Attribution Fingerprinting by Interpretable Machine Learning Reveals Category‐Specific Additive Design Rules for Zinc Anodes
Advanced Materials · 02.11.2026
DOI: 10.1002/adma.75609 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Materials, online erschienen am 02.11.2026. Verfasst von Guolang Zhou und 15 weiteren Autor:innen. Beteiligte Einrichtung: Jiangsu Key Laboratory for the Chemistry of Low-Dimensional Materials, School of Chemistry and Chemical Engineering, Huaiyin Normal University, Huai'…. Die Arbeit nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Science Foundation for Distinguished Young Scholars, Natural Science Foundation of Jiangsu Province.
Abstract (Originalsprache)
Electrolyte additives are one of the most direct remedy for interfacial instability in aqueous zinc‐ion batteries, yet their development remains empirical. Existing machine‐learning (ML) screening strategies presume a single global structure‐property relationship shared by all additives. Here, an interpretable ML framework predicts cycle life from molecular descriptors and test conditions, and molecule‐specific SHapley Additive exPlanations (SHAP) profiles serve as attribution fingerprints. Unsupervised clustering resolves the additives into three attribution‐based categories, governed respectively by adsorption energetics, charge‐transfer gap and hydrogen‐bond‐network regulation, indicating that one universal descriptor set may not hold across chemically distinct additives. Representative additives from each category, none present in the training set, agree with experiment to within 11%. Category I screening identifies 2‐fluoropyridine‐5‐carbaldehyde (2FPD), predicted at 3218 h, and Zn//Zn cells deliver 3010 h at 1 mA cm −2 and 1 mAh cm −2 , within 6.5% of prediction. Structural controls trace the improvement to the aldehyde: retaining it alone gives 900 h against an 89 h baseline, whereas fluorine alone gives 90 h. 2FPD constructs a graded organic‐inorganic interphase that limits water access to the zinc surface and accelerates Zn 2+ desolvation, and Zn//MnO 2 full cells retain 96% capacity over 4000 cycles. This workflow offers a route towards interpretability‐guided additive design.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Jiangsu Key Laboratory for the Chemistry of Low-Dimensional Materials, School of Chemistry and Chemical Engineering, Huaiyin Normal University, Huai'an, P. R. China.
- Key Laboratory for Soft Chemistry and Functional Materials of Ministry of Education, Nanjing University of Science and Technology, Nanjing, P. R. China.
- State Key Laboratory of Heavy Oil Processing, College of Chemical Engineering and Environment, China University of Petroleum-Beijing, Beijing, P. R. China.
ORCID-Profile: Guolang Zhou, Minmeng Tang, Zhendong Yu, Wenshuai Zhu, Junwu Zhu
Förderung
- National Natural Science Foundation of China
- National Science Foundation for Distinguished Young Scholars
- Natural Science Foundation of Jiangsu Province
- Major Project of Basic Natural Science Research for Colleges and Universities in Jiangsu Province
- China Postdoctoral Science Foundation
Zitieren
APA
Zhou, G., Tang, M., Xu, X., Tang, X., Wang, T., Zhao, C., Tang, C., Liu, C., Miao, T., Xu, L., Yan, Y., Yu, Z., Cheng, Z., Zhang, L., Zhu, W., & Zhu, J. (2026). Attribution Fingerprinting by Interpretable Machine Learning Reveals Category‐Specific Additive Design Rules for Zinc Anodes. Advanced Materials. https://doi.org/10.1002/adma.75609
Vancouver
Zhou G, Tang M, Xu X, Tang X, Wang T, Zhao C, et al. Attribution Fingerprinting by Interpretable Machine Learning Reveals Category‐Specific Additive Design Rules for Zinc Anodes. Advanced Materials. 2026. doi:10.1002/adma.75609
BibTeX
@article{Zhou2026,
author = {Zhou, Guolang and Tang, Minmeng and Xu, Xinwang and Tang, Xin and Wang, Tianshi and Zhao, Chong and Tang, Chao and Liu, Cheng and Miao, Tengfei and Xu, Le and Yan, Yubo and Yu, Zhendong and Cheng, Zhipeng and Zhang, Lili and Zhu, Wenshuai and Zhu, Junwu},
title = {Attribution Fingerprinting by Interpretable Machine Learning Reveals Category‐Specific Additive Design Rules for Zinc Anodes},
journal = {Advanced Materials},
year = {2026},
doi = {10.1002/adma.75609}
}
EUVIMED