Scholarlink

<p>This work presents results on the design of machine learning models trained using a large set of experimental kinetic data for the catalytic Suzuki—Miyaura reaction (approximately 5000 measurements from kinetic experiments). The training was performed on different types of datasets describing the rate and selectivity of the product formation and the product yield. The incorporation of kinetic parameters (rate and differential selectivity) significantly enhances the predictive capability of the models across a wide range of process conditions.</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

New applications of kinetic data. The development of machine learning kinetic models for the Suzuki—Miyaura reaction

  • 期刊论文

  • 发表日期：

    2025年11月1日

查看全文
  • A. F. Schmidt,
  • A. A. Kurokhtina,
  • E. V. Larina,
  • N. A. Lagoda

摘要

This work presents results on the design of machine learning models trained using a large set of experimental kinetic data for the catalytic Suzuki—Miyaura reaction (approximately 5000 measurements from kinetic experiments). The training was performed on different types of datasets describing the rate and selectivity of the product formation and the product yield. The incorporation of kinetic parameters (rate and differential selectivity) significantly enhances the predictive capability of the models across a wide range of process conditions.