Briceno-Mena, Romagnoli Paper Published
March 7, 2022
BATON ROUGE, LA – LSU Chemical Engineering PhD Student Luis Briceno-Mena, Chemical Engineering Professor Jose Romagnoli, and Pennsylvania State University Chemical Engineering Associate Professor Chris Arges recently had their paper, “PemNet: A Transfer Learning-Based Modeling Approach of High-Temperature Polymer Electrolyte Membrane Electrochemical Systems,” published in Industrial & Engineering Chemistry Research.
The paper details the problem of modeling systems, for which experimental data is scarce and physical knowledge is limited. Specifically, widespread adoption of high-temperature electrochemical systems, such as polymer electrolyte membrane fuel cells (HT-PEMFCs), requires models and computational tools for accurate optimization and guiding new materials for enhancing fuel cell performance and durability. Knowledge-based modeling has its limitations, as it is time-consuming and requires information about the system that is not always available. Data-driven modeling, on the other hand, is easier to implement but often necessitates large datasets that can be difficult to obtain.
Briceno-Mena, Romagnoli, and Arges write that combining the two modeling approaches by implementing a few-shot learning (FSL) approach, or making predictions based on a large simulated datasets and a limited number of experimental samples, results in a more efficient modeling framework.
Like us on Facebook (@lsuengineering) or follow us on Twitter and Instagram (@lsuengineering).
Contact: Joshua Duplechain
Director of Communications