Designing High-T_c Bulk and Two-Dimensional (2D) Superconductors with BCS-Inspired Screening, Density Functional Theory, Deep-Learning and Experiments

High-throughput density functional theory (DFT) calculations allow for a systematic search for conventional Bardeen–Cooper–Schrieffer (BCS) superconductors. With the recent interest in bulk and two-dimensional (2D) superconductors, we develop a multi-step workflow for the discovery of conventional superconductors. After screening over 55,000 bulk and 1,000 2D materials in the JARVIS-DFT database, we perform electron-phonon coupling (EPC) calculations and use the McMillan-Allen-Dynes formula to calculate the superconducting transition temperature (T_c) for 1,736 bulk and 172 2D materials. From this, we identify 112 bulk and 33 monolayer structures that are dynamically stable with superconducting transition temperatures above 5 K, including bulk materials such as VTe, KB₆, Ru₃NbC, V₃Pt, ScN, LaN₂, RuO₂, and TaC and 2D materials such as W₂N₃, NbO₂, ZrBrO, TiClO, NaSn₂S₄, Mg₂B₄C₂ and the previously undiscovered Mg₂B₄N₂, which has a T_c of 22.51 K. Additionally, we demonstrate that deep-learning models can predict superconductor properties, including the Eliashberg function, thousands of times faster than direct first principles computations for bulk materials. Finally, we performed experiments to determine the T_c of selected layered superconductors (2H-NbSe₂, 2H-NbS₂, ZrSiS, FeSe) and discuss the measured results within the context of our DFT computed results. We aim that the outcome of this workflow can guide future computational and experimental studies of new and emerging superconductors by providing a roadmap of high-throughput DFT data.