Scholarlink

<p>This study presents a bibliometric analysis on the use of artificial neural networks in chemical reactions, focusing on processes involving esters. Global trends, authors, institutions, countries, and methodological approaches were examined between 2020 and 2025. Bibliometric mapping was conducted using VOSviewer and RStudio. The initial search identified 3227 publications, of which only 38 (1.18%) addressed reactions involving esters and only 14 (0.43%) focused directly on this topic, indicating that the application of neural networks in this field is still at an early stage but presents significant growth potential. China, India, and the United States lead in publication volume and international collaboration, whereas Brazil shows limited participation. Institutions such as the Chinese Academy of Sciences and the Indian Institute of Technology stand out in productivity and scientific impact. Term analysis revealed increasing attention to concepts related to kinetics, neural networks, optimization, and machine learning, reflecting growing interest in AI assisted modeling of chemical reactions. The detailed analysis of the 14 selected studies organized the literature into five axes: objectives, methodologies, machine learning categories, input and output variables, and main results. Neural network models, particularly when integrated with optimization methods or physicochemical knowledge, demonstrated high predictive capacity, reduced experimental effort, and improved understanding of reaction kinetics in ester related systems.</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

Machine learning in chemical engineering: a bibliometric mapping of processes involving esters

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月13日

查看全文
  • Caio P. Silva,
  • Ana L. G. Ferreira,
  • William M. Godoy,
  • Leandro G. Aguiar

摘要

This study presents a bibliometric analysis on the use of artificial neural networks in chemical reactions, focusing on processes involving esters. Global trends, authors, institutions, countries, and methodological approaches were examined between 2020 and 2025. Bibliometric mapping was conducted using VOSviewer and RStudio. The initial search identified 3227 publications, of which only 38 (1.18%) addressed reactions involving esters and only 14 (0.43%) focused directly on this topic, indicating that the application of neural networks in this field is still at an early stage but presents significant growth potential. China, India, and the United States lead in publication volume and international collaboration, whereas Brazil shows limited participation. Institutions such as the Chinese Academy of Sciences and the Indian Institute of Technology stand out in productivity and scientific impact. Term analysis revealed increasing attention to concepts related to kinetics, neural networks, optimization, and machine learning, reflecting growing interest in AI assisted modeling of chemical reactions. The detailed analysis of the 14 selected studies organized the literature into five axes: objectives, methodologies, machine learning categories, input and output variables, and main results. Neural network models, particularly when integrated with optimization methods or physicochemical knowledge, demonstrated high predictive capacity, reduced experimental effort, and improved understanding of reaction kinetics in ester related systems.