通过机器学习设计新型超导材料

Discovering High-Temperature Conventional Superconductors via Machine Learning

在常压下寻找新型高温超导材料是物理和材料领域共同关注的热点问题。近年来,机器学习技术和大数据成功地解决了材料特性与复杂物理因素之间关系建模的难题,在新型材料的优化设计中获得了重要应用。然而利用机器学习在材料数据库中寻找常规Bardeen-Cooper-Schrieffer (BCS)超导材料,存在可用数据量少的问题,导致设计出的超导材料种类少,结构构型单一。结合BCS超导理论和半监督学习方法,发展了神经网络模型预测BCS超导体。通过充分利用材料数据库中大量的无标签数据,即未知超导温度但已知电子结构的晶体材料,使得训练出的分类模型准确性达72%。模型预测出数十种可常压下存在的新型BCS超导材料,其中B-C和B-C-N体系的超导温度最高可达约60 K,高于MgB_(2)的39 K超导纪录。

Searching for high-temperature ambient-pressure superconductors is a challenge in materials science.Machine learning has a promising application in materials discovery.A data-driven approach that overcomes low-data limitations by computationally inexpensive descriptors based on the Bardeen-Cooper-Schrieffer (BCS) theory and semi-supervised learning was proposed.The accuracy of the classification mode is 72%.This approach can screen over 10 000 binary and ternary BCS compounds in the Material Project database,thus identifying some promising superconductors at ambient pressure.The compounds in B-C and B-C-N systems have a maximum superconducting critical temperature (T_C) of 60 K,which is greater than that for MgB_2 (i.e.,T_C=39 K)