High-temperature superconductors’ critical temperature has been demonstrated to be correlated with the interlayer Coulombic coupling. In order to improve prediction accuracy and stabilities from simple algebraic expressions, we propose the Gaussian process regression model for predictions of critical temperature of high-temperature superconductors from structural and electronic parameters. The model could be applied to a wide variety of superconductor families, including cuprate, ruthenate, rutheno-cuprate, iron-pnictide, iron-chalcogenide, organic, and intercalated group-V-metal nitride-halides. It can be employed as an efficient and low-cost technique for predictions of critical temperature.

高温超导体的临界温度已被证明与层间库仑耦合有关。为了提高简单代数表达式的预测精度和稳定性，我们提出了高斯过程回归模型，用于从结构和电子参数预测高温超导体的临界温度。该模型可应用于多种超导体家族，包括铜酸盐、钌酸盐、钌-铜酸盐、铁-磷化物、铁-硫属化物、有机和插层-V族金属氮化物-卤化物。它可以用作预测临界温度的有效且低成本的技术。