning the Voltage of Electrode Materials in Metal-ion Batteries
• Machine learning with force-field inspired descriptors for materials: fast screening and mapping energy landscape
• Machine-learned multi-system surrogate models for materials prediction
• Paradigm shift in electron-based crystallography via machine learning
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• Machine Learning on Neutron and X-Ray Scattering
• Neural Network-based Classification of Crystal Symmetries from X-Ray Diffraction Patterns
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Predicting the Curie temperature of ferromagnets using machine learning
• Graph convolutional neural networks as "general-purpose" property predictors: the universality and limits of applicability
• Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings
• Machine Learning and Evolutionary Prediction of Superhard B-C-N Compounds
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks
• Accelerated Discovery of Two-Dimensional Optoelectronic Octahedral Oxyhalides via High-Throughput Ab Initio Calculations and Machine Learning
• Direct prediction of phonon density of states with Euclidean neural networks
• Physically inspired deep learning of molecular excitations and photoemission spectra
• Modelling the dielectric constants of crystals using machine learning
• aflow.org: A Web Ecosystem of Databases, Software and Tools
• Machine learning and excited-state molecular dynamics
• PANNA: Properties from Artificial Neural Network Architectures
• Detection of Topological Materials with Machine Learning
• Calibrating DFT formation enthalpy calculations by multi-fidelity machine learning
• On Machine Learning Force Fields for Metallic Nanoparticles
• Extensible Structure-Informed Prediction of Formation Energy with Improved Accuracy and Usability employing Neural Networks
• A New Kind of Atlas of Zeolite Building Blocks
• Layer shift factor in layered hybrid perovskites -- univocal quantitative descriptor of composition-structure-property relationships
• Data Mining for better material synthesis: the case of pulsed laser deposition of complex oxides
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data
• A rule-free workflow for the automated generation of databases from scientific literature
• Machine-learning enabled thermodynamic model for the design of new rare-earth compounds
• Computational Design of Corrosion-resistant and Wear-resistant Titanium Alloys for Orthopedic Implants
• Few-shot machine learning in the three-dimensional Ising model
• Accelerating inverse crystal structure prediction by machine learning: a case study of carbon allotropes
• Accelerated chemical space search using a quantum-inspired cluster expansion approach
• Efficient first principles based modeling via machine learning: from simple representations to high entropy materials
• Convergence and pitfalls of density functional perturbation theory phonons calculations from a high-throughput perspective
• Hardness and fracture toughness models by symbolic regression
• Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction
• High-Efficient ab initio Bayesian Active Learning Method and Applications in Prediction of Two-dimensional Functional Materials
• Voting Data-Driven Regression Learning for Discovery of Functional Materials and Applications to Two-Dimensional Ferroelectric Materials
• Materials property prediction using symmetry-labeled graphs as atomic-position independent descriptors
• XtalOpt Version 13: Multi-Objective Evolutionary Search for Novel Functional Materials
• Dimensionalities and multiplicities determination of crystal nets
• Impact of Data Bias on Machine Learning for Crystal Compound Synthesizability Predictions
• Mean-Field Density Matrix Decompositions
• Structural Motifs and Bonding in Two Families of Boron Structures Predicted at Megabar Pressures
• AFLOW-QHA3P: Robust and automated method to compute thermodynamic properties of solids
• Predicting Solid State Material Platforms for Quantum Technologies
• First-principles Hubbard parameters with automated and reproducible workflows
• Machine learning for accuracy in density functional approximations
• Graph-neural-network predictions of solid-state NMR parameters from spherical tensor decomposition
• Generative Adversarial Networks for Crystal Structure Prediction
• Alloy Informatics through Ab Initio Charge Density Profiles: Case Study of Hydrogen Effects in Face-Centered Cubic Crystals
• Learning the Crystal Structure Genome for Property Classification
• PINK: physical-informed machine learning for lattice thermal conductivity
• Physics-guided descriptors for prediction of structural polymorphs
• MATGANIP: Learning to Discover the Structure-Property Relationship in Perovskites with Generative Adversarial Networks
• Microscopic Geometry Characterizes Structure/Potential-Energy Correspondence in a Thermodynamic System
• MC3D: The Materials Cloud computational database of experimentally known stoichiometric inorganics
• Machine learning for accelerated bandgap prediction in strain-engineered quaternary III-V semiconductors
• Identifying candidate hosts for quantum defects via data mining
• A QMC-deep learning method for diffusivity estimation in random domains
• Theoretical Predictions of MB5N5: Atom-Stuffed Boronitride Clathrate Cages Derived from the High-Pressure Superhydride
• Rapid Identification of X-ray Diffraction Spectra Based on Very Limited Data by Interpretable Convolutional Neural Networks
• Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks
• Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks
• Machine learning, phase stability, and disorder with the Automatic Flow Framework for Materials Discovery
• M-CODE: Materials Categorization via Ontology, Dimensionality and Evolution
• Load-dependent Hardness Prediction for Materials using Machine Learning
• Quantitative trends in 8 physical properties of 115000 inorganic compounds gained by machine learning
• Physics-informed machine learning for composition-process-property alloy design: shape memory alloy demonstration