Scholarlink

<p>Superconductors, which are crucial for modern advanced technologies due to their zero-resistance properties, are limited by low critical temperature (<Emphasis Type="BoldItalic">T</Emphasis><sub><Emphasis Type="BoldItalic">c</Emphasis></sub>) and the difficulty of accurate prediction. This article makes the initial endeavor to apply machine learning to predict the <Emphasis Type="BoldItalic">T</Emphasis><sub><Emphasis Type="BoldItalic">c</Emphasis></sub> of liquid metal (LM) alloy superconductors. Leveraging the SuperCon dataset, which includes extensive superconductor property data, we developed a machine learning model to predict <i>T</i><sub><i>c</i></sub> under ambient pressure. After addressing data issues through preprocessing, we compared multiple models and found that the ExtraTrees model outperformed others with a coefficient of determination (<i>R</i><sup>2</sup>) of 0.9519 and a root mean square error (RMSE) of 6.2624&#xa0;K. This model is subsequently used to predict <Emphasis Type="BoldItalic">T</Emphasis><sub><Emphasis Type="BoldItalic">c</Emphasis></sub> for LM alloys, revealing In<sub>0.5</sub>Sn<sub>0.5</sub> as having the highest <Emphasis Type="BoldItalic">T</Emphasis><sub><Emphasis Type="BoldItalic">c</Emphasis></sub> at 7.01&#xa0;K. Furthermore, we extended the prediction to 2145 alloys binary and 45670 ternary alloys across 66 metal elements and promising results were achieved. This work demonstrates the advantages of tree-based models in predicting <Emphasis Type="BoldItalic">T</Emphasis><sub><Emphasis Type="BoldItalic">c</Emphasis></sub> and would help accelerate the discovery of high-performance LM alloy superconductors in the coming time.</p> Graphical abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Tree model machine learning to identify liquid metal-based alloy superconductor

  • 期刊论文

  • 发表日期：

    2025年7月10日

查看全文
  • Chen Hua,
  • Jing Liu

摘要

Superconductors, which are crucial for modern advanced technologies due to their zero-resistance properties, are limited by low critical temperature (Tc) and the difficulty of accurate prediction. This article makes the initial endeavor to apply machine learning to predict the Tc of liquid metal (LM) alloy superconductors. Leveraging the SuperCon dataset, which includes extensive superconductor property data, we developed a machine learning model to predict Tc under ambient pressure. After addressing data issues through preprocessing, we compared multiple models and found that the ExtraTrees model outperformed others with a coefficient of determination (R2) of 0.9519 and a root mean square error (RMSE) of 6.2624 K. This model is subsequently used to predict Tc for LM alloys, revealing In0.5Sn0.5 as having the highest Tc at 7.01 K. Furthermore, we extended the prediction to 2145 alloys binary and 45670 ternary alloys across 66 metal elements and promising results were achieved. This work demonstrates the advantages of tree-based models in predicting Tc and would help accelerate the discovery of high-performance LM alloy superconductors in the coming time.

Graphical abstract