Machine learning modeling of superconducting critical temperature

Abstract

Superconductivity has been the focus of enormous research effort since its discovery more than a century ago. Yet, some features of this unique phenomenon remain poorly understood; prime among these is the connection between superconductivity and chemical/structural properties of materials. To bridge the gap, several machine learning schemes are developed herein to model the critical temperatures ($T_{\mathrm{c}}$) of the 12,000+ known superconductors available via the SuperCon database. Materials are first divided into two classes based on their $T_{\mathrm{c}}$ values, above and below 10 K, and a classification model predicting this label is trained. The model uses coarse-grained features based only on the chemical compositions. It shows strong predictive power, with out-of-sample accuracy of about 92%. Separate regression models are developed to predict the values of $T_{\mathrm{c}}$ for cuprate, iron-based, and "low-$T_{\mathrm{c}}$" compounds. These models also demonstrate good performance, with learned predictors offering potential insights into the mechanisms behind superconductivity in different families of materials. To improve the accuracy and interpretability of these models, new features are incorporated using materials data from the AFLOW Online Repositories. Finally, the classification and regression models are combined into a single integrated pipeline and employed to search the entire Inorganic Crystallographic Structure Database (ICSD) for potential new superconductors. We identify more than 30 non-cuprate and non-iron-based oxides as candidate materials.

arXiv comment17 pages, 7 figures

References in corpus (22)

• SMOTE: Synthetic Minority Over-sampling Technique
• A General-Purpose Machine Learning Framework for Predicting Properties of Inorganic Materials
• High-throughput electronic band structure calculations: challenges and tools
• AFLOW: An automatic framework for high-throughput materials discovery
• High-temperature superconductivity in iron-based materials
• Universal Fragment Descriptors for Predicting Electronic Properties of Inorganic Crystals
• Superfluidity in topologically nontrivial flat bands
• High-temperature surface superconductivity in topological flat-band systems
• Exploration of new superconductors and functional materials and fabrication of superconducting tapes and wires of iron pnictides
• Machine learning with systematic density-functional theory calculations: Application to melting temperatures of single and binary component solids
• High-Throughput Computational Screening of thermal conductivity, Debye temperature and Grüneisen parameter using a quasi-harmonic Debye Model
• Materials Cartography: Representing and Mining Material Space Using Structural and Electronic Fingerprints
• A RESTful API for exchanging Materials Data in the AFLOWLIB.org consortium
• High-Dimensional Materials and Process Optimization using Data-driven Experimental Design with Well-Calibrated Uncertainty Estimates
• Hole-Doped Cuprate High Temperature Superconductors
• Spectral descriptors for bulk metallic glasses based on the thermodynamics of competing crystalline phases
• Materials Design for New Superconductors
• Superconducting materials classes: introduction and overview
• Combining the AFLOW GIBBS and Elastic Libraries for efficiently and robustly screening thermo-mechanical properties of solids
• Structure maps for hcp metals from first principles calculations
• Unconventional Superconductivity in electron-doped layered metal nitride halides $M$N$X$ ($M$ = Ti, Zr, Hf; $X$ = Cl, Br, I)
• Deep data mining in a real space: Separation of intertwined electronic responses in a lightly-doped BaFe2As2

Cited by in corpus (89)

• Recent Advances and Applications of Deep Learning Methods in Materials Science
• Data-driven materials science: status, challenges and perspectives
• A Perspective on Conventional High-Temperature Superconductors at High Pressure: Methods and Materials
• Opportunities and Challenges for Machine Learning in Materials Science
• Interpretable and Explainable Machine Learning for Materials Science and Chemistry
• Towards high-throughput superconductor discovery via machine learning
• The 2021 Quantum Materials Roadmap
• Machine Learning in Electronic Quantum Matter Imaging Experiments
• Machine Learning Guided Discovery of Gigantic Magnetocaloric Effect in HoB${}_2$ Near Hydrogen Liquefaction Temperature
• Strong correlation between bonding network and critical temperature in hydrogen-based superconductors
• Machine Learning on Neutron and X-Ray Scattering
• Neural Network-based Classification of Crystal Symmetries from X-Ray Diffraction Patterns
• Deep Learning Model for Finding New Superconductors
• Advances of Machine Learning in Materials Science: Ideas and Techniques
• Predicting the Curie temperature of ferromagnets using machine learning
• Room Temperature Superconductivity: the Roles of Theory and Materials Design
• The Materials Simulation Toolkit for Machine Learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research
• Designing High-Tc Superconductors with BCS-inspired Screening, Density Functional Theory and Deep-learning
• Band gap prediction for large organic crystal structures with machine learning
• Predicting new superconductors and their critical temperatures using unsupervised machine learning
• AI-driven inverse design of materials: Past, present and future
• Functional Form of the Superconducting Critical Temperature from Machine Learning
• Direct prediction of phonon density of states with Euclidean neural networks
• aflow.org: A Web Ecosystem of Databases, Software and Tools
• Deformation potential extraction and computationally efficient mobility calculations in silicon from first principles
• Materials informatics based on evolutionary algorithms: Application to search for superconducting hydrogen compounds
• Detection of Topological Materials with Machine Learning
• Inverse Design of Next-generation Superconductors Using Data-driven Deep Generative Models
• Developments and applications of the OPTIMADE API for materials discovery, design, and data exchange
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• CRYSPNet: Crystal Structure Predictions via Neural Network
• Machine-Learning-Guided Prediction Models of Critical Temperature of Cuprates
• Piezoelectric modulus prediction using machine learning and graph neural networks
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• Machine Learning based prediction of noncentrosymmetric crystal materials
• Robust model benchmarking and bias-imbalance in data-driven materials science: a case study on MODNet
• Compressing deep neural networks by matrix product operators
• Recent advances in high-throughput superconductivity research
• Efficient Estimation of Material Property Curves and Surfaces via Active Learning
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Understanding Magnetic Properties of Actinide-Based Compounds from Machine Learning
• Predicting Superconducting Transition Temperature through Advanced Machine Learning and Innovative Feature Engineering
• Automatic extraction of materials and properties from superconductors scientific literature
• Hardness and fracture toughness models by symbolic regression
• Ternary mixed-anion semiconductors with tunable band gaps from machine-learning and crystal structure prediction
• InvDesFlow: An AI-driven materials inverse design workflow to explore possible high-temperature superconductors
• Data-driven Design of High Pressure Hydride Superconductors using DFT and Deep Learning
• Deep learning of spectra: Predicting the dielectric function of semiconductors
• Prediction of Large Magnetic Moment Materials With Graph Neural Networks and Random Forests
• Data-driven analysis of the electronic-structure factors controlling the work functions of perovskite oxides
• Machine-learning correction to density-functional crystal structure optimization
• XtalOpt Version 13: Multi-Objective Evolutionary Search for Novel Functional Materials
• Accelerating superconductor discovery through tempered deep learning of the electron-phonon spectral function
• Pressure-Induced Superconductivity in Layered Transition-metal Chalcogenides (Zr,Hf)GeTe${}_4$ Explored by Data-driven Approach
• Deep Learning Based Superconductivity: Prediction and Experimental Tests
• Charting the landscape of Bardeen-Cooper-Schrieffer superconductors in experimentally known compounds
• Classification-based detection and quantification of cross-domain data bias in materials discovery
• Prediction of an unusual trigonal phase of superconducting LaH${}_{10}$ stable from 250 to 425 GPa pressure
• Exceeding the Chandrasekhar-Clogston limit in flat-band superconductors: A multiband strong-coupling approach
• Data-driven determination of the spin Hamiltonian parameters and their uncertainties: The case of the zigzag-chain compound KCu${}_4$P${}_3$O${}_{12}$
• Leveraging Composition-Based Material Descriptors for Machine Learning Optimization
• Many-body perturbation theory vs. density functional theory: A systematic benchmark for band gaps of solids
• Semi-automatic staging area for high-quality structured data extraction from scientific literature
• Superconductor discovery in the emerging paradigm of Materials Informatics
• 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
• Discovery of sustainable energy materials via the machine-learned material space
• Classification of magnetic order from electronic structure by using machine learning
• Accelerating the Search for Superconductors Using Machine Learning
• Machine-learning Guided Search for Phonon-mediated Superconductivity in Boron and Carbon Compounds
• Simple predictors of $T_c$ in superconducting cuprates and the role of interactions between effective Wannier orbitals in the $d-p$ 3-band model
• MC3D: The Materials Cloud computational database of experimentally known stoichiometric inorganics
• Exploring explicit coarse-grained structure in artificial neural networks
• Developing a Complete AI-Accelerated Workflow for Superconductor Discovery
• XtalOpt Version 14: Variable-Composition Crystal Structure Search for Functional Materials Through Pareto Optimization
• Perturbing finite temperature multicomponent DFT 1D Kohn-Sham systems: Peierls Gap & Kohn Anomaly
• Structure-Driven Prediction of Magnetic Order in Uranium Compounds
• Bridging microscopy with molecular dynamics and quantum simulations: An AtomAI based pipeline
• Elemental Reactivity Maps for Materials Discovery
• Deep-Learning Estimation of Band Gap with the Reading-Periodic-Table Method and Periodic Convolution Layer
• Optimization and benchmarking of the thermal cycling algorithm
• Tree Models Machine Learning to Identify Liquid Metal based Alloy Superconductor
• Generalized deformation potential and machine-learning approaches for electron-phonon coupling and thermoelectric transport in semiconductors
• Towards In Silico Mining for Superconductors -- Cutting the Gordian Knot
• Synergistic Fusion of Multi-Source Knowledge via Evidence Theory for High-Entropy Alloy Discovery
• Effects of Li Doping on Superconducting Properties of Citrate Gel Prepared Y1-xLixBa2Cu3O7-d Compound
• Composition-Based Machine Learning for Screening Superconducting Ternary Hydrides from a Curated Dataset
• Predicting parameters of a model cuprate superconductor using machine learning
• Accelerating Ensemble Error Bar Prediction with Single Models Fits