Machine Learning Models for Melting Point Prediction of Ionic Liquids: CatBoost Approach

FH-HES Universities of Applied Sciences

Authors

  • Florence Yerly Haute école d'ingénierie et d'architecture, Fribourg, HES-SO University of Applied Sciences and Arts Western Switzerland https://orcid.org/0009-0002-5369-7342
  • Mathias Blaise Haute école d’ingénierie et d’architecture Fribourg, HES-SO University of Applied Sciences and Arts Western Switzerland
  • Simon Barras Haute école d’ingénierie et d’architecture Fribourg, HES-SO University of Applied Sciences and Arts Western Switzerland

DOI:

https://doi.org/10.2533/chimia.2023.625

Keywords:

Ionic liquids, Melting Point, Molecular Descriptors, Prediction

Abstract

Using ionic liquids as phase changing materials is of particular interest in the context of heat storage. As a consequence, predicting accurately the melting point of ionic liquids is of capital importance as it is one of the most important thermophysical properties in this context. In this work we consider a data set composed of 2249 different ionic liquids, with a majority of imidazole or ammonium cation-based molecules. We present a free and easy-to-use melting point predictive algorithm built on the CatBoost algorithm, making strong use of molecular descriptors. Based on LASSO, we select the most relevant descriptors for the task at hand and compare the model with previous ones.

Author Biography

Florence Yerly, Haute école d'ingénierie et d'architecture, Fribourg, HES-SO University of Applied Sciences and Arts Western Switzerland

Dr. Florence Yerly studied mathematics at the University of Fribourg. She has completed his PhD with Prof. Christian Mazza in applied mathematics. She is now associate professor at the Haute Ecole d'ingénierie et d'Architecture de Fribourg, a school of the HES-SO. She is member of the Institue ChemTech and FRISAM, a mathematical and statistical consulting service in Fribourg. As an applied mathematician, she worked in various fields such as systems biology, genetics, micropaleontology or chemistry, using tools from dynamical systems, probability theory, (Bayesian) inferential statistics, experimental design.

Downloads

Published

2023-09-20

How to Cite

[1]
F. Yerly, M. Blaise, S. Barras, Chimia 2023, 77, 625, DOI: 10.2533/chimia.2023.625.

Issue

Vol. 77 No. 9 (2023): Swiss TPH: 30 Years of R&D Towards New Drugs for Tropical Diseases

Section

Columns, Conference Reports

Categories

License

Copyright (c) 2023 Florence Yerly, Mathias Blaise, Simon Barras

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.