Development of an Artificial Intelligence-Augmented Impedance Spectroscopy Platform for Characterising Energy Storage Materials Under Nigerian Operational Conditions

Background: Electrochemical impedance spectroscopy is the most informative technique for characterising energy storage materials, but equivalent circuit model selection and parameter extraction require expert knowledge that constrains accessibility in Nigerian research contexts. Artificial intelligence augmentation can democratise impedance spectroscopy analysis. Aim: This study developed an AI-augmented impedance spectroscopy platform integrating hardware design with machine learning-based automatic equivalent circuit identification and parameter extraction for energy storage material characterisation. Methods: A custom impedance analyser hardware platform was designed around a precision signal chain with frequency coverage from 1 mHz to 1 MHz. A deep learning architecture combining convolutional and recurrent neural networks was trained on a dataset of 50,000 simulated and 3,200 experimental impedance spectra with validated circuit model labels. The platform was applied to lithium-ion, lead-acid, and supercapacitor cells under Nigerian ambient conditions from 25 to 50 degrees Celsius. Results: Automatic circuit model identification accuracy was 96.4% on the validation set. Parameter extraction root mean square error was below 3.2% for all major circuit elements. The platform identified thermally accelerated degradation mechanisms in batteries operated above 45 degrees Celsius with 91% diagnostic accuracy. Conclusion: The AI-augmented impedance platform democratises advanced electrochemical characterisation for Nigerian research laboratories. Its application to sustainable energy storage materials research is recommended as an immediate priority. Keywords: electrochemical impedance spectroscopy, artificial intelligence, energy storage, deep learning, Nigeria.