Year: 2025
Type: article
Abstract: Glass development is driven by scientific insights into their material genes as well as engineering practices in response to industry needs. Incubating domain knowledge into well‐formatted datasets and databases, and making them open and visible can accelerate the process, facilitating automated material discovery, and design in the data‐driven era. In this work, we implement a machine‐learning framework to collect information from published research articles. The enriched product, SciGlass+ , transcends the publicly available glass database SciGlass by including both scientific data and research metadata. With these enriched contents, research patterns of glasses are analyzed to identify milestone events in technological development and evaluate their sustainability impact. The integration of experimental data from literature and those from computer simulations provides refined insights into the composition–property relationship, thereby supporting a theory‐driven and artificial intelligence‐assisted approach to glass development. The practical applications of SciGlass+ are demonstrated in screening and designing glasses for electronic packaging and low‐carbon emission materials.
DOI: 10.1111/jace.70393
Authors: Yingjie Zhao, Wei Chen, Haoxuan Tang, Yuanhong Zhao, Hongjinyi Liu, Zhongcheng Min, Yuxiu Luo, Junjie Lu, Jianing Qu, Ruixue Yang, Chuanzhi Li, Qingmin Zhu, Wanting He, Jia Chen, Yuting Mao, Jie Niu, Zhiping Xu
Institutions: Guizhou University, Tsinghua University
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: hybrid
Estimated APC paid: $4,070
Awards: G5388520862, G5819332598
OpenAlex ID: W4416557108