Big Data of Materials Science - Critical Role of the Descriptor

Abstract

Statistical learning of materials properties or functions so far starts with a largely silent, non-challenged step: the choice of the set of descriptive parameters (termed descriptor). However, when the scientific connection between the descriptor and the actuating mechanisms is unclear, causality of the learned descriptor-property relation is uncertain. Thus, trustful prediction of new promising materials, identification of anomalies, and scientific advancement are doubtful. We analyse this issue and define requirements for a suited descriptor. For a classical example, the energy difference of zincblende/wurtzite and rocksalt semiconductors, we demonstrate how a meaningful descriptor can be found systematically.

arXiv commentAccepted to Phys. Rev. Lett

References in corpus (2)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• Compressive sensing as a new paradigm for model building

Cited by in corpus (151)

• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• New Tolerance Factor to Predict the Stability of Perovskite Oxides and Halides
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Machine learning phases of matter
• The Computational 2D Materials Database: High-Throughput Modeling and Discovery of Atomically Thin Crystals
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• 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
• Comparing molecules and solids across structural and alchemical space
• Data-driven materials science: status, challenges and perspectives
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Recent Progress of the Computational 2D Materials Database (C2DB)
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• Machine Learning Energies of 2 M Elpasolite (ABC${}_2$D${}_6$) Crystals
• Insightful classification of crystal structures using deep learning
• Prediction model of band-gap for AX binary compounds by combination of density functional theory calculations and machine learning techniques
• Realizing the $XY$ Hamiltonian in polariton simulators
• Resolving transition metal chemical space: feature selection for machine learning and structure-property relationships
• Representation of compounds for machine-learning prediction of physical properties
• Symbolic Regression in Materials Science
• Unified Representation of Molecules and Crystals for Machine Learning
• Developing an improved Crystal Graph Convolutional Neural Network framework for accelerated materials discovery
• Autonomous discovery in the chemical sciences part II: Outlook
• Physical descriptor for the Gibbs energy of inorganic crystalline solids and temperature-dependent materials chemistry
• Understanding molecular representations in machine learning: The role of uniqueness and target similarity
• FAIR data enabling new horizons for materials research
• Machine Learning Phases of Strongly Correlated Fermions
• A recommendation engine for suggesting unexpected thermoelectric chemistries
• Accurate Interatomic Force Fields via Machine Learning with Covariant Kernels
• Machine Learning for Quantum Mechanical Properties of Atoms in Molecules
• Approximating quantum many-body wave-functions using artificial neural networks
• A learning scheme to predict atomic forces and accelerate materials simulations
• Atom2Vec: learning atoms for materials discovery
• Machine Learning the Voltage of Electrode Materials in Metal-ion Batteries
• Database of 2D hybrid perovskite materials: open-access collection of crystal structures, band gaps and atomic partial charges predicted by machine learning
• Orbital Graph Convolutional Neural Network for Material Property Prediction
• Probing many-body localization with neural networks
• Learning physical descriptors for materials science by compressed sensing
• Synthetic accessibility and stability rules of NASICONs
• Uncovering structure-property relationships of materials by subgroup discovery
• Non-perturbative methodologies for low-dimensional strongly-correlated systems: From non-abelian bosonization to truncated spectrum methods
• Machine Learning the Physical Non-Local Exchange-Correlation Functional of Density-Functional Theory
• Maximizing information from chemical engineering data sets: Applications to machine learning
• MODNet -- accurate and interpretable property predictions for limited materials datasets by feature selection and joint-learning
• Predicting the Curie temperature of ferromagnets using machine learning
• Unveiling phase transitions with machine learning
• Graph convolutional neural networks as "general-purpose" property predictors: the universality and limits of applicability
• Using Gaussian Process Regression to Simulate the Vibrational Raman Spectra of Molecular Crystals
• Representing individual electronic states for machine learning GW band structures of 2D materials
• Pattern Learning Electronic Density of States
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks
• Machine Learning Study of the Magnetic Ordering in 2D Materials
• Compositional optimization of hard-magnetic phases with machine-learning models
• Extrapolating quantum observables with machine learning: Inferring multiple phase transitions from properties of a single phase
• NOMAD 2018 Kaggle Competition: Solving Materials Science Challenges Through Crowd Sourcing
• Atomic positions independent descriptor for machine learning of material properties
• A machine learning-based selective sampling procedure for identifying the low energy region in a potential energy surface: a case study on proton conduction in oxides
• Transferable and extensible machine learning derived atomic charges for modeling hybrid nanoporous materials
• Microscopic origin of entropy-driven polymorphism in hybrid organic-inorganic perovskite materials
• Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential
• Sparse Modeling in Quantum Many-Body Problems
• Bayesian optimization of chemical composition: a comprehensive framework and its application to $R$Fe${}_{12}$-type magnet compounds
• Toward Accurate Interpretable Predictions of Materials Properties within Transformer Language Models
• IRNet: A General Purpose Deep Residual Regression Framework for Materials Discovery
• Artificial Intelligence for High-Throughput Discovery of Topological Insulators: the Example of Alloyed Tetradymites
• Towards Linearly Scaling and Chemically Accurate Global Machine Learning Force Fields for Large Molecules
• 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
• Multidimensional hyperspin machine
• Neural Network Kinetics for Exploring Diffusion Multiplicity and Chemical Ordering in Compositionally Complex Materials
• Multimodal Foundation Models for Material Property Prediction and Discovery
• Exploring a potential energy surface by machine learning for characterizing atomic transport
• Insights into cation ordering of double perovskite oxides from machine learning and causal relations
• Minimal set of crystallographic descriptors for sorption properties in hypothetical Metal Organic Frameworks: Role in sequential learning optimization
• Self-optimized construction of transition rate matrices from accelerated atomistic simulations with Bayesian uncertainty quantification
• Telling Cause from Effect using MDL-based Local and Global Regression
• A rule-free workflow for the automated generation of databases from scientific literature
• Hierarchical symbolic regression for identifying key physical parameters correlated with bulk properties of perovskites
• Machine-learning enabled thermodynamic model for the design of new rare-earth compounds
• First-Principles Prediction of Electronic Transport in Experimental Semiconductor Heterostructures via Physics-Based Machine Learning
• Important descriptors and descriptor groups of Curie temperatures of rare-earth transition-metal binary alloys
• Construction of Hamiltonians by supervised learning of energy and entanglement spectra
• Estimating the degree of non-Markovianity using machine learning
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Finite-temperature materials modeling from the quantum nuclei to the hot electrons regime
• Genarris: Random Generation of Molecular Crystal Structures and Fast Screening with a Harris Approximation
• Electronic structure based descriptor for characterizing local atomic environments
• Deep neural networks for direct, featureless learning through observation: the case of 2d spin models
• Compact atomic descriptors enable accurate predictions via linear models
• Controlled exploration of chemical space by machine learning of coarse-grained representations
• Kernel based quantum machine learning at record rate : Many-body distribution functionals as compact representations
• Resolution limit of data-driven coarse-grained models spanning chemical space
• Hardness and fracture toughness models by symbolic regression
• Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction
• Data-driven equation for drug-membrane permeability across drugs and membranes
• Parametrization of Non-Bonded Force Field Terms for Metal-Organic Frameworks Using Machine Learning Approach
• The fundamentals of quantum machine learning
• Machine learning for phase ordering dynamics of charge density waves
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Classifying surface probe images in strongly correlated electronic systems via machine learning
• Machine learning predictions for local electronic properties of disordered correlated electron systems
• Data-driven analysis of the electronic-structure factors controlling the work functions of perovskite oxides
• Extracting many-particle entanglement entropy from observables using supervised machine learning
• Validation Workflow for Machine Learning Interatomic Potentials for Complex Ceramics
• Structural Signatures for Thermodynamic Stability in Vitreous Silica: Insight from Machine Learning and Molecular Dynamics Simulations
• Building nonparametric $n$-body force fields using Gaussian process regression
• Machine learning for structure-property relationships: Scalability and limitations
• Machine Learning and Materials Informatics: Recent Applications and Prospects
• Self-supervised graph neural networks for accurate prediction of Néel temperature
• Materials Expert-Artificial Intelligence for Materials Discovery
• Leveraging Legacy Data to Accelerate Materials Design via Preference Learning
• Data-driven determination of the spin Hamiltonian parameters and their uncertainties: The case of the zigzag-chain compound KCu${}_4$P${}_3$O${}_{12}$
• Advancing descriptor search in materials science: feature engineering and selection strategies
• Electronic Descriptors for Supervised Spectroscopic Predictions
• 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
• Symbolic Regression in Materials Science: Discovering Interatomic Potentials from Data
• Kinetics of orbital ordering in cooperative Jahn-Teller models: Machine-learning enabled large-scale simulations
• Deep Learning Hamiltonians from Disordered Image Data in Quantum Materials
• Topological descriptors for the electron density of inorganic solids
• Functional Unit: A New Perspective on Materials Science Research Paradigms
• A Physics-Informed Machine Learning Model for Porosity Analysis in Laser Powder Bed Fusion Additive Manufacturing
• Ab initio machine learning in chemical compound space
• A Fuzzy Classification Framework to Identify Equivalent Atoms in Complex Materials and Molecules
• Machine Learning S-Wave Scattering Phase Shifts Bypassing the Radial Schrödinger Equation
• A new strategy for directly calculating the minimum eigenvector of matrices without diagonalization
• Data-driven formulation of natural laws by recursive-LASSO-based symbolic regression
• Operator-induced structural variable selection for identifying materials genes
• Establishing simple relationship between eigenvector and matrix elements
• Self-supervised Representations and Node Embedding Graph Neural Networks for Accurate and Multi-scale Analysis of Materials
• What can one learn about material structure given a single first-principles calculation?
• Replica Analysis for Ensemble Techniques in Variable Selection
• Prediction of Atomization Energies of Au13+ Clusters through the Machine Learning Approach
• Machine-learning force-field models for dynamical simulations of metallic magnets
• Simple prediction of immiscible metal alloying based on metastability analysis
• Active learning and element embedding approach in neural networks for infinite-layer versus perovskite oxides
• Machine learning, phase stability, and disorder with the Automatic Flow Framework for Materials Discovery
• A computational high-throughput search for new ternary superalloys
• Graph Neural Network for Hamiltonian-Based Material Property Prediction
• Physics-informed machine learning for composition-process-property alloy design: shape memory alloy demonstration
• A Short Review on Data Modelling for Vector Fields
• Learning Functional Dependencies with Sparse Regression
• TCMI: a non-parametric mutual-dependence estimator for multivariate continuous distributions
• Machine learning approach for vibronically renormalized electronic band structures
• Chemical Bond-Based Representation of Materials
• Causal Inference on Multivariate and Mixed-Type Data
• Machine-learning modeling of magnetization dynamics in quasi-equilibrium and driven metallic spin systems
• Machine learning reveals orbital interaction in crystalline materials
• Learning general sparse additive models from point queries in high dimensions