Scholarlink

<p>Machine-learning models for high-entropy alloy (HEA) phase prediction often perform well under random splits yet degrade on chemically novel systems. We introduce Combinatorial Element Exclusion, which excludes from training all alloys containing a chosen element or elements and evaluates prediction on those excluded alloys. Random holdout yields accuracies of ≈0.80–0.83, but exclusion lowers empirical-descriptor and elemental-vector models by 30–50 percentage points, to Matthews correlation coefficients (MCC) of ≈0.30–0.36. In contrast, the best first-principles setting reaches ≈0.79 accuracy and a MCC of ≈0.57. Cross-encoding first-principles data into HEA parameters further drops accuracy to ≈0.53–0.55, evidencing descriptor-induced information loss.</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

Chemical-transferability limits of HEA phase selection: Element-exclusion validation and descriptor-physics effects

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月4日

查看全文
  • G. W. Strzelecki,
  • K. Nowakowska-Langier,
  • P. Czuma,
  • K. Zdunek

摘要

Machine-learning models for high-entropy alloy (HEA) phase prediction often perform well under random splits yet degrade on chemically novel systems. We introduce Combinatorial Element Exclusion, which excludes from training all alloys containing a chosen element or elements and evaluates prediction on those excluded alloys. Random holdout yields accuracies of ≈0.80–0.83, but exclusion lowers empirical-descriptor and elemental-vector models by 30–50 percentage points, to Matthews correlation coefficients (MCC) of ≈0.30–0.36. In contrast, the best first-principles setting reaches ≈0.79 accuracy and a MCC of ≈0.57. Cross-encoding first-principles data into HEA parameters further drops accuracy to ≈0.53–0.55, evidencing descriptor-induced information loss.

Graphical abstract