Machine Learning for Polymer Chemical Resistance to Organic Solvents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kunieda, Shogo, Yambe, Mitsuru, Murashima, Hiromori, Nakamura, Takeru, Shintani, Toshiaki, Kamijima, Hitoshi, Hayashi, Yoshihiro, Hanawa, Yosuke, Yoshida, Ryo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911140587503616
author Kunieda, Shogo
Yambe, Mitsuru
Murashima, Hiromori
Nakamura, Takeru
Shintani, Toshiaki
Kamijima, Hitoshi
Hayashi, Yoshihiro
Hanawa, Yosuke
Yoshida, Ryo
author_facet Kunieda, Shogo
Yambe, Mitsuru
Murashima, Hiromori
Nakamura, Takeru
Shintani, Toshiaki
Kamijima, Hitoshi
Hayashi, Yoshihiro
Hanawa, Yosuke
Yoshida, Ryo
contents Predicting the chemical resistance of polymers to organic solvents is a longstanding challenge in materials science, with significant implications for sustainable materials design and industrial applications. Here, we address the need for interpretable and generalizable frameworks to understand and predict polymer chemical resistance beyond conventional solubility models. We systematically analyze a large dataset of polymer solvent combinations using a data-driven approach. Our study reveals that polymer crystallinity and density, as well as solvent polarity, are key factors governing chemical resistance, and that these trends are consistent with established theoretical models. These findings provide a foundation for rational screening and design of polymer materials with tailored chemical resistance, advancing both fundamental understanding and practical applications.
format Preprint
id arxiv_https___arxiv_org_abs_2509_05344
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Machine Learning for Polymer Chemical Resistance to Organic Solvents
Kunieda, Shogo
Yambe, Mitsuru
Murashima, Hiromori
Nakamura, Takeru
Shintani, Toshiaki
Kamijima, Hitoshi
Hayashi, Yoshihiro
Hanawa, Yosuke
Yoshida, Ryo
Soft Condensed Matter
Materials Science
Predicting the chemical resistance of polymers to organic solvents is a longstanding challenge in materials science, with significant implications for sustainable materials design and industrial applications. Here, we address the need for interpretable and generalizable frameworks to understand and predict polymer chemical resistance beyond conventional solubility models. We systematically analyze a large dataset of polymer solvent combinations using a data-driven approach. Our study reveals that polymer crystallinity and density, as well as solvent polarity, are key factors governing chemical resistance, and that these trends are consistent with established theoretical models. These findings provide a foundation for rational screening and design of polymer materials with tailored chemical resistance, advancing both fundamental understanding and practical applications.
title Machine Learning for Polymer Chemical Resistance to Organic Solvents
topic Soft Condensed Matter
Materials Science
url https://arxiv.org/abs/2509.05344