Real-Time Parameter Estimation in Electrochemical Systems with Confounding Variables using Neural Network

Measuring and estimating parameters of interest in real-time in electrochemical systems remains a challenge. Traditional methods used to characterize the response and estimate parameters of interest are often slow and time-consuming, thus, not applicable for real-time applications. Here, we develop a workflow utilizing physics-based processing and deep learning to estimate parameters and confounding variables with uncertainties in real-time from large amplitude AC Voltammetry (LA-ACV) measurements on electrochemical systems. We demonstrate our approach on a model electrochemical system (K₃Fe(CN)₆ in potassium phosphate buffer) to estimate the concentration of redox active species (K₃Fe(CN)₆) in the presence of unknown viscosity (confounding variable) with 0.3 mM median absolute error in concentration estimation.