School of Materials Science and Engineering, Harbin Institute of Technology, Shenzhen 518055, P. R. China
Blockchain Development and Research Institute, Harbin Institute of Technology, Shenzhen 518055, P. R. China
Department of Materials Science and Engineering & Department of Physics, Southern University of Science and Technology, Shenzhen 518055, P. R. China
State Key Laboratory of Advanced Welding and Joining, Harbin Institute of Technology, Harbin 150001, P. R. China
Superconductivity allows electric conductance with no energy losses when the ambient temperature drops below a critical value (
T
c
). Currently, the machine learning (ML)-based prediction of potential superconductors has been limited to chemical formulas without explicit treatment of material structures. Herein, we implement an efficient structural descriptor, the smooth overlap of atomic position (SOAP), into the ML models to predict the
T
c
values with explicit atomic structural information. Using a data set containing 5713 compounds, our ML models with the SOAP descriptor achieved a 92.9% prediction accuracy of coefficient of determination (
R
2
) score via rigorous multialgorithm cross-verification procedures, exceeding the 86.3% accuracy record without atomic structure information. Several new high-temperature superconductors with
T
c
values over 90 K were predicted using the SOAP-assisted ML model. This study provides insights into the structure–property relationship of high-temperature superconductors.
中文翻译：
当环境温度降至临界值(
Tc
)以下时，超导性允许电导没有能量损失。目前，基于机器学习 (ML) 的潜在超导体预测仅限于化学公式，而没有明确处理材料结构。在这里，我们在 ML 模型中实现了一个有效的结构描述符，即原子位置的平滑重叠 (SOAP)，以使用明确的原子结构信息来预测
T
c
值。使用包含 5713 种化合物的数据集，我们使用 SOAP 描述符的 ML 模型实现了 92.9% 的决定系数预测准确度 (
R
2
) 通过严格的多算法交叉验证程序得分，超过了没有原子结构信息的 86.3% 准确度记录。使用 SOAP 辅助 ML 模型预测了几种
T
c
值超过 90 K 的新型高温超导体。这项研究为高温超导体的结构-性能关系提供了见解。
