Magnesium boride, MgB₂, has attracted much attention since the discovery of its superconductivity in 2001. The absence of weak-links in grain boundaries, less prominent anisotropy, rather simple powder-in-tube wire fabrication techniques, and much lower prices of raw materials, have made this new superconducting material a promising candidate for high-field magnet applications. Furthermore, it has been demonstrated that various methods, such as chemical doping, irradiations, and different processing parameters, can lead to lattice disorders in the materials and thus alter physical properties. Empirical results have shown that changes in lattice parameters through various methods correlate with changes in T_c but correlations are merely general tendencies and obviously not universal. In this work, the Gaussian process regression model is developed to predict critical temperature based on lattice parameters among disordered MgB₂ in various materials systems. This modeling approach demonstrates a high degree of accuracy and stability, contributing to efficient and low-cost predictions of T_c and understandings of disorders and superconductivity in MgB₂ superconductors.

自从2001年发现其超导电性以来，硼化镁MgB ₂就引起了人们的广泛关注。晶界中没有弱连接，各向异性不那么明显，管内粉末制造工艺相当简单，并且生坯价格低得多这种材料已经使这种新的超导材料成为高磁场磁体应用的有希望的候选者。此外，已经证明各种方法，例如化学掺杂，辐照和不同的加工参数，可导致材料中的晶格紊乱并因此改变物理性质。实证结果表明，通过各种方法改变晶格参数与T _c的变化相关。但是关联仅仅是一般趋势，显然不是普遍的。在这项工作中，开发了高斯过程回归模型以基于各种材料系统中无序MgB ₂之间的晶格参数预测临界温度。这种建模方法证明了高度的准确性和稳定性，有助于对T _c进行高效且低成本的预测，并有助于理解MgB ₂超导体的无序性和超导电性。