Sampling the Whole Materials Space for Conventional Superconducting Materials

TL;DR

This study uses machine learning to efficiently predict superconducting transition temperatures for a large set of materials, identifying promising candidates including LiMoN2 with high Tc.

Contribution

It introduces a high-throughput workflow combining machine learning and density-functional theory to discover new superconductors from a vast materials space.

Findings

Identified 545 compounds with Tc > 10 K.

Predicted LiMoN2 to have Tc > 38 K, matching experimental synthesis.

Evaluated ~200,000 metallic compounds for superconductivity.

Abstract

We perform a large scale study of conventional superconducting materials using a machine-learning accelerated high-throughput workflow. We start by creating a comprehensive dataset of around 7000 electron-phonon calculations performed with reasonable convergence parameters. This dataset is then used to train a robust machine learning model capable of predicting the electron-phonon and superconducting properties based on structural, compositional, and electronic ground-state properties. Using this machine, we evaluate the transition temperature (Tc ) of approximately 200000 metallic compounds, all of which on the convex hull of thermodynamic stability (or close to it) to maximize the probability of synthesizability. Compounds predicted to have Tc values exceeding 5 K are further validated using density-functional perturbation theory. As a result, we identify 545 compounds with Tc values surpassing 10 K, encompassing a variety of crystal structures and chemical compositions. This work is complemented with a detailed examination of several interesting materials, including nitrides, hydrides, and intermetallic compounds. Particularly noteworthy is LiMoN2 , which we predict to be superconducting in the stoichiometric trigonal phase, with a Tc exceeding 38 K. LiMoN2 has been previously synthesized in this phase, further heightening its potential for practical applications.