Functional Form of the Superconducting Critical Temperature from Machine Learning

Abstract

Predicting the critical temperature $T_c$ of new superconductors is a notoriously difficult task, even for electron-phonon paired superconductors for which the theory is relatively well understood. Early attempts by McMillan and Allen and Dynes to improve on the weak-coupling BCS formula led to closed-form approximate relations between $T_c$ and various measures of the phonon spectrum and the electron-phonon interaction appearing in Eliashberg theory. Here we propose that these approaches can be improved with the use of machine learning algorithms. As an initial test, we train a model for identifying low-dimensional descriptors using the $T_c<10$ K data tested by Allen and Dynes, and show that a simple analytical expression thus obtained improves upon the Allen-Dynes fit. Furthermore, the prediction for the recently discovered high $T_c$ material H${}_3$S at high pressure is quite reasonable. Interestingly, $T_c$'s for more recently discovered superconducting systems with a more two-dimensional electron-phonon coupling, which do not follow Allen and Dynes' expression, also do not follow our analytic expression. Thus, this machine learning approach appears to be a powerful method for highlighting the need for a new descriptor beyond those used by Allen and Dynes to describe their set of isotropic electron-phonon coupled superconductors. We argue that this machine learning method, and its implied need for a descriptor characterizing Fermi surface properties, represents a promising new approach to superconductor materials discovery which may eventually replace the serendipitous discovery paradigm begun by Kamerlingh Onnes.

References in corpus (10)

• Conventional superconductivity at 203 K at high pressures
• Superconductivity at 250 K in lanthanum hydride under high pressures
• Evidence for superconductivity above 260 K in lanthanum superhydride at megabar pressures
• SISSO: a compressed-sensing method for identifying the best low-dimensional descriptor in an immensity of offered candidates
• Machine learning modeling of superconducting critical temperature
• Anisotropic Migdal-Eliashberg theory using Wannier functions
• Materials Design for New Superconductors
• Effect of Pressure on Superconducting Ca-intercalated Graphite CaC${}_6$
• Ab Initio Models of Dislocations
• Electron-phonon coupling and exchange-correlation effects in superconducting ${\mathrm{H}}_3\mathrm{S}$ under high pressure

Cited by in corpus (16)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Towards high-throughput superconductor discovery via machine learning
• Explicit Multi-element Extension of the Spectral Neighbor Analysis Potential for Chemically Complex Systems
• Machine-Learning-Guided Prediction Models of Critical Temperature of Cuprates
• High-Temperature Conventional Superconductivity in the Boron-Carbon system: Material Trends
• Hierarchical symbolic regression for identifying key physical parameters correlated with bulk properties of perovskites
• Machine-learning approach for discovery of conventional superconductors
• Linear Jacobi-Legendre expansion of the charge density for machine learning-accelerated electronic structure calculations
• Explainable Machine Learning for Breakdown Prediction in High Gradient RF Cavities
• A deep learning approach to search for superconductors from electronic bands
• Superconductor discovery in the emerging paradigm of Materials Informatics
• Symmetric Helmholtz Fermi-surface harmonics for an optimal representation of anisotropic quantities on the Fermi surface: Application to the electron-phonon problem
• Machine-learning Guided Search for Phonon-mediated Superconductivity in Boron and Carbon Compounds
• Developing a Complete AI-Accelerated Workflow for Superconductor Discovery
• Perturbing finite temperature multicomponent DFT 1D Kohn-Sham systems: Peierls Gap & Kohn Anomaly
• Composition-Based Machine Learning for Screening Superconducting Ternary Hydrides from a Curated Dataset