Amin Sadeghi

AutoEIS is an innovative Python software tool designed to automate the analysis of Electrochemical Impedance Spectroscopy (EIS) data, a key technique in electrochemical materials research. By integrating evolutionary algorithms and Bayesian inference, AutoEIS automates the construction and evaluation of equivalent circuit models (ECM), providing more objective, efficient, and accurate analysis compared to traditional manual methods. EIS data interpretation is fundamental for understanding electrochemical processes and generating mechanistic insights. However, selecting an appropriate ECM has historically been complex, time-consuming, and subjective (Wang et al., 2021). AutoEIS resolves this challenge through a systematic approach: it generates multiple candidate ECMs, evaluates their fit against experimental data, and ranks them using comprehensive statistical metrics. This methodology not only streamlines analysis but also introduces reproducibility and objectivity that manual analysis cannot consistently achieve. The effectiveness of AutoEIS has been validated through diverse case studies, including oxygen evolution reaction electrocatalysis, corrosion of multi-principal element alloys, and CO2 reduction in electrolyzer devices (Zhang et al., 2023). These applications demonstrate the software’s versatility across different electrochemical systems and its ability to identify physically meaningful ECMs that accurately capture the underlying electrochemical phenomena.

A machine learning (ML) model was developed to study the discharge behaviour of a Li(x)Ni(0.33)Mn(0.33)Co(0.33)O2 half-cell with particle-scale resolution. The ML model could predict the state-of-lithiation of the particles as a function of time and C-rate. Although direct numerical simulation has been well established in this area as the prevalent method of modeling batteries, computational expense increases going from 1D-homogenized model to particle-resolved 3D models. The present ML model was trained on a total of sixty different electrodes with various lengths for a total of 4 different C-rates: 0.25, 1, 2, and 3C. The ML model used convolutional layers, resulting in an image-to-image regression network. To evaluate model performance, the root mean squared error was compared between the state of lithiation (SoL) predicted by the ML model and ground truth results from pore-scale direct numerical simulation (DNS) on unseen electrode configurations. It was shown that the ML model can predict the SoL at better than 99% accuracy in terms of relative error, but almost an order of magnitude faster than the DNS approach. The present work was limited to 2D cases but demonstrates that ML is a viable path forward for studying real 3D microstructures.