Guiding the optimization of membraneless microfluidic fuel cells via explainable artificial intelligence: Comparative analyses of multiple machine learning models and investigation of key operating parameters

This study employs explainable artificial intelligence to optimize membraneless microfluidic fuel cells, comparing the performance of multiple machine learning models to identify key operating parameters that influence system efficiency. The research reveals that a combination of feature selection and gradient boosting models yields the most accurate predictions, while also highlighting the importance of pH, flow rate, and electrode spacing in determining system performance. The findings provide a framework for optimizing MES design and operation, with potential applications in bioelectrochemical systems and sustainable energy production.

Generated by MESSAI extraction pipeline · review against source PDF