Can interpretation of electrochemical impedance spectroscopy data be automated? Where do artificial intelligence algorithms stand?

Abstract

While automation of data interpretation has been successful for optical spectroscopy and chromatography methods, automated interpretation of electrochemical impedance spectroscopy data is confounded by the nonuniqueness of models used to interpret the data in terms of physical quantities. Where automation has been successful, the data are compared with known libraries of high-quality, well-characterized, and specific datasets. In this manuscript, use of automation for data interpretation is reviewed, and guidelines are proposed for those seeking to develop artificial intelligence algorithms for analysis of impedance data.