Uncovering structure-property relationships of materials by subgroup discovery

Abstract

Subgroup discovery (SGD) is presented here as a data-mining approach to help find interpretable local patterns, correlations, and descriptors of a target property in materials-science data. Specifically, we will be concerned with data generated by density-functional theory calculations. At first, we demonstrate that SGD can identify physically meaningful models that classify the crystal structures of 82 octet binary semiconductors as either rocksalt or zincblende. SGD identifies an interpretable two-dimensional model derived from only the atomic radii of valence s and p orbitals that properly classifies the crystal structures for 79 of the 82 octet binary semiconductors. The SGD framework is subsequently applied to 24 400 configurations of neutral gas-phase gold clusters with 5 to 14 atoms to discern general patterns between geometrical and physicochemical properties. For example, SGD helps find that van der Waals interactions within gold clusters are linearly correlated with their radius of gyration and are weaker for planar clusters than for nonplanar clusters. Also, a descriptor that predicts a local linear correlation between the chemical hardness and the cluster isomer stability is found for the even-sized gold clusters.

References in corpus (10)

• Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Parallel Tempering: Theory, Applications, and New Perspectives
• Big Data of Materials Science - Critical Role of the Descriptor
• Big Data meets Quantum Chemistry Approximations: The $\Delta$-Machine Learning Approach
• Long-range correlation energy calculated from coupled atomic response functions
• Density functional study of Au${}_n$ (n=2-20) clusters: lowest-energy structures and electronic properties
• Predicting Crystal Structures with Data Mining of Quantum Calculations
• Compressive sensing as a new paradigm for model building
• Computational Design of Nanoclusters by Property-Based Genetic Algorithms: Tuning the Electronic Properties of (TiO${}_2$)${}_n$ Clusters

Cited by in corpus (16)

• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Data-driven materials science: status, challenges and perspectives
• Single-Atom Alloy Catalysts Designed by First-Principles Calculations and Artificial Intelligence
• Artifcial-intelligence-driven discovery of catalyst \textit{genes} with application to CO2 activation on semiconductor oxides
• Two-to-three dimensional transition in neutral gold clusters: the crucial role of van der Waals interactions and temperature
• Discovering Reliable Approximate Functional Dependencies
• Telling Cause from Effect using MDL-based Local and Global Regression
• Identifying Consistent Statements about Numerical Data with Dispersion-Corrected Subgroup Discovery
• Genarris: Random Generation of Molecular Crystal Structures and Fast Screening with a Harris Approximation
• Robust subgroup discovery
• Machine Learning and Materials Informatics: Recent Applications and Prospects
• Advancing descriptor search in materials science: feature engineering and selection strategies
• Electronic Descriptors for Supervised Spectroscopic Predictions
• Screening of potential double perovskite materials for photovoltaic applications using agglomerative hierarchical clustering
• Interpretable Summaries of Black Box Incident Triaging with Subgroup Discovery
• Efficiently Discovering Locally Exceptional yet Globally Representative Subgroups