Virtual reaction condition optimization based on machine learning for a small number of experiments in high-dimensional continuous and discrete variables

Mikito Fujinami, Junji Seino, Takumi Nukazawa, Shintaro Ishida, Takeaki Iwamoto, Hiromi Nakai

Research output: Contribution to journalArticle

Abstract

We examined a virtual simulation scheme for reaction condition optimization using machine learning for a small number of experiments with nine reaction conditions, consisting of five continuous and four discrete variables. Simulations were performed for predicting product yields in a synthetic reaction of tetrasilabicyclo[1.1.0]but-1(3)-ene (SiBBE). The performances in terms of accuracy and efficiency in the simulations and the chemical implications of the results were discussed.

Original languageEnglish
Pages (from-to)961-964
Number of pages4
JournalChemistry Letters
Volume48
Issue number8
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

Learning systems
Experiments

Keywords

  • Data science
  • Machine learning
  • Reaction condition optimization

ASJC Scopus subject areas

  • Chemistry(all)

Cite this

Virtual reaction condition optimization based on machine learning for a small number of experiments in high-dimensional continuous and discrete variables. / Fujinami, Mikito; Seino, Junji; Nukazawa, Takumi; Ishida, Shintaro; Iwamoto, Takeaki; Nakai, Hiromi.

In: Chemistry Letters, Vol. 48, No. 8, 01.01.2019, p. 961-964.

Research output: Contribution to journalArticle

@article{6af057f7b9de4010a6fdd775027f168c,
title = "Virtual reaction condition optimization based on machine learning for a small number of experiments in high-dimensional continuous and discrete variables",
abstract = "We examined a virtual simulation scheme for reaction condition optimization using machine learning for a small number of experiments with nine reaction conditions, consisting of five continuous and four discrete variables. Simulations were performed for predicting product yields in a synthetic reaction of tetrasilabicyclo[1.1.0]but-1(3)-ene (SiBBE). The performances in terms of accuracy and efficiency in the simulations and the chemical implications of the results were discussed.",
keywords = "Data science, Machine learning, Reaction condition optimization",
author = "Mikito Fujinami and Junji Seino and Takumi Nukazawa and Shintaro Ishida and Takeaki Iwamoto and Hiromi Nakai",
year = "2019",
month = "1",
day = "1",
doi = "10.1246/cl.190267",
language = "English",
volume = "48",
pages = "961--964",
journal = "Chemistry Letters",
issn = "0366-7022",
publisher = "Chemical Society of Japan",
number = "8",

}

TY - JOUR

T1 - Virtual reaction condition optimization based on machine learning for a small number of experiments in high-dimensional continuous and discrete variables

AU - Fujinami, Mikito

AU - Seino, Junji

AU - Nukazawa, Takumi

AU - Ishida, Shintaro

AU - Iwamoto, Takeaki

AU - Nakai, Hiromi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We examined a virtual simulation scheme for reaction condition optimization using machine learning for a small number of experiments with nine reaction conditions, consisting of five continuous and four discrete variables. Simulations were performed for predicting product yields in a synthetic reaction of tetrasilabicyclo[1.1.0]but-1(3)-ene (SiBBE). The performances in terms of accuracy and efficiency in the simulations and the chemical implications of the results were discussed.

AB - We examined a virtual simulation scheme for reaction condition optimization using machine learning for a small number of experiments with nine reaction conditions, consisting of five continuous and four discrete variables. Simulations were performed for predicting product yields in a synthetic reaction of tetrasilabicyclo[1.1.0]but-1(3)-ene (SiBBE). The performances in terms of accuracy and efficiency in the simulations and the chemical implications of the results were discussed.

KW - Data science

KW - Machine learning

KW - Reaction condition optimization

UR - http://www.scopus.com/inward/record.url?scp=85069809892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069809892&partnerID=8YFLogxK

U2 - 10.1246/cl.190267

DO - 10.1246/cl.190267

M3 - Article

AN - SCOPUS:85069809892

VL - 48

SP - 961

EP - 964

JO - Chemistry Letters

JF - Chemistry Letters

SN - 0366-7022

IS - 8

ER -