Big data of materials science: critical role of the descriptor.

Statistical learning of materials properties or functions so far starts with a largely silent, nonchallenged 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, the causality of the learned descriptor-property relation is uncertain. Thus, a trustful prediction of new promising materials, identification of anomalies, and scientific advancement are doubtful. We analyze this issue and define requirements for a suitable descriptor. For a classic example, the energy difference of zinc blende or wurtzite and rocksalt semiconductors, we demonstrate how a meaningful descriptor can be found systematically.

• Publication year

  2014

• Venue

  Physical Review Letters

• Publication date

  2014-11-27

• Fields of study

  Medicine, Materials Science, Physics

• Identifiers
  DOI 10.1103/PhysRevLett.114.105503arXiv 1411.7437PMID 25815947
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• A Mathematical Introduction to Compressive Sensing

  2015cited by this paper
• Origins of hole traps in hydrogenated nanocrystalline and amorphous silicon revealed through machine learning

  2014cited by this paper
• A Mathematical Introduction to Compressive Sensing

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

  2013cited by this paper
• Compressive sensing as a paradigm for building physics models

  2013cited by this paper
• Data mining for materials: Computational experiments with AB compounds

  2012cited by this paper
• I and J

  2012cited by this paper
• Fast and accurate modeling of molecular atomization energies with machine learning.

  2011cited by this paper
• THE GROUND STATE OF THE ELECTRON GAS BY A STOCHASTIC METHOD

  2010cited by this paper
• Ab initio molecular simulations with numeric atom-centered orbitals

  2009cited by this paper
• Computational Complexity: A Modern Approach

  2009cited by this paper
• Combinatorial Materials Sciences: Experimental Strategies for Accelerated Knowledge Discovery

  2008cited by this paper
• Predicting crystal structure by merging data mining with quantum mechanics

  2006cited by this paper
• The formation of molecular clouds in spiral galaxies

  2006cited by this paper
• Causation: A Unified Framework for the Social Sciences

  2005cited by this paper
• Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information

  2004cited by this paper
• Causation, Prediction, and Search

  2003cited by this paper
• An Introduction to Variable and Feature Selection

  2003cited by this paper
• The Elements of Statistical Learning

  2003cited by this paper
• ! I ! i ! I ! i ! I ! i ! I ! I 138 ! !

  2000cited by this paper
• Regression Shrinkage and Selection via the Lasso

  1996cited by this paper
• Relativistic total energy using regular approximations

  1994cited by this paper
• Accurate and simple analytic representation of the electron-gas correlation energy.

  1992cited by this paper
• A chemical scale for crystal-structure maps

  1984cited by this paper
• Systematization of the stable crystal structure of all AB-type binary compounds: A pseudopotential orbital-radii approach

  1980cited by this paper
• Ionicity of the Chemical Bond in Crystals

  1970cited by this paper
• Quantum Dielectric Theory of Electronegativity in Covalent Systems. I. Electronic Dielectric Constant

  1969cited by this paper
• A and V

  1962cited by this paper
• Causality : Models , Reasoning , and Inference

  year unknowncited by this paper

• Equivariant Neural Networks for Force-Field Models of Lattice Systems

  2026cites this paper
• A Comparative Study of Structural Representations for 2D Materials: Insights from Dynamic Collision Fingerprint and Matminer

  2026cites this paper
• Artificial intelligence in the development of structural and functional materials: A transformative frontier and complementary enabler of the rational alloy design framework

  2026cites this paper
• Machine learning-enhanced exploration of 2D MXene van der Waals heterostructures for energy storage

  2026cites this paper
• Machine-learning modeling of magnetization dynamics in quasi-equilibrium and driven metallic spin systems

  2026cites this paper
• Graph neural network force fields for adiabatic dynamics of lattice Hamiltonians

  2026cites this paper
• Machine-learning force-field models for dynamical simulations of metallic magnets

  2026cites this paper
• Topological transitions via dynamic SOC in Kagome lattices

  2026cites this paper
• Information-Theoretic Multi-Model Fusion for Target-Oriented Adaptive Sampling in Materials Design

  2026cites this paper
• Machine learning nonequilibrium phase transitions in charge-density wave insulators

  2026cites this paper
• Discovery of Interpretable Physical Laws in Materials via Language-Model-Guided Symbolic Regression

  2026cites this paper
• AI-Driven Decoding of Material Dynamics: From Machine Learning Potentials and Interpretability to Generative Prediction.

  2025cites this paper
• Interpretable Machine Learning for the Design of (K, Na)NbO3-Based Piezoceramics Using Combinatorial and Knowledge-Embedded Descriptors.

  2025cites this paper
• Kinetics of Peierls dimerization transition: Machine learning force-field approach

  2025cites this paper
• TMDCs and related vdW-heterostructures: a gap analysis of hybrid synthesis and the realization of optimal properties for practical applications, current challenges, and future prospects

  2025cites this paper
• From Formability to Bandgap: Machine Learning Accelerates the Discovery and Application of Perovskite Materials.

  2025cites this paper
• An Interpretable Machine Learning Workflow for Evaluating and Analyzing the Performance of Thermoelectric Materials

  2025cites this paper
• Materials informatics: A review of AI and machine learning tools, platforms, data repositories, and applications to architectured porous materials

  2025cites this paper
• Topological Descriptors for the Electron Density of Inorganic Solids

  2025cites this paper
• Machine Learning in Polymer Research

  2025cites this paper
• Data‐Driven Design of Mechanically Hard Soft Magnetic High‐Entropy Alloys

  2025cites this paper
• Advancements and Applications of Artificial Intelligence and Machine Learning in Material Science and Membrane Technology: A Comprehensive Review

  2025cites this paper
• Feature-Driven Prediction of HOMO-LUMO Gaps in Transition-Metal Complexes Using the SLEET Model: A SMILES-Based Transformer Framework.

  2025cites this paper
• Machine Learning in Flocculant Research and Application: Toward Smart and Sustainable Water Treatment

  2025cites this paper
• Tradition of Data-Intensive Use: The Example of Domain Thermophysics. Methods and Algorithms

  2025cites this paper
• Enhancing composition-based materials property prediction by cross-modal knowledge transfer

  2025cites this paper
• Digital Descriptors in Predicting Catalysis Reaction Efficiency and Selectivity.

  2025cites this paper
• Non-blocking functional dependency discovery from data streams

  2025cites this paper
• Evolvable Conditional Diffusion

  2025cites this paper
• Recent progress in the design and application of machine learning for the hydrogen evolution reaction in electrocatalysis and photocatalysis

  2025cites this paper
• Self supervised ensemble learning models for 2D semiconductors bandgap prediction

  2025cites this paper
• Taskblaster: a generic framework for automated computational workflows

  2025cites this paper
• High throughput screening of new piezoelectric materials using graph machine learning and knowledge graph approach

  2025cites this paper
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie

  2025cites this paper
• Confidence evaluation for feature selection in expanded feature space based on density of states

  2025cites this paper
• Machine learning-assisted design and prediction of materials for batteries based on alkali metals.

  2025cites this paper
• EFTGAN: Elemental features and transferring corrected data augmentation for the study of high-entropy alloys

  2025cites this paper
• Predicting material properties in AlSi12Mg alloy additive manufacturing using KNN and ANN machine learning techniques

  2025cites this paper
• Bibliometric Study on the Role of Big Data in the Science Revolution

  2025cites this paper
• Accelerated discovery of ultraincompressible, superhard materials via physics-enhanced active learning.

  2025cites this paper
• Enabling extrapolation of Young’s modulus of CaO-Al2O3-SiO2 ternary glasses by topology-informed machine learning

  2025cites this paper
• Harnessing the leading edge: machine learning ventures in chemistry and materials science.

  2025cites this paper
• Discovery and Design of Equiatomic Heusler Alloys Magnetic Properties using Machine Learning with DFT Approach

  2025cites this paper
• Data-Driven Studies of Two-Dimensional Materials and Their Nonlinear Optical Properties.

  2025cites this paper
• Machine learning-guided space-filling designs for high throughput liquid formulation development

  2025cites this paper
• Exploring a novel approach for computing topological descriptors of graphene structure using neighborhood multiple M-polynomial

  2025cites this paper
• A machine learning workflow for large-scale discovery of direct bandgap double perovskites

  2025cites this paper
• A review of machine learning approaches for the discovery of thermoelectric materials

  2025cites this paper
• Machine Learning Helps Data Mining to Build Descriptor Databases for Lithium‐Ion Batteries

  2025cites this paper
• Rapid data acquisition and machine learning-assisted composition design of functionally graded alloys via wire arc additive manufacturing

  2025cites this paper
• Designing and synthesizing perovskites with targeted bandgaps via tailored descriptors

  2025cites this paper
• Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding

  2024cites this paper
• Interpretable machine learning boosting the discovery of targeted organometallic compounds with optimal bandgap

  2024cites this paper
• A critical reflection on attempts to machine-learn materials synthesis insights from text-mined literature recipes.

  2024cites this paper
• Prediction of phase and tensile properties of selective laser melting manufactured high entropy alloys by machine learning

  2024cites this paper
• Rational Design of Deep Learning Networks Based on a Fusion Strategy for Improved Material Property Predictions.

  2024cites this paper
• Speeding up the development of solid state electrolyte by machine learning

  2024cites this paper
• The mastery of details in the workflow of materials machine learning

  2024cites this paper
• Electron-vibrational renormalization in fullerenes through ab initio and machine learning methods.

  2024cites this paper
• Data-Intensive Science: Problems and Development of the Fourth Paradigm

  2024cites this paper
• Machine learning driven advancements in catalysis for predicting hydrogen evolution reaction activity

  2024cites this paper
• Discovery of novel materials through machine learning

  2024cites this paper
• High-throughput calculations and machine learning modeling of 17O NMR in non-magnetic oxides.

  2024cites this paper
• High- Tc superconductor candidates proposed by machine learning

  2024cites this paper
• High-throughput thiophene adsorption calculations on bimetallic surfaces

  2024cites this paper
• Multi-scale computational study of high-temperature corrosion and the design of corrosion-resistant alloys

  2024cites this paper
• Rapid estimation of γ' solvus temperature for composition design of Ni-based superalloy via physics-informed generative artificial intelligence

  2024cites this paper
• Interpretably learning the critical temperature of superconductors: Electron concentration and feature dimensionality reduction

  2024cites this paper
• High-Quality Data Enabling Universality of Band Gap Descriptor and Discovery of Photovoltaic Perovskites.

  2024cites this paper
• Hybrid Quantum Graph Neural Network for Molecular Property Prediction

  2024cites this paper
• Synthesis, properties, applications, 3D printing and machine learning of graphene quantum dots in polymer nanocomposites

  2024cites this paper
• Enhancing interpretability in the exploration of high-energy conversion efficiency in CsSnBr3−xIx configurations using crystal graph convolutional neural networks and adversarial example methods

  2024cites this paper
• A Compute-in-Memory Annealing Processor With Interaction Coefficient Reuse and Sparse Energy Computation for Solving Combinatorial Optimization Problems

  2024cites this paper
• LCAONet: Message-passing with physically optimized atomic basis functions

  2024cites this paper
• Machine learning guided rapid discovery of narrow-bandgap inorganic halide perovskite materials

  2024cites this paper
• Validation Workflow for Machine Learning Interatomic Potentials for Complex Ceramics

  2024cites this paper
• Advances in materials informatics: a review

  2024cites this paper
• Element-configuration dependent first-principles machine learning studies of multiple alloying effects on the structure stability of Co3(Al, W)

  2024cites this paper
• Causal emergent principles and relations for mechanical properties of covalent and ionic crystals

  2024cites this paper
• Combining Transfer Learning and Representation Learning to Improve Predictive Analytics on Small Materials Data

  2024cites this paper
• Scrutinizing Big Data with Commutative and Non-commutative Algebra

  2024cites this paper
• Machine learning-assisted design of high-performance perovskite photodetectors: a review

  2024cites this paper
• Machine Learning-Assisted Hartree–Fock Approach for Energy Level Calculations in the Neutral Ytterbium Atom

  2024cites this paper
• Automatic feature engineering for catalyst design using small data without prior knowledge of target catalysis

  2024cites this paper
• Neural network for predicting Peierls barrier spectrum and its influence on dislocation motion

  2024cites this paper
• When Machine Learning Meets 2D Materials: A Review

  2024cites this paper
• Kolmogorov-Arnold Network Made Learning Physics Laws Simple.

  2024cites this paper
• Hierarchical Gaussian process-based Bayesian optimization for materials discovery in high entropy alloy spaces

  2024cites this paper
• Accessing the usefulness of atomic adsorption configurations in predicting the adsorption properties of molecules with machine learning.

  2024cites this paper
• Coarsening of chiral domains in itinerant electron magnets: A machine learning force field approach

  2024cites this paper
• Machine Learning Aided Design and Optimization of Thermal Metamaterials

  2024cites this paper
• Accelerating the Development of Thin Film Photovoltaic Technologies: An Artificial Intelligence Assisted Methodology Using Spectroscopic and Optoelectronic Techniques

  2024cites this paper
• A novel design for refractory complex concentrated alloys based on multi-objective bi-level optimization

  2024cites this paper
• The bottleneck and innovation key of MEMS-based metal oxide semiconductors gas sensor for petrochemical industry

  2024cites this paper
• Machine learning prediction of materials properties from chemical composition: Status and prospects

  2024cites this paper
• Machine learning-assisted dual-atom sites design with interpretable descriptors unifying electrocatalytic reactions

  2024cites this paper
• Merits and Demerits of Machine Learning of Ferroelectric, Flexoelectric, and Electrolytic Properties of Ceramic Materials

  2024cites this paper
• Rise of machine learning potentials in heterogeneous catalysis: Developments, applications, and prospects

  2024cites this paper
• Predicting Model for Device Density of States of Quantum-Confined SiC Nanotube with Magnetic Dopant: An Integrated Approach Utilizing Machine Learning and Density Functional Theory

  2024cites this paper
• Ionic species representations for materials informatics

  2024cites this paper