Scholarlink

<p>Sustainable polymers are often designed to be degradable or recyclable via low-energy, low-CO₂-emission pathways while demonstrating high physical properties comparable to those of conventional plastics. Aliphatic polycarbonates (APCs), studied as functionalized degradable polymers, are promising candidates for use as sustainable materials. However, enhancing their physical properties remains essential. Polymer properties depend on various factors, including chemical structure, molecular weight and its distribution, branching, higher-order structures, and thermal history, and are therefore not uniquely determined. Machine learning models are powerful tools for predicting polymer properties with associated uncertainty, particularly for polymers absent from open datasets. Herein, we investigate uncertainty-aware predictions of the glass transition temperature (<i>T</i><sub>g</sub>) of APCs using ensembles of multiple molecular descriptors and machine learning methods. The <i>T</i><sub>g</sub> data for more than 50 APCs were collected from previous experimental studies. Prediction models for <i>T</i><sub>g</sub> were constructed using more than 100 combinations of molecular descriptors and machine learning algorithms based on datasets of common polymers. The top five models, selected by coefficients of determination, exhibited moderate predictive performance for APCs. The mean values and standard deviations of the predictions obtained from the top five models provide <i>T</i><sub>g</sub> predictions with quantified uncertainty. This ensemble-based framework will be extended to uncertainty-aware prediction of various polymer properties.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Uncertainty-aware prediction of the glass transition temperature of aliphatic polycarbonates using ensemble machine learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月16日

查看全文
  • Yoshifumi Amamoto,
  • Ryunosuke Ito,
  • Mikako Murakami,
  • Kohzo Ito,
  • Kazuki Fukushima

摘要

Sustainable polymers are often designed to be degradable or recyclable via low-energy, low-CO₂-emission pathways while demonstrating high physical properties comparable to those of conventional plastics. Aliphatic polycarbonates (APCs), studied as functionalized degradable polymers, are promising candidates for use as sustainable materials. However, enhancing their physical properties remains essential. Polymer properties depend on various factors, including chemical structure, molecular weight and its distribution, branching, higher-order structures, and thermal history, and are therefore not uniquely determined. Machine learning models are powerful tools for predicting polymer properties with associated uncertainty, particularly for polymers absent from open datasets. Herein, we investigate uncertainty-aware predictions of the glass transition temperature (Tg) of APCs using ensembles of multiple molecular descriptors and machine learning methods. The Tg data for more than 50 APCs were collected from previous experimental studies. Prediction models for Tg were constructed using more than 100 combinations of molecular descriptors and machine learning algorithms based on datasets of common polymers. The top five models, selected by coefficients of determination, exhibited moderate predictive performance for APCs. The mean values and standard deviations of the predictions obtained from the top five models provide Tg predictions with quantified uncertainty. This ensemble-based framework will be extended to uncertainty-aware prediction of various polymer properties.