Scholarlink

<p>Data-driven machine learning (ML) has demonstrated tremendous potential in material property predictions. However, the scarcity of materials data with costly property labels in the vast chemical space presents a significant challenge for ML in efficiently predicting properties and uncovering structure-property relationships. Here, we propose a novel hierarchy-boosted funnel learning (HiBoFL) framework, which is successfully applied to identify semiconductors with ultralow lattice thermal conductivity (<i>κ</i><sub>L</sub>). By training on only a few hundred materials targeted by unsupervised learning from a pool of hundreds of thousands, we achieve efficient and interpretable supervised predictions of ultralow <i>κ</i><sub>L</sub>, thereby circumventing large-scale brute-force ab initio calculations without clear objectives. As a result, we provide a list of candidates with ultralow <i>κ</i><sub>L</sub> for potential thermoelectric applications and discover a new factor that significantly influences structural anharmonicity. This HiBoFL framework offers a novel practical pathway for accelerating the discovery of functional materials.</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

Hierarchy-boosted funnel learning for identifying semiconductors with ultralow lattice thermal conductivity

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年4月22日

查看全文
  • Mengfan Wu,
  • Shenshen Yan,
  • Jie Ren

摘要

Data-driven machine learning (ML) has demonstrated tremendous potential in material property predictions. However, the scarcity of materials data with costly property labels in the vast chemical space presents a significant challenge for ML in efficiently predicting properties and uncovering structure-property relationships. Here, we propose a novel hierarchy-boosted funnel learning (HiBoFL) framework, which is successfully applied to identify semiconductors with ultralow lattice thermal conductivity (κL). By training on only a few hundred materials targeted by unsupervised learning from a pool of hundreds of thousands, we achieve efficient and interpretable supervised predictions of ultralow κL, thereby circumventing large-scale brute-force ab initio calculations without clear objectives. As a result, we provide a list of candidates with ultralow κL for potential thermoelectric applications and discover a new factor that significantly influences structural anharmonicity. This HiBoFL framework offers a novel practical pathway for accelerating the discovery of functional materials.