Equivalent circuit model recognition of electrochemical impedance spectroscopy via machine learning

Electrochemical impedance spectroscopy (EIS) is an effective method for studying electrochemical systems. The interpretation of EIS is the biggest challenge in this technology, which requires reasonable modeling. To overcome the subjectivity of human analysis, this work uses machine learning to carry out EIS model recognition. Raw EIS data and their equivalent circuit models are collected from the literature, and the support vector machine (SVM) is used to analyze these data. Comparing with other machine learning algorithms, SVM achieves the best comprehensive performance in this database. As a result, the optimized SVM model can efficiently figure out the most suitable equivalent circuit model of the given EIS spectrum. This study demonstrates the great potential of machine learning in electrochemical researches.