Scholarlink

<p>The rational design of organic functional devices relies on understanding structure-property-performance relationships through multi-scale characterization. However, traditional characterizations are costly and require multidisciplinary expertise. Here we present OCNet, a domain-knowledge-enhanced representation learning framework that, for the first time, enables unified virtual characterization from molecules to devices. Pre-trained on over ten million self-generated conjugated molecules and dimers, OCNet learns generalizable microscopic representations comparable to expert-crafted features. As a result, it surpasses state-of-the-art models by over 20% in predicting key computed and experimental molecular optoelectronic properties. OCNet further provides the first transferable model for predicting transfer integrals in thin films, enabling accurate mesoscale carrier mobility estimation via multiscale simulations. By integrating tight-binding-level electronic descriptors, OCNet achieves near real-time, accurate prediction of device power conversion efficiency. Together, OCNet offers a unified and scalable foundation for virtual characterization of organic materials across multiple scales, with broad applicability in photovoltaics, displays, and sensing.</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

Virtual characterization via knowledge-enhanced representation learning: from organic conjugated molecules to devices

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月16日

查看全文
  • Guojiang Zhao,
  • Qi Ou,
  • Zifeng Zhao,
  • Shangqian Chen,
  • Haitao Lin,
  • Xiaohong Ji,
  • Zhen Wang,
  • Hongshuai Wang,
  • Hengxing Cai,
  • Lirong Wu,
  • Shuqi Lu,
  • FengTianCi Yang,
  • Yaping Wen,
  • Yingfeng Zhang,
  • Haibo Ma,
  • Zhifeng Gao,
  • Zheng Cheng,
  • Weinan E

摘要

The rational design of organic functional devices relies on understanding structure-property-performance relationships through multi-scale characterization. However, traditional characterizations are costly and require multidisciplinary expertise. Here we present OCNet, a domain-knowledge-enhanced representation learning framework that, for the first time, enables unified virtual characterization from molecules to devices. Pre-trained on over ten million self-generated conjugated molecules and dimers, OCNet learns generalizable microscopic representations comparable to expert-crafted features. As a result, it surpasses state-of-the-art models by over 20% in predicting key computed and experimental molecular optoelectronic properties. OCNet further provides the first transferable model for predicting transfer integrals in thin films, enabling accurate mesoscale carrier mobility estimation via multiscale simulations. By integrating tight-binding-level electronic descriptors, OCNet achieves near real-time, accurate prediction of device power conversion efficiency. Together, OCNet offers a unified and scalable foundation for virtual characterization of organic materials across multiple scales, with broad applicability in photovoltaics, displays, and sensing.