Abstract Scope |
Recent advances in first principles calculations and machine learning techniques allow for a systematic search for phonon-mediated superconductors. We develop a multi-step workflow for the discovery of conventional superconductors, starting with a Bardeen-Cooper-Schrieffer inspired pre-screening of 1736 materials with high Debye temperature and electronic density of states at the Fermi-level. Next, we perform electron-phonon coupling calculations for 1058 of them to establish a large and systematic database. Using the McMillan-Allen-Dynes formula, we identify 105 dynamically stable materials with transition temperatures, Tc > 5 K. In addition, we analyze trends in our dataset and individual materials including MoN, VC, VTe, KB6, Ru3NbC, V3Pt, ScN, LaN2, RuO2, and TaC. Finally, we demonstrate that deep-learning models can predict superconductor properties, including the Eliashberg function, thousands of times faster than direct first principles computations. We apply the trained model on the crystallographic open database to pre-screen candidates for further DFT calculations. |