Scholarlink

<p>Covalent organic frameworks (COFs) are promising photocatalysts for hydrogen peroxide (H<sub>2</sub>O<sub>2</sub>) production, yet their rational design remains challenging. Although machine learning has advanced the prediction of properties of porous materials, its application to COF-based photocatalysis faces two major challenges: the representation of multilevel structural features and the limited availability of training datasets. Here we present a comprehensive computational framework, termed ‘information co-evolution’, that accelerates the discovery of efficient COF structures for H<sub>2</sub>O<sub>2</sub> photosynthesis. This framework integrates two pathways: to mitigate data limitations, we introduce data augmentation techniques and ensemble modelling; concurrently, to address the structural encoding challenge, we introduce a cross-level feature fusion strategy that integrates these fragment descriptors with mechanism-driven physical descriptors. These strategies collectively reduced the validation root mean square error from 4.70 to 3.31. Among over 10,000 candidates, our framework can successfully identify high-performance COFs for H<sub>2</sub>O<sub>2</sub> photosynthesis, for example, COF-343 achieves a H<sub>2</sub>O<sub>2</sub> photosynthetic rate of 12,978.7 μmol h<sup>−1</sup> g<sup>−1</sup>. The model interpretation further unveiled critical structural motifs, offering information for the rational design of COF photocatalysts beyond traditional trial-and-error methods.</p><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

Machine learning-accelerated discovery of covalent organic frameworks for hydrogen peroxide photosynthesis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月25日

查看全文
  • Xiaoke Jia,
  • Li Chen,
  • Kun Xiong,
  • Yujie Wang,
  • Linjie Zhou,
  • Xiaohui Xu,
  • Shuang Li,
  • Mao Wang,
  • Arne Thomas,
  • Chong Cheng

摘要

Covalent organic frameworks (COFs) are promising photocatalysts for hydrogen peroxide (H2O2) production, yet their rational design remains challenging. Although machine learning has advanced the prediction of properties of porous materials, its application to COF-based photocatalysis faces two major challenges: the representation of multilevel structural features and the limited availability of training datasets. Here we present a comprehensive computational framework, termed ‘information co-evolution’, that accelerates the discovery of efficient COF structures for H2O2 photosynthesis. This framework integrates two pathways: to mitigate data limitations, we introduce data augmentation techniques and ensemble modelling; concurrently, to address the structural encoding challenge, we introduce a cross-level feature fusion strategy that integrates these fragment descriptors with mechanism-driven physical descriptors. These strategies collectively reduced the validation root mean square error from 4.70 to 3.31. Among over 10,000 candidates, our framework can successfully identify high-performance COFs for H2O2 photosynthesis, for example, COF-343 achieves a H2O2 photosynthetic rate of 12,978.7 μmol h−1 g−1. The model interpretation further unveiled critical structural motifs, offering information for the rational design of COF photocatalysts beyond traditional trial-and-error methods.