Data-driven materials science: status, challenges and perspectives

Abstract

Data-driven science is heralded as a new paradigm in materials science. In this field, data is the new resource, and knowledge is extracted from materials data sets that are too big or complex for traditional human reasoning - typically with the intent to discover new or improved materials or materials phenomena. Multiple factors, including the open science movement, national funding, and progress in information technology, have fueled its development. Such related tools as materials databases, machine learning, and high-throughput methods are now established as parts of the materials research toolset. However, there are a variety of challenges that impede progress in data-driven materials science: data veracity, integration of experimental and computational data, data longevity, standardization, and the gap between industrial interests and academic efforts. In this perspective article, we discuss the historical development and current state of data-driven materials science, building from the early evolution of open science to the rapid expansion of materials data infrastructures. We also review key successes and challenges so far, providing a perspective on the future development of the field.

arXiv commentAdded new entries to the materials data infrastucture tables, updated references and affiliations

References in corpus (39)

• XGBoost: A Scalable Tree Boosting System
• Deep Learning in Neural Networks: An Overview
• Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
• Automatic chemical design using a data-driven continuous representation of molecules
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• On representing chemical environments
• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• SchNet - a deep learning architecture for molecules and materials
• DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• New Tolerance Factor to Predict the Stability of Perovskite Oxides and Halides
• High-throughput electronic band structure calculations: challenges and tools
• AFLOW: An automatic framework for high-throughput materials discovery
• OpenML: networked science in machine learning
• High-entropy high-hardness metal carbides discovered by entropy descriptors
• Big Data of Materials Science - Critical Role of the Descriptor
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Comparing molecules and solids across structural and alchemical space
• Machine Learning Unifies the Modelling of Materials and Molecules
• By-passing the Kohn-Sham equations with machine learning
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Finding Density Functionals with Machine Learning
• Discovering Phase Transitions with Unsupervised Learning
• AiiDA: Automated Interactive Infrastructure and Database for Computational Science
• Error estimates for solid-state density-functional theory predictions: an overview by means of the ground-state elemental crystals
• Machine learning modeling of superconducting critical temperature
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Insightful classification of crystal structures using deep learning
• Alchemical and structural distribution based representation for improved QML
• Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
• WACSF - Weighted Atom-Centered Symmetry Functions as Descriptors in Machine Learning Potentials
• Accurate molecular polarizabilities with coupled-cluster theory and machine learning
• A RESTful API for exchanging Materials Data in the AFLOWLIB.org consortium
• Growth Mechanism and Origin of High $s{p}^3$ Content in Tetrahedral Amorphous Carbon
• Efficient Bayesian Inference of Atomistic Structure in Complex Functional Materials
• Uncovering structure-property relationships of materials by subgroup discovery
• Chemical diversity in molecular orbital energy predictions with kernel ridge regression
• Finding the Right Bricks for Molecular Lego: A Data Mining Approach to Organic Semiconductor Design
• Test set for materials science and engineering with user-friendly graphic tools for error analysis: Systematic benchmark of the numerical and intrinsic errors in state-of-the-art electronic-structure approximations

Cited by in corpus (59)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Autonomous discovery in the chemical sciences part I: Progress
• Autonomous discovery in the chemical sciences part II: Outlook
• A critical examination of compound stability predictions from machine-learned formation energies
• FAIR data enabling new horizons for materials research
• Database of 2D hybrid perovskite materials: open-access collection of crystal structures, band gaps and atomic partial charges predicted by machine learning
• Recent Advances and Applications of Machine Learning in Experimental Solid Mechanics: A Review
• Data-driven discovery of novel 2D materials by deep generative models
• Deep Learning Model for Finding New Superconductors
• OPTIMADE, an API for exchanging materials data
• Thermodynamics and dielectric response of ${\text{BaTiO}}_3$ by data-driven modeling
• Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis
• Machine Learning and Evolutionary Prediction of Superhard B-C-N Compounds
• Efficient Training of ANN Potentials by Including Atomic Forces via Taylor Expansion and Application to Water and a Transition-Metal Oxide
• Exploring diamond-like lattice thermal conductivity crystals via feature-based transfer learning
• Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange
• Recording provenance of workflow runs with RO-Crate
• ET-AL: Entropy-Targeted Active Learning for Bias Mitigation in Materials Data
• Relativistic correction scheme for core-level binding energies from $GW$
• Predicting Gas-Particle Partitioning Coefficients of Atmospheric Molecules with Machine Learning
• Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet
• AlabOS: A Python-based Reconfigurable Workflow Management Framework for Autonomous Laboratories
• A machine learning route between band mapping and band structure
• Autonomous sputter synthesis of thin film nitrides with composition controlled by Bayesian optimization of optical plasma emission
• Predicting Superconducting Transition Temperature through Advanced Machine Learning and Innovative Feature Engineering
• Toward Automated Simulation Research Workflow through LLM Prompt Engineering Design
• Machine Learning Accelerated Descriptor Design for Catalyst Discovery in CO${}_2$ to Methanol Conversion
• An open-source, end-to-end workflow for multidimensional photoemission spectroscopy
• Atomic structure optimization with machine-learning enabled interpolation between chemical elements
• Electronic Characterization of a Charge-Transfer Complex Monolayer on Graphene
• Machine Learning Enabled Discovery of Application Dependent Design Principles for Two-dimensional Materials
• Screening Mixed-Metal Sn${}_2$M(III)Ch${}_2$X${}_3$ Chalcohalides for Photovoltaic Applications
• The Northeast Materials Database for Magnetic Materials
• Impact of Data Bias on Machine Learning for Crystal Compound Synthesizability Predictions
• Towards data-driven mass spectrometry in atmospheric science
• Illustrating an Effective Workflow for Accelerated Materials Discovery
• Sim2Ls: FAIR simulation workflows and data
• Accelerating Electronic Stopping Power Predictions by 10 Million Times with a Combination of Time-Dependent Density Functional Theory and Machine Learning
• Atomic and electronic structure of cesium lead triiodide surfaces
• Surface reconstruction of tetragonal methylammonium lead triiodide
• Classification-based detection and quantification of cross-domain data bias in materials discovery
• Active and transfer learning with partially Bayesian neural networks for materials and chemicals
• Bridging Fidelities to Predict Nanoindentation Tip Radii Using Interpretable Deep Learning Models
• Ab initio property characterisation of thousands of previously unknown 2D materials
• Iterative peak-fitting of frequency-domain data via deep convolution neural networks
• Shifting computational boundaries for complex organic materials
• Symbolic Regression in Materials Science: Discovering Interatomic Potentials from Data
• Morphological evolution via surface diffusion learned by convolutional, recurrent neural networks: extrapolation and prediction uncertainty
• Efficient dataset generation for machine learning perovskite alloys
• Data analysis of $ab$ $initio$ effective Hamiltonians in iron-based superconductors $\unicode{x2014}$ Construction of predictors for superconducting critical temperature
• The AiiDA-Spirit plugin for automated spin-dynamics simulations and multi-scale modelling based on first-principles calculations
• The Predictive Power of Chemical Bonding Analysis in Materials: a Perspective on Optoelectronic Properties
• Elemental Reactivity Maps for Materials Discovery
• Towards knowledge-based workflows: a semantic approach to atomistic simulations for mechanical and thermodynamic properties
• Scalable Training of Neural Network Potentials for Complex Interfaces Through Data Augmentation
• Electrostatic Discovery Atomic Force Microscopy
• A critical assessment of bonding descriptors for predicting materials properties
• GEWUM: General Exploration Workflow for the Utopia of Materials: A Unified Platform for Automated Structure Generation, Selection, and Validation
• Design Rules for Optimizing Quaternary Mixed-Metal Chalcohalides