Mapping the application research on machine learning in the field of ionic liquids: A bibliometric analysis

Abstract

The aim was to gain a deep understanding of the research status and application of machine learning in the field of ionic liquids, and to identify the research hotspots and frontiers. Co-occurrence analysis, co-citation analysis, key literature citation temporal analysis and emerging word analysis were used. The results show that the knowledge base of applying machine learning in the field of ionic liquids can be divided into three parts: fundamental properties and application research, thermodynamics and phase equilibrium research, and the combination of machine learning with computational chemistry methods. The research hotspots mainly include the prediction and optimization of properties, the prediction of phase behavior, and research on machine learning algorithms. The current research frontiers in applying machine learning in the field of ionic liquids include the prediction of ionic liquid performance, the structure-property relationships of ionic liquids, and the optimization and design of ionic liquid processes.