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

Abstract 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.

Authors

Institutions

Publication Details

Journal
ACS Applied Engineering Materials
Published
2026-11-17
DOI
https://doi.org/10.1021/acsaenm.6c01357
Primary Topic
Conducting polymers and applications
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Aiwei Zhao, Masayoshi Higuchi, Satya Ranjan Jena
2 links
ACS Applied Engineering Materials
Conducting polymers and applications
article

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

Aiwei Zhao, Masayoshi Higuchi, Satya Ranjan Jena
article en

Abstract

Abstract 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.

ACS Applied Engineering Materials
National Institute for Materials Science (JP), The University of Osaka (JP)
Environmental Restoration and Conservation Agency, Japan Society for the Promotion of Science, JST-Mirai Program
Conducting polymers and applications
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon