Synthesis of lithium-ion Conducting Polymers Designed by Machine Learning-based Prediction and Screening

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A database for 240 types of lithium-ion conducting solid polymer electrolytes was newly constructed and analyzed by machine learning. Despite the complexity of the polymer composites as electrolytes, accurate prediction was achieved by the appropriate learning model. Inspired by the analyses, poly(glycidyl ether) derivatives were synthesized to yield higher conductivity. Screening of single-ion conducting polymers with de novo design (>15000 candidates) was also conducted based on the established database.

Original languageEnglish
Pages (from-to)130-132
Number of pages3
JournalChemistry Letters
Volume48
Issue number2
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Conducting polymers
Lithium
Electrolytes
Learning systems
Screening
Polymers
Ions
Derivatives
Composite materials
glycidyl ethers

Keywords

  • Lithium-ion battery
  • Machine learning
  • Solid polymer electrolyte

ASJC Scopus subject areas

  • Chemistry(all)

Cite this

@article{eb2e0a3da6e54c56b73f0dc25ae6cb56,
title = "Synthesis of lithium-ion Conducting Polymers Designed by Machine Learning-based Prediction and Screening",
abstract = "A database for 240 types of lithium-ion conducting solid polymer electrolytes was newly constructed and analyzed by machine learning. Despite the complexity of the polymer composites as electrolytes, accurate prediction was achieved by the appropriate learning model. Inspired by the analyses, poly(glycidyl ether) derivatives were synthesized to yield higher conductivity. Screening of single-ion conducting polymers with de novo design (>15000 candidates) was also conducted based on the established database.",
keywords = "Lithium-ion battery, Machine learning, Solid polymer electrolyte",
author = "Kan Hatakeyama and Toshiki Tezuka and Yoshinori Nishikitani and Hiroyuki Nishide and Kenichi Oyaizu",
year = "2019",
month = "1",
day = "1",
doi = "10.1246/cl.180847",
language = "English",
volume = "48",
pages = "130--132",
journal = "Chemistry Letters",
issn = "0366-7022",
publisher = "Chemical Society of Japan",
number = "2",

}

TY - JOUR

T1 - Synthesis of lithium-ion Conducting Polymers Designed by Machine Learning-based Prediction and Screening

AU - Hatakeyama, Kan

AU - Tezuka, Toshiki

AU - Nishikitani, Yoshinori

AU - Nishide, Hiroyuki

AU - Oyaizu, Kenichi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - A database for 240 types of lithium-ion conducting solid polymer electrolytes was newly constructed and analyzed by machine learning. Despite the complexity of the polymer composites as electrolytes, accurate prediction was achieved by the appropriate learning model. Inspired by the analyses, poly(glycidyl ether) derivatives were synthesized to yield higher conductivity. Screening of single-ion conducting polymers with de novo design (>15000 candidates) was also conducted based on the established database.

AB - A database for 240 types of lithium-ion conducting solid polymer electrolytes was newly constructed and analyzed by machine learning. Despite the complexity of the polymer composites as electrolytes, accurate prediction was achieved by the appropriate learning model. Inspired by the analyses, poly(glycidyl ether) derivatives were synthesized to yield higher conductivity. Screening of single-ion conducting polymers with de novo design (>15000 candidates) was also conducted based on the established database.

KW - Lithium-ion battery

KW - Machine learning

KW - Solid polymer electrolyte

UR - http://www.scopus.com/inward/record.url?scp=85060593169&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060593169&partnerID=8YFLogxK

U2 - 10.1246/cl.180847

DO - 10.1246/cl.180847

M3 - Article

VL - 48

SP - 130

EP - 132

JO - Chemistry Letters

JF - Chemistry Letters

SN - 0366-7022

IS - 2

ER -