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

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.

• Publication year

  2016

• Venue

  arXiv: Materials Science

• Publication date

  2016-06-30

• Fields of study

  Physics, Materials Science, Computer Science

• Identifiers
  DOI 10.1038/npjcompumats.2016.28arXiv 1606.09551
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Materials informatics

  2018cited by this paper
• Perspective: Materials informatics and big data: Realization of the “fourth paradigm” of science in materials science

  2016cited by this paper
• Perspective: Materials informatics across the product lifecycle: Selection, manufacturing, and certification

  2016cited by this paper
• Perspective: Codesign for materials science: An optimal learning approach

  2016cited by this paper
• Machine learning bandgaps of double perovskites

  2016cited by this paper
• Predicting density functional theory total energies and enthalpies of formation of metal-nonmetal compounds by linear regression

  2016cited by this paper
• Data mining our way to the next generation of thermoelectrics

  2016cited by this paper
• Materials Data Science: Current Status and Future Outlook

  2015cited by this paper
• Materials Informatics: The Materials ``Gene'' and Big Data

  2015cited by this paper
• The Open Quantum Materials Database (OQMD): assessing the accuracy of DFT formation energies

  2015cited by this paper
• Crystal structure representations for machine learning models of formation energies

  2015cited by this paper
• A Bayesian Approach to Calibrating High-Throughput Virtual Screening Results and Application to Organic Photovoltaic Materials

  2015cited by this paper
• Big-deep-smart data in imaging for guiding materials design.

  2015cited by this paper
• ProtDCal: A program to compute general-purpose-numerical descriptors for sequences and 3D-structures of proteins

  2015cited by this paper
• Solution phase n-doping of C60and PCBM using tetrabutylammonium fluoride

  2014cited by this paper
• Prediction and Calculation of Crystal Structures: Methods and Applications

  2014cited by this paper
• Data mining approaches to high-throughput crystal structure and compound prediction.

  2014cited by this paper
• Combinatorial development of bulk metallic glasses.

  2014cited by this paper
• Informatics-aided bandgap engineering for solar materials

  2014cited by this paper
• Big data of materials science: critical role of the descriptor.

  2014cited by this paper
• Prediction and accelerated laboratory discovery of previously unknown 18-electron ABX compounds.

  2014cited by this paper
• Sparse representation for a potential energy surface

  2014cited by this paper
• Dissolving the Periodic Table in Cubic Zirconia: Data Mining to Discover Chemical Trends

  2014cited by this paper
• Combinatorial screening for new materials in unconstrained composition space with machine learning

  2014influential reference
• Spinel compounds as multivalent battery cathodes: A systematic evaluation based on ab initio calculations

  2014cited by this paper
• High‐Throughput Computational Screening of New Li‐Ion Battery Anode Materials

  2013cited by this paper
• Commentary: The Materials Project: A materials genome approach to accelerating materials innovation

  2013cited by this paper
• The high-throughput highway to computational materials design.

  2013cited by this paper
• Materials Design and Discovery with High-Throughput Density Functional Theory: The Open Quantum Materials Database (OQMD)

  2013cited by this paper
• Accelerating materials property predictions using machine learning

  2013cited by this paper
• “Property Phase Diagrams” for Compound Semiconductors through Data Mining

  2013cited by this paper
• How to represent crystal structures for machine learning: Towards fast prediction of electronic properties

  2013cited by this paper
• Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single- and binary-component solids

  2013cited by this paper
• Data-mined similarity function between material compositions

  2013cited by this paper
• A search model for topological insulators with high-throughput robustness descriptors.

  2012cited by this paper
• Carbonophosphates: A New Family of Cathode Materials for Li-Ion Batteries Identified Computationally

  2012cited by this paper
• AFLOWLIB.ORG: A distributed materials properties repository from high-throughput ab initio calculations

  2012cited by this paper
• Information-Theoretic Approach for the Discovery of Design Rules for Crystal Chemistry

  2012cited by this paper
• A high-throughput infrastructure for density functional theory calculations

  2011cited by this paper
• Fast and accurate modeling of molecular atomization energies with machine learning.

  2011cited by this paper
• Data mined ionic substitutions for the discovery of new compounds.

  2011cited by this paper
• Dlib-ml: A Machine Learning Toolkit

  2009cited by this paper
• Performance of neural networks in materials science

  2009cited by this paper
• The WEKA data mining software: an update

  2009cited by this paper
• Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons.

  2009cited by this paper
• δ TRIP steel

  2007cited by this paper
• Formation of Bulk Metallic Glasses and Their Composites

  2007cited by this paper
• Rotation Forest: A New Classifier Ensemble Method

  2006cited by this paper
• Predicting crystal structure by merging data mining with quantum mechanics

  2006cited by this paper
• DRAGON SOFTWARE: AN EASY APPROACH TO MOLECULAR DESCRIPTOR CALCULATIONS

  2006cited by this paper
• Bioinspired antifouling polymers

  2005cited by this paper
• Bulk metallic glasses

  2004cited by this paper
• Data-driven atomic environment prediction for binaries using the Mendeleev number: Part 1. Composition AB

  2004cited by this paper
• Predicting crystal structures with data mining of quantum calculations.

  2003cited by this paper
• Handbook of Molecular Descriptors

  2002cited by this paper
• New developments in the Inorganic Crystal Structure Database (ICSD): accessibility in support of materials research and design.

  2002cited by this paper
• Formation and High Mechanical Strength of Bulk Glassy Alloys in Zr-Al-Co-Cu System

  2002cited by this paper
• Random Forests

  2001cited by this paper
• Stabilization of metallic supercooled liquid and bulk amorphous alloys

  2000cited by this paper
• The Random Subspace Method for Constructing Decision Forests

  1998cited by this paper
• Nonequilibrium phase diagrams of ternary amorphous alloys

  1997cited by this paper
• Artificial neural network aided design of catalyst for propane ammoxidation

  1997cited by this paper
• On the Design, Analysis, and Characterization of Materials Using Computational Neural Networks

  1996cited by this paper
• Cumulative Author Index

  1995cited by this paper
• Vegard's law.

  1991cited by this paper
• Materials Science and Engineering: An Introduction

  1985cited by this paper
• Detailed Balance Limit of Efficiency of p‐n Junction Solar Cells

  1961cited by this paper

• Data‐Guided Photocatalysis: Supervised Machine Learning in Water Splitting and CO 2 Conversion

  2026cites this paper
• Data-driven and computational insights into borophene: Integrating machine learning with DFT and AI

  2026cites this paper
• Machine learning-assisted design of lightweight refractory high-entropy alloys: a comprehensive review

  2026cites this paper
• Machine-Learning-Guided Discovery and Statistical Analysis of Multielemental Reverse Water–Gas Shift Catalysts

  2026cites this paper
• Toward intelligent design of solid-state hydrogen storage: trends, challenges, and machine learning insights

  2026cites this paper
• Perovskite electrolytes for dual-ion conduction in SOFCs: A combined DFT–NEB–PCA approach

  2026cites this paper
• TheMeCat: Dataset of Thermocatalytic Conversion of CO2 to Methanol

  2026cites this paper
• Soft lattice elasto-plasticity of halide perovskites: origin of multifunctionalities

  2026cites this paper
• Chemical Feature Engineering and Defect-Aware Structural Fingerprint Representations for Complex Defects in 2D Materials.

  2026cites this paper
• SPFlow: A flow-based symmetry-preserving generative model for crystalline materials

  2026cites this paper
• Data-Driven Deciphering Structure-Mössbauer Spectroscopy Relationships in Iron-Based Compounds.

  2026cites this paper
• Machine learning technique for prediction of crystal structure in austenitic and martensitic phase of Ni–Mn-based Heusler alloys

  2026cites this paper
• Machine Learning Prediction of Ionic Conductivity and Binding Energy in Doped Li2ZrCl6 Halides for Solid-State Electrolyte.

  2026cites this paper
• Machine learning analysis of band gap difference between HSE and PBE functionals in double perovskites

  2026cites this paper
• Multimodal explainable artificial intelligence-driven analysis of quantum size effects in copper nanoclusters for hydrogen storage

  2026cites this paper
• Machine learning aided bandgap and defect engineering of mixed halide perovskites for photovoltaic applications

  2026cites this paper
• Predicting vacancy formation energies in refractory non-dilute random alloys using improved graph-based machine learning models trained on density functional theory data

  2026cites this paper
• Performance Assessment of AB2 Alloys (A = Zr, Ti; B = Mn, Ni, Cr, V, Fe, Al) for Hydrogen Storage and Separation in the Presence of Carbon Dioxide

  2026cites this paper
• A parametrically‐Conditioned Deep Learning Surrogate for Coherent Spinodal Decomposition

  2026cites this paper
• Data-driven inorganic material design for future all-solid-state batteries: innovations and perspectives

  2026cites this paper
• Machine-learning-accelerated band gap prediction from chemical composition with near-experimental accuracy

  2026cites this paper
• AI-Driven Design of Sustainable Flame-Retardant Biodegradable Polymer Composites

  2026cites this paper
• Development of Machine Learning Models for Thermoelectric Figure of Merit Predictions of Doped Chalcogenides

  2026cites this paper
• Recent advances in carbon-based materials for supercapacitors: synthesis, electrochemical properties, and impact of machine learning

  2026cites this paper
• AI-driven bandgap engineering of Mg–Ca Co-doped HgS semiconductors: A hybrid ML–DL–DFT+U framework for next-generation solar energy materials

  2026cites this paper
• Interpretable machine learning-aided prediction of ferroelectric property in HfO2-based thin films

  2026cites this paper
• AI-driven design and applications of quantum dots

  2026cites this paper
• Data-driven assisted design of highly stable and superhard high-entropy diborides

  2026cites this paper
• Applied mathematical and computational frameworks in materials science: a comprehensive review

  2026cites this paper
• Structure maps and crystal growth of ternary ThCr2Si2-type rare-earth transition-metal silicides and germanides

  2026cites this paper
• MAPAL: A python library for mapping features and properties of alloys over compositional spaces

  2026cites this paper
• Machine learning prediction and multivariate pattern recognition for optimizing the mechanical behavior of heat-treated SLM-fabricated UNS S32205 duplex stainless steel

  2026cites this paper
• Machine learning-driven prediction of magnetic parameters in magnetic nanoparticles

  2026cites this paper
• Synergistic machine learning and DFT driven high-throughput screening strategy for A2BX6-Type inorganic perovskite photovoltaic materials

  2026cites this paper
• Deconstruction Analysis and Regeneration Optimization of Solid Electrolyte Components for Energy Storage Based on the Finite Data Statistics

  2026cites this paper
• Sintering Process Analysis of Aluminum Matrix Composites Using Machine Learning

  2026cites this paper
• Accelerated prediction of elastic constants in cubic crystals via interpretable machine learning: From metallic alloys to broader material systems

  2026cites this paper
• Machine Learning-Guided Ab Initio Study of Na Super Ionic Conductor-Type Na4Hf2(SiO4)3 Solid-State Electrolyte for Sodium-Ion Batteries

  2026cites this paper
• High-performance interpretable model for exfoliation energy prediction of 2D nanomaterials

  2026cites this paper
• Automated Extraction of Multicomponent Alloy Data Using Large Language Models for Sustainable Design

  2026cites this paper
• Towards intelligent design of metallic glasses: a data-driven pathway for closing the theory-experiment loop

  2026cites this paper
• Space Series: Leveraging Geometric Features of Heterostructures for Cross-Composition Property Prediction of Core-Shell Quantum Dots.

  2026cites this paper
• Artificial Intelligence in Accelerating Materials Discovery: Opportunities and Challenges

  2026cites this paper
• Artificial Intelligence‐Driven Discovery and Design of Solid-State Hydrogen Storage Materials

  2026cites this paper
• ML-guided screening of chalcogenide perovskites as solar energy materials

  2026cites this paper
• A physically informed and transferable framework for predicting cubic crystal lattice constants

  2026cites this paper
• Clever Materials: When Models Identify Good Materials for the Wrong Reasons

  2026cites this paper
• NIMMGen: Learning Neural-Integrated Mechanistic Digital Twins with LLMs

  2026cites this paper
• Deep learning and multiple linear regression for predicting mechanical properties from elastic constants: Application to aluminum-based alloys used in 3D printing

  2026cites this paper
• M-CODE: Materials Categorization via Ontology, Dimensionality and Evolution

  2026cites this paper
• Searching for high-performance thermoelectric materials via an advanced machine learning framework

  2026cites this paper
• Word embeddings as autonomous predictors in materials design—the effect of inherent variability on information transfer

  2026influential citation
• Information-Theoretic Multi-Model Fusion for Target-Oriented Adaptive Sampling in Materials Design

  2026cites this paper
• Thermophysical properties of spark plasma sintered UCo: a comparison with machine learning predictions

  2026cites this paper
• Machine Learning-Driven Prediction of Microstructural Evolution and Mechanical Properties in Heat-Treated Steels Using Gradient Boosting

  2026cites this paper
• Uncertainty estimation affects predictor selection and its calibration improves materials optimization

  2026cites this paper
• Predicting the critical temperature of superconductors and materials classification with a balanced dataset without prior knowledge

  2026cites this paper
• Active Learning Strategies for Efficient Machine-Learned Interatomic Potentials Across Diverse Material Systems

  2026cites this paper
• SSFormer: Self-supervised transformer model for predicting the properties of crystalline materials

  2026cites this paper
• Artificial intelligence models for supercapacitor performance prediction in energy storage

  2026cites this paper
• Efficiently predicting pressure-composition-temperature diagrams to discover low-stability metal hydrides

  2026cites this paper
• Living dynamic polymeric materials.

  2025cites this paper
• Accelerated discovery of solid-state battery properties enabled by active learning approaches

  2025cites this paper
• Ternary materials discovery using human-in-the-loop generative machine learning

  2025cites this paper
• Bridging language models and computational materials science: A prompt‐driven framework for material property prediction

  2025cites this paper
• Machine Learning-Based Computational Design Methods for High-Entropy Alloys

  2025cites this paper
• A machine learning strategy to achieve dual-synchronous property improvement of aviation Al-Cu-Mg alloy

  2025cites this paper
• Machine Learning and Explainable AI-Guided Design and Optimization of High-Entropy Alloys as Binder Phases for WC-Based Cemented Carbides

  2025cites this paper
• Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey

  2025cites this paper
• Machine Learning‐Driven Band Gap Prediction/Classification and Feature Importance Analysis of Inorganic Perovskites

  2025cites this paper
• Explainable Artificial Intelligence (XAI) for Material Design and Engineering Applications: A Quantitative Computational Framework

  2025cites this paper
• Space Group Equivariant Crystal Diffusion

  2025cites this paper
• Adsorption behavior and surface modification of metal atoms on AlGaN surfaces with multiple configurations: First principle calculation assisted by machine learning

  2025cites this paper
• Explainable Machine Learning for Oxygen Diffusion in Perovskites and Pyrochlores

  2025cites this paper
• Comprehensive Review on the Use of Machine Learning Techniques Applied to the Ultrasound Data for the Characterisation of Porosity across Carbon Fibre Reinforced Polymer Layers

  2025cites this paper
• Feature-Extended Descriptor Construction for Prediction of Consecutive Elementary Reaction Energies in Methane Oxidation

  2025cites this paper
• Machine Learning-Assisted Discovery of Empirical Rule for Martensite Transition Temperature of Shape Memory Alloys

  2025cites this paper
• Exploration of crystal chemical space using text-guided generative artificial intelligence

  2025cites this paper
• Rationally Design Thermoelectric Materials Based on Ingenious Machine Learning Methods

  2025cites this paper
• A hierarchical HGBT-based machine learning framework for predicting the power conversion efficiency of perovskite solar cells

  2025cites this paper
• Learning simple heuristic rules for classifying materials based on chemical composition

  2025cites this paper
• Discovering key factors determining perovskite bandgap under data scarcity inspired by knowledge distillation.

  2025cites this paper
• Structure and Synthesizability of Iron-Sulfur Metal-Organic Frameworks.

  2025cites this paper
• Controllable Crystalline Phases of Multi‐Cation Oxides

  2025cites this paper
• Amending CALPHAD databases using a neural network for predicting mixing enthalpy of liquids

  2025cites this paper
• Synergistic Machine Learning Guided Discovery of ABa3(BSe3)2X (A = Rb, Cs; X = Cl, Br, I): A Promising Family as Property‐Balanced IR Functional Materials

  2025cites this paper
• A Deep Generative Model for the Inverse Design of Transition Metal Ligands and Complexes

  2025cites this paper
• Ten‐Electron Count Rule of MXene‐Supported Single‐Atom Catalysts for Sulfur Reduction in Lithium–Sulfur Batteries

  2025cites this paper
• Prediction of Enthalpy of Mixing of Binary Alloys Based on Machine Learning and CALPHAD Assessments

  2025cites this paper
• Prediction of thermodynamic stability of rare earth compounds by machine learning model

  2025cites this paper
• Predicting thermophysical properties and fracture toughness of Zirconia-based thermal barrier coating by interpretable machine learning method

  2025cites this paper
• The ensemble learning algorithms for prediction high entropy alloys phases

  2025cites this paper
• Unveiling potential lithium ionic conductors through machine learning and atomic simulation approaches

  2025cites this paper
• Harnessing machine learning for high-entropy alloy catalysis: a focus on adsorption energy prediction

  2025cites this paper
• Application of Machine Learning in Amorphous Alloys

  2025cites this paper
• Ensemble Machine Learning for the Prediction and Understanding of the Refractive Index in Chalcogenide Glasses

  2025cites this paper
• A combined experimental and machine learning exploration of Ti2-xZrxMnCrFeNi high entropy Laves hydrides

  2025cites this paper
• Fast-Track to Catalyst Stability: Machine Learning Optimized Predictions for M1/M2-N6-Gra Catalysts.

  2025cites this paper
• A machine learning model with minimize feature parameters for multi-type hydrogen evolution catalyst prediction

  2025cites this paper
• Realizing Ultra-fast Spheroidization of GCr15 Bearing Steel by Analyzing the Correlation of Carbide Dissolution Law and Pulsed Electric Current Parameters Through Machine Learning

  2025cites this paper