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. Next, we perform electron-phonon coupling calculations for 1058 of them to establish a large and systematic database of BCS superconducting properties. Using the McMillan-Allen-Dynes formula, we identify 105 dynamically stable materials with transition temperatures, T_C ≥ 5 K. Additionally, we analyze trends in our dataset and individual materials including MoN, VC, VTe, KB₆, Ru₃NbC, V₃Pt, ScN, LaN₂, RuO₂, and TaC. We demonstrate that deep-learning(DL) models can predict superconductor properties faster than direct first-principles computations. Notably, we find that by predicting the Eliashberg function as an intermediate quantity, we can improve model performance versus a direct DL prediction of T_C. We apply the trained models on the crystallographic open database and pre-screen candidates for further DFT calculations.

我们开发了一个用于发现传统超导体的多步骤工作流程，从受 Bardeen-Cooper-Schrieffer 启发对具有高德拜温度和电子态密度的 1736 材料进行预筛选开始。接下来，我们对其中的1058个进行了电子-声子耦合计算，建立了一个庞大而系统的BCS超导特性数据库。使用 McMillan-Allen-Dynes 公式，我们确定了 105 种具有转变温度T _C  ≥ 5 K 的动态稳定材料。此外，我们分析了数据集和单个材料的趋势，包括 MoN、VC、VTe、KB ₆、Ru ₃ NbC、 V ₃ Pt、ScN、LaN ₂、RuO ₂, 和 TaC。我们证明深度学习 (DL) 模型可以比直接第一性原理计算更快地预测超导体特性。值得注意的是，我们发现通过将 Eliashberg 函数预测为中间量，我们可以提高模型性能，而不是直接 DL 预测T _C。我们将经过训练的模型应用于晶体学开放数据库，并预筛选候选人以进行进一步的 DFT 计算。