A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials

Abstract

A very active area of materials research is to devise methods that use machine learning to automatically extract predictive models from existing materials data. While prior examples have demonstrated successful models for some applications, many more applications exist where machine learning can make a strong impact. To enable faster development of machine-learning-based models for such applications, we have created a framework capable of being applied to a broad range of materials data. Our method works by using a chemically diverse list of attributes, which we demonstrate are suitable for describing a wide variety of properties, and a novel method for partitioning the data set into groups of similar materials in order to boost the predictive accuracy. In this manuscript, we demonstrate how this new method can be used to predict diverse properties of crystalline and amorphous materials, such as band gap energy and glass-forming ability.

18 pages, 2 figures, 3 tables

References in corpus (9)

• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Big Data of Materials Science - Critical Role of the Descriptor
• How to represent crystal structures for machine learning: towards fast prediction of electronic properties
• Prediction and accelerated laboratory discovery of previously unknown 18-electron ABX compounds
• Predicting Crystal Structures with Data Mining of Quantum Calculations
• Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single and binary component solids
• A sparse representation for potential energy surface
• Crystal Structure Representations for Machine Learning Models of Formation Energies

Cited by in corpus (187)

• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Recent Advances and Applications of Deep Learning Methods 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
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Opportunities and Challenges for Machine Learning in Materials Science
• Machine learning modeling of superconducting critical temperature
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• Benchmarking Materials Property Prediction Methods: The Matbench Test Set and Automatminer Reference Algorithm
• Accelerating Materials Development via Automation, Machine Learning, and High-Performance Computing
• Representation of compounds for machine-learning prediction of physical properties
• Generative adversarial networks (GAN) based efficient sampling of chemical space for inverse design of inorganic materials
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Chemical Shifts in Molecular Solids by Machine Learning
• Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction
• A critical examination of compound stability predictions from machine-learned formation energies
• Deep Neural Networks for Accurate Predictions of Garnet Stability
• Predicting the thermodynamic stability of perovskite oxides using machine learning models
• 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
• Atom-Density Representations for Machine Learning
• High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates
• Deep learning and the Schrödinger equation
• Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
• Machine Learning of Mechanical Properties of Steels
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• Accelerated Discovery of Efficient Solar-cell Materials using Quantum and Machine-learning Methods
• Towards Stacking Fault Energy Engineering in FCC High Entropy Alloys
• A critical examination of robustness and generalizability of machine learning prediction of materials properties
• Machine Learning on Neutron and X-Ray Scattering
• Uncovering structure-property relationships of materials by subgroup discovery
• Modern Data Analytics Approach to Predict Creep of High-Temperature Alloys
• Crystal Diffusion Variational Autoencoder for Periodic Material Generation
• Predicting the Curie temperature of ferromagnets using machine learning
• A transferable machine-learning framework linking interstice distribution and plastic heterogeneity in metallic glasses
• Transfer learning for materials informatics using crystal graph convolutional neural network
• Bayesian optimization package: PHYSBO
• Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings
• ViscNet: Neural network for predicting the fragility index and the temperature-dependency of viscosity
• Representing individual electronic states for machine learning GW band structures of 2D materials
• Designing optical glasses by machine learning coupled with a genetic algorithm
• Phase Classification of Multi-Principal Element Alloys via Interpretable Machine Learning
• Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
• The Materials Simulation Toolkit for Machine Learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research
• Extending Shannon's Ionic Radii Database Using Machine Learning
• Band gap prediction for large organic crystal structures with machine learning
• GlassNet: a multitask deep neural network for predicting many glass properties
• AI-driven inverse design of materials: Past, present and future
• Machine Learning and Evolutionary Prediction of Superhard B-C-N Compounds
• Robust FCC solute diffusion predictions from ab-initio machine learning methods
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks
• Materials Representation and Transfer Learning for Multi-Property Prediction
• Machine Learning Study of the Magnetic Ordering in 2D Materials
• Machine learning for materials discovery: two-dimensional topological insulators
• Direct prediction of phonon density of states with Euclidean neural networks
• Artificial Intelligence in Material Engineering: A review on applications of AI in Material Engineering
• Machine learning the band gap properties of kesterite I${}_2$-II-IV-V${}_4$ quaternary compounds for photovoltaics applications
• Probing out-of-distribution generalization in machine learning for materials
• Precursor recommendation for inorganic synthesis by machine learning materials similarity from scientific literature
• JARVIS-Leaderboard: A Large Scale Benchmark of Materials Design Methods
• Detection of Topological Materials with Machine Learning
• Discrepancies and Error Evaluation Metrics for Machine Learning Interatomic Potentials
• Matrix- and tensor-based recommender systems for the discovery of currently unknown inorganic compounds
• An accelerating approach of designing ferromagnetic materials via machine learning modeling of magnetic ground state and Curie temperature
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• The Phase Stability Network of all Inorganic Materials
• Quantifying the performance of machine learning models in materials discovery
• Calibrating DFT formation enthalpy calculations by multi-fidelity machine learning
• Compositional descriptor-based recommender system accelerating the materials discovery
• A machine learning-based classification approach for phase diagram prediction
• Generative Language Model for Catalyst Discovery
• Database, Features, and Machine Learning Model to Identify Thermally Driven Metal-Insulator Transition Compounds
• A high-throughput structural and electrochemical study of metallic glass formation in Ni-Ti-Al
• A Unified Understanding of Minimum Lattice Thermal Conductivity
• IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
• CRYSPNet: Crystal Structure Predictions via Neural Network
• Inverse Design of Composite Metal Oxide Optical Materials based on Deep Transfer Learning
• Machine-Learning-Guided Prediction Models of Critical Temperature of Cuprates
• Predicting Elastic Properties of Materials from Electronic Charge Density Using 3D Deep Convolutional Neural Networks
• Extensible Structure-Informed Prediction of Formation Energy with Improved Accuracy and Usability employing Neural Networks
• Structure motif centric learning framework for inorganic crystalline systems
• Machine Learning - Driven Materials Discovery: Unlocking Next-Generation Functional Materials - A review
• A universal model for the formation energy prediction of inorganic compounds
• Exploring a potential energy surface by machine learning for characterizing atomic transport
• Machine learning aided materials design platform for predicting the mechanical properties of Na-ion solid-state electrolytes
• Multimodal Foundation Models for Material Property Prediction and Discovery
• A rule-free workflow for the automated generation of databases from scientific literature
• Machine learning spectral indicators of topology
• Hierarchical symbolic regression for identifying key physical parameters correlated with bulk properties of perovskites
• First-Principles Prediction of Electronic Transport in Experimental Semiconductor Heterostructures via Physics-Based Machine Learning
• A Quantum-Chemical Bonding Database for Solid-State Materials
• Piezoelectric modulus prediction using machine learning and graph neural networks
• Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet
• Machine Learning based prediction of noncentrosymmetric crystal materials
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Analogical discovery of disordered perovskite oxides by crystal structure information hidden in unsupervised material fingerprints
• Integrating Machine Learning with Mechanistic Models for Predicting the Yield Strength of High Entropy Alloys
• Formula graph self-attention network for representation-domain independent materials discovery
• Dynamic optimization of volatile fatty acids to enrich biohydrogen production using a deep learning neural network
• Exploring effective charge in electromigration using machine learning
• Random projections and Kernelised Leave One Cluster Out Cross-Validation: Universal baselines and evaluation tools for supervised machine learning for materials properties
• CheMixNet: Mixed DNN Architectures for Predicting Chemical Properties using Multiple Molecular Representations
• Anharmonic Thermodynamics of Vacancies Using a Neural Network Potential
• Machine Learning Prediction of Critical Cooling Rate for Metallic Glasses From Expanded Datasets and Elemental Features
• Convergence and pitfalls of density functional perturbation theory phonons calculations from a high-throughput perspective
• Probabilistic selection and design of concrete using machine learning
• Efficient first principles based modeling via machine learning: from simple representations to high entropy materials
• Reproducibility in Computational Materials Science: Lessons from 'A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials'
• NIMS-OS: An automation software to implement a closed loop between artificial intelligence and robotic experiments in materials science
• Machine Learning Accelerated Descriptor Design for Catalyst Discovery in CO${}_2$ to Methanol Conversion
• Machine-learning accelerated identification of exfoliable two-dimensional materials
• Machine learning formation enthalpies of intermetallics
• Hardness and fracture toughness models by symbolic regression
• Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction
• Explainable Machine Learning for Hydrogen Diffusion in Metals and Random Binary Alloys
• Prediction on Properties of Rare-earth 2-17-X Magnets Ce2Fe17-xCoxCN : A Combined Machine-learning and Ab-initio Study
• Machine Learning for compositional disorder: A Comparison Between Different Descriptors and Machine Learning Frameworks
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Predicting Oxide Glass Properties with Low Complexity Neural Network and Physical and Chemical Descriptors
• Prediction of Large Magnetic Moment Materials With Graph Neural Networks and Random Forests
• Experimentally validated and empirically compared machine learning approach for predicting yield strength of additively manufactured multi-principal element alloys from Co-Cr-Fe-Mn-Ni system
• Data-driven study of the enthalpy of mixing in the liquid phase
• Data-driven analysis of the electronic-structure factors controlling the work functions of perovskite oxides
• The Northeast Materials Database for Magnetic Materials
• CrystalFlow: A Flow-Based Generative Model for Crystalline Materials
• Data-driven study of composition-dependent phase compatibility in NiTi shape memory alloys
• Identification of High-Dielectric Constant Compounds from Statistical Design
• Deep learning and high harmonic generation
• Materials Graph Transformer predicts the outcomes of inorganic reactions with reliable uncertainties
• Closed-loop Error Correction Learning Accelerates Experimental Discovery of Thermoelectric Materials
• Data-Driven Materials Discovery and Synthesis using Machine Learning Methods
• Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function
• Deep Learning Based Superconductivity: Prediction and Experimental Tests
• Molecular simulation-derived features for machine learning predictions of metal glass forming ability
• Evaluating the Performance and Robustness of LLMs in Materials Science Q&A and Property Predictions
• Predicting densities and elastic moduli of SiO2-based glasses by machine learning
• Materials Expert-Artificial Intelligence for Materials Discovery
• Classification-based detection and quantification of cross-domain data bias in materials discovery
• Predicting Solid State Material Platforms for Quantum Technologies
• Machine Learning and Materials Informatics: Recent Applications and Prospects
• Robust data-driven approach for predicting the configurational energy of high entropy alloys
• Machine learning for accuracy in density functional approximations
• Active and transfer learning with partially Bayesian neural networks for materials and chemicals
• Advancing descriptor search in materials science: feature engineering and selection strategies
• Data-driven determination of the spin Hamiltonian parameters and their uncertainties: The case of the zigzag-chain compound KCu${}_4$P${}_3$O${}_{12}$
• Leveraging Composition-Based Material Descriptors for Machine Learning Optimization
• Ab initio property characterisation of thousands of previously unknown 2D materials
• Accelerating Discovery of Extreme Lattice Thermal Conductivity by Crystal Attention Graph Neural Network (CATGNN) Using Chemical Bonding Intuitive Descriptors
• Towards machine learning for microscopic mechanisms: a formula search for crystal structure stability based on atomic properties
• Superconductor discovery in the emerging paradigm of Materials Informatics
• Energy-GNoME: A Living Database of Selected Materials for Energy Applications
• Assessing the Frontier: Active Learning, Model Accuracy, and Multi-objective Materials Discovery and Optimization
• Lean CNNs for mapping electron charge density fields to material properties
• Experimental exploration of ErB${}_2$ and SHAP analysis on a machine-learned model of magnetocaloric materials for materials design
• Machine-learning Based Extraction of the Short-Range Part of the Interaction in Non-contact Atomic Force Microscopy
• Efficient nonmyopic active search with applications in drug and materials discovery
• Emerging Microelectronic Materials by Design: Navigating Combinatorial Design Space with Scarce and Dispersed Data
• A Physics-Informed Machine Learning Model for Porosity Analysis in Laser Powder Bed Fusion Additive Manufacturing
• Charting Lattice Thermal Conductivity of Inorganic Crystals
• Machine learning for accelerated bandgap prediction in strain-engineered quaternary III-V semiconductors
• Machine learning metallic glass critical cooling rates through elemental and molecular simulation based featurization
• Constructing material network representations for intelligent amorphous alloys design
• Machine-learning guided discovery of a high-performance spin-driven thermoelectric material
• MLatticeABC: Generic Lattice Constant Prediction of Crystal Materials using Machine Learning
• The Predictive Power of Chemical Bonding Analysis in Materials: a Perspective on Optoelectronic Properties
• CHILI: Chemically-Informed Large-scale Inorganic Nanomaterials Dataset for Advancing Graph Machine Learning
• Predicting band gaps and band-edge positions of oxide perovskites using DFT and machine learning
• Composition based crystal materials symmetry prediction using machine learning with enhanced descriptors
• Machine-learned metrics for predicting the likelihood of success in materials discovery
• Prediction of Reduced Glass Transition Temperature using Machine Learning
• An even-load-distribution design for composite bolted joints using a novel circuit model and artificial neural networks
• Deep-Learning Estimation of Band Gap with the Reading-Periodic-Table Method and Periodic Convolution Layer
• Active learning and element embedding approach in neural networks for infinite-layer versus perovskite oxides
• Generating a Machine-learned Equation of State for Fluid Properties
• Rapid Identification of X-ray Diffraction Spectra Based on Very Limited Data by Interpretable Convolutional Neural Networks
• Tree Models Machine Learning to Identify Liquid Metal based Alloy Superconductor
• Interpretation of Crystal Energy Landscapes with Kolmogorov-Arnold Networks
• Explainable Machine Learning for Oxygen Diffusion in Perovskites and Pyrochlores
• Machine learning, phase stability, and disorder with the Automatic Flow Framework for Materials Discovery
• Accelerated Discovery of Topological Conductors for Nanoscale Interconnects
• Supervised deep learning prediction of the formation enthalpy of the full set of configurations in complex phases: the $\sigma -$phase as an example
• M-CODE: Materials Categorization via Ontology, Dimensionality and Evolution
• Physics-informed machine learning for composition-process-property alloy design: shape memory alloy demonstration
• Assisting human experts in the interpretation of their visual process: A case study on assessing copper surface adhesive potency
• Nonmyopic Multifidelity Active Search
• Physics Aware Representation Learning on Electronic Charge Density for Materials Property Prediction