Scholarlink

<p>Machine learning is creating new opportunities in solving classical physics problems, particularly in calculating the Debye temperature. This paper explores machine learning regression models customized for various materials. Using Microsoft Azure’s machine learning services, we predict the Debye temperature for metals with face-centered cubic (f.c.c.) and hexagonal crystal structures. The study includes an analysis of feature importance, accuracy, and performance metrics, and validates the results against traditional methods for calculating the Debye temperature.</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

Prediction of Debye temperature by machine learning

  • 期刊论文

  • 发表日期：

    2026年2月24日

查看全文
  • Svitlana Ponomarova,
  • Oleksandr Ponomarov,
  • Yurii Koval

摘要

Machine learning is creating new opportunities in solving classical physics problems, particularly in calculating the Debye temperature. This paper explores machine learning regression models customized for various materials. Using Microsoft Azure’s machine learning services, we predict the Debye temperature for metals with face-centered cubic (f.c.c.) and hexagonal crystal structures. The study includes an analysis of feature importance, accuracy, and performance metrics, and validates the results against traditional methods for calculating the Debye temperature.

Graphical abstract