EUVIMEDEUVIMED entdecken
Crossref

Electrolyte Screening with Machine-Learning for Electrochromic Devices with Metallosupramolecular Polymer for Enhancement of Coloration Efficiency

Aiwei Zhao, Satya Ranjan Jena, Masayoshi Higuchi

ACS Applied Engineering Materials · 17.11.2026

DOI: 10.1021/acsaenm.6c01357 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACS Applied Engineering Materials, online erschienen am 17.11.2026. Verfasst von Aiwei Zhao und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Gefördert von: JST-Mirai Program, Japan Society for the Promotion of Science, Environmental Restoration and Conservation Agency.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Electrolyte composition greatly influences electrochromic devices (ECDs) performance including switching kinetics and coloration efficiency (CE), but finding suitable electrolytes remains difficult because the device properties cannot be predicted from ionic conductivity alone. We performed electrolyte screening with machine-leaning for the development of ECDs with metallosupramolecular polymers (MSPs) for the first time. As the experimental training data, 15 formulations from four electrolyte systems were evaluated in ECDs with Fe(II)-based MSP (polyFe). The measured bleaching time (t90) ranged from 1.5 to 46.2 s, and the average CE ranged from 223.0 to 932.8 cm2/C. In grouped cross-validation, the bleaching time prediction gave a Spearman correlation coefficient of 0.798, indicating that the relative ordering of formulations was captured more reliably than their absolute switching times. Direct regression of CE showed limited predictive performance, whereas classification of high coloring CE gave a ROC-AUC of 0.820 and an average precision of 0.646. Four formulations selected from a literature-derived electrolyte collection were then tested experimentally. Among them, it was found that an ECD with LiClO4/poly(tetrahydrofuran) exhibited very high coloring CE value of 976.9 cm2/C. It was revealed that machine-learning screening reduced the number of electrolyte candidates requiring experimental testing. While quantitative switching behavior and processing requirements still had to be confirmed experimentally.

Förderung

  • JST-Mirai Program
  • Japan Society for the Promotion of Science
  • Environmental Restoration and Conservation Agency

Zitieren

APA

Zhao, A., Jena, S. R., & Higuchi, M. (2026). Electrolyte Screening with Machine-Learning for Electrochromic Devices with Metallosupramolecular Polymer for Enhancement of Coloration Efficiency. ACS Applied Engineering Materials. https://doi.org/10.1021/acsaenm.6c01357

Vancouver

Zhao A, Jena SR, Higuchi M. Electrolyte Screening with Machine-Learning for Electrochromic Devices with Metallosupramolecular Polymer for Enhancement of Coloration Efficiency. ACS Applied Engineering Materials. 2026. doi:10.1021/acsaenm.6c01357

BibTeX
@article{Zhao2026,
  author = {Zhao, Aiwei and Jena, Satya Ranjan and Higuchi, Masayoshi},
  title = {Electrolyte Screening with Machine-Learning for Electrochromic Devices with Metallosupramolecular Polymer for Enhancement of Coloration Efficiency},
  journal = {ACS Applied Engineering Materials},
  year = {2026},
  doi = {10.1021/acsaenm.6c01357}
}
Kostenlos starten →