Chemically-informed active learning enables data-efficient multi-objective optimization of self-healing polyurethanes
Chemical Science · 2026 · 17 (7) · 3627-3638
DOI: 10.1039/d5sc07752d ↗Kurz gefasst
Fachartikel in der Zeitschrift Chemical Science, 2026. Verfasst von Kang Liang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Henan Key Laboratory of Protection and Safety Energy Storage of Light Metal Materials, College of Chemistry and Molecular Sciences, Henan University …. Die Arbeit wurde bisher 47-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 3.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
A chemically-informed active learning (CIAL) framework synergizes chemical knowledge with machine learning to achieve multi-objective optimization of self-healing polyurethanes with only 20 samples, overcoming traditional material design trade-offs.
Autor:innen und Institutionen
- Henan Key Laboratory of Protection and Safety Energy Storage of Light Metal Materials, College of Chemistry and Molecular Sciences, Henan University Kaifeng 475004 China chemwangl@henu.edu.cn zhangjinglai@henu.edu.cn.
ORCID-Profile: Li Wang, Jinglai Zhang
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Liang, K., Qi, X., Xiao, X., Wang, L., & Zhang, J. (2026). Chemically-informed active learning enables data-efficient multi-objective optimization of self-healing polyurethanes. Chemical Science, 17(7), 3627-3638. https://doi.org/10.1039/d5sc07752d
Vancouver
Liang K, Qi X, Xiao X, Wang L, Zhang J. Chemically-informed active learning enables data-efficient multi-objective optimization of self-healing polyurethanes. Chemical Science. 2026;17(7):3627-3638. doi:10.1039/d5sc07752d
BibTeX
@article{Liang2026,
author = {Liang, Kang and Qi, Xinke and Xiao, Xu and Wang, Li and Zhang, Jinglai},
title = {Chemically-informed active learning enables data-efficient multi-objective optimization of self-healing polyurethanes},
journal = {Chemical Science},
year = {2026},
volume = {17},
number = {7},
pages = {3627--3638},
doi = {10.1039/d5sc07752d}
}
EUVIMED