SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates

Abstract

The lack of reliable methods for identifying descriptors - the sets of parameters capturing the underlying mechanisms of a materials property - is one of the key factors hindering efficient materials development. Here, we propose a systematic approach for discovering descriptors for materials properties, within the framework of compressed-sensing based dimensionality reduction. SISSO (sure independence screening and sparsifying operator) tackles immense and correlated features spaces, and converges to the optimal solution from a combination of features relevant to the materials' property of interest. In addition, SISSO gives stable results also with small training sets. The methodology is benchmarked with the quantitative prediction of the ground-state enthalpies of octet binary materials (using ab initio data) and applied to the showcase example of predicting the metal/insulator classification of binaries (with experimental data). Accurate, predictive models are found in both cases. For the metal-insulator classification model, the predictive capability are tested beyond the training data: It rediscovers the available pressure-induced insulator->metal transitions and it allows for the prediction of yet unknown transition candidates, ripe for experimental validation. As a step forward with respect to previous model-identification methods, SISSO can become an effective tool for automatic materials development.

11 pages, 5 figures, in press in Phys. Rev. Materials

References in corpus (9)

• Sparsity and Incoherence in Compressive Sampling
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• Big Data of Materials Science - Critical Role of the Descriptor
• Machine Learning Unifies the Modelling of Materials and Molecules
• Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
• Compressive sensing as a new paradigm for model building
• Spectral descriptors for bulk metallic glasses based on the thermodynamics of competing crystalline phases
• Learning physical descriptors for materials science by compressed sensing
• Uncovering structure-property relationships of materials by subgroup discovery

Cited by in corpus (67)

• New Tolerance Factor to Predict the Stability of Perovskite Oxides and Halides
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Data-driven materials science: status, challenges and perspectives
• Big-Data Science in Porous Materials: Materials Genomics and Machine Learning
• Physics-inspired structural representations for molecules and materials
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• Interpretable and Explainable Machine Learning for Materials Science and Chemistry
• Symbolic Regression in Materials Science
• Beyond scaling relations for the description of catalytic materials
• Single-Atom Alloy Catalysts Designed by First-Principles Calculations and Artificial Intelligence
• Unsupervised machine learning in atomistic simulations, between predictions and understanding
• Towards Stacking Fault Energy Engineering in FCC High Entropy Alloys
• A critical examination of robustness and generalizability of machine learning prediction of materials properties
• Synthetic accessibility and stability rules of NASICONs
• A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
• Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws
• MODNet -- accurate and interpretable property predictions for limited materials datasets by feature selection and joint-learning
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Efficient machine-learning model for fast assessment of elastic properties of high-entropy alloys
• Lattice Thermal Conductivity Prediction using Symbolic Regression and Machine Learning
• Machine learning-assisted design of material properties
• Hypothesis Learning in Automated Experiment: Application to Combinatorial Materials Libraries
• AI-driven inverse design of materials: Past, present and future
• Machine Learning Study of the Magnetic Ordering in 2D Materials
• Distilling Accurate Descriptors from Multi-Source Experimental Data for Discovering Highly Active Perovskite OER Catalysts
• Functional Form of the Superconducting Critical Temperature from Machine Learning
• Machine learning for materials discovery: two-dimensional topological insulators
• NOMAD 2018 Kaggle Competition: Solving Materials Science Challenges Through Crowd Sourcing
• Predicting binding motifs of complex adsorbates using machine learning with a physics-inspired graph representation
• Bayesian optimization of chemical composition: a comprehensive framework and its application to $R$Fe${}_{12}$-type magnet compounds
• Evolving symbolic density functionals
• One-Component Order Parameter in URu${}_2$Si${}_2$ Uncovered by Resonant Ultrasound Spectroscopy and Machine Learning
• Artificial Intelligence for High-Throughput Discovery of Topological Insulators: the Example of Alloyed Tetradymites
• Sensitivity and Dimensionality of Atomic Environment Representations used for Machine Learning Interatomic Potentials
• Insights into cation ordering of double perovskite oxides from machine learning and causal relations
• Machine-learning enabled thermodynamic model for the design of new rare-earth compounds
• Hierarchical symbolic regression for identifying key physical parameters correlated with bulk properties of perovskites
• Navigating the Evolution of Two-dimensional Carbon Nitride Research: Integrating Machine Learning into Conventional Approaches
• Formal structure of periodic system of elements
• Analogical discovery of disordered perovskite oxides by crystal structure information hidden in unsupervised material fingerprints
• Compact atomic descriptors enable accurate predictions via linear models
• Machine Learning-Guided Screening of Advantageous Solvents for Solid Polymer Electrolytes in Lithium Metal Batteries
• Voting Data-Driven Regression Learning for Discovery of Functional Materials and Applications to Two-Dimensional Ferroelectric Materials
• Data-driven equation for drug-membrane permeability across drugs and membranes
• Iterative Symbolic Regression for Learning Transport Equations
• Discovering dynamic laws from observations: the case of self-propelled, interacting colloids
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Understanding and predicting trends in adsorption energetics on monolayer transition metal dichalcogenides
• Machine-learning correction to density-functional crystal structure optimization
• Machine learning of microscopic ingredients for graphene oxide/cellulose interaction
• High-throughput characterization of transition metal dichalcogenide alloys: Thermodynamic stability and electronic band alignment
• Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space
• Advancing descriptor search in materials science: feature engineering and selection strategies
• Optical materials discovery and design with federated databases and machine learning
• Electronic Descriptors for Supervised Spectroscopic Predictions
• A transferable prediction model of molecular adsorption on metals based on adsorbate and substrate properties
• Molecular Bond Engineering and Feature Learning for the Design of Hybrid Organic-Inorganic Perovskites Solar Cells with Strong Non-Covalent Halogen-Cation Interactions
• Superconductor discovery in the emerging paradigm of Materials Informatics
• Can we predict interface dipoles based on molecular properties?
• Soliquidy: a descriptor for atomic geometrical confusion
• Interpretable machine learned predictions of adsorption energies at the metal--oxide interface
• Operator-induced structural variable selection for identifying materials genes
• Accelerating the Discovery of Materials with Expected Thermal Conductivity via a Synergistic Strategy of DFT and Interpretable Deep Learning
• A critical assessment of bonding descriptors for predicting materials properties
• Interfacial Magnetic Anisotropy of Iron-Adsorbed Ferroelectric Perovskites: First-Principles and Machine Learning Study
• TCMI: a non-parametric mutual-dependence estimator for multivariate continuous distributions
• Electron correlation in semiconductors and insulators via symbolic regression