Utilization of machine learning for radiation graft polymerization and and construction of polymerization yield prediction model

2023 Fiscal Year Final Research Report

• Project/Area Number: 20K12488
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Review Section: Basic Section 80040:Quantum beam science-related
• Research Institution: National Institutes for Quantum Science and Technology
• Principal Investigator: Ueki Yuji 国立研究開発法人量子科学技術研究開発機構, 高崎量子応用研究所 先端機能材料研究部, 併任 (50446415)
• Project Period (FY): 2020-04-01 – 2024-03-31
• Keywords: 量子ビーム / 放射線グラフト重合 / 機械学習 / 重合予測

Outline of Final Research Achievements

Conventional polymer material development relies on inefficient trial-and-error experiments based on researcher’s “experience and intuition”. As a result, the development of new polymers requires an enormous amount of time and high costs. In this research, we have succeeded in creating an AI model that can instantly predict the grafting yields based solely on the physical and chemical properties of the monomers, by integrating machine learning approach in the conventional radiation grafting process. Additionally, the creating AI model can quantify the importance of various explanatory variables on the grafting yield. Analysis of the AI model revealed that the monomer’s “polarizability”, which represents a miscibility indicator of the monomer to the trunk polymer, and the “O2 NMR shift”, which represents a diffusivity indicator of the monomer into the trunk polymer, were important explanatory variables for predicting the grafting yield.

Free Research Field

量子ビーム科学関連

Academic Significance and Societal Importance of the Research Achievements

本成果は、機能性高分子材料の創製手法のひとつである放射線グラフト重合における機械学習利用の有用性を示したものである。本成果は、低コストで迅速性のある効率的な高分子材料開発に資する基礎技術であり、企業競争力向上に貢献可能であることから、その社会的意義は大きい。また、本成果の応用・発展は、高分子材料開発分野における新たな科学的知見の発見や革新的高分子材料の創出に繋がる可能性を有していることから、その学術的意義も大きい。