Development of Deep Learning Simulation and Density Functional Theory Framework for Electrocatalyst Layers for PEM Electrolyzers

The electrocatalyst layers (ECLs) in polymer electrolyte membrane (PEM) electrolyzers are fundamentally comprised of IrOx catalysts, support material, and an ionomer. Their stability is critically dependent on structure and composition, necessitating a thorough understanding of ionization potential and work function. We employ Density Functional Theory (DFT) to determine the ionization states of ECLs and to optimize their electronic properties. Furthermore, advanced deep learning simulations (DLSs) significantly enhance the kinetic and transport behaviors of these layers. This work integrates DFT and DLS to elucidate the characteristics of ECLs within PEM electrolyzer cells. We strategically utilize DFT to refine catalyst molecules and assess their electronic properties, while DLS is employed to predict the potential energy of support molecules in the catalyst layers. We establish a clear relationship between the energy and geometry of IrOx molecules. The DFT-DLS framework robustly calculates potential energy and reaction coordinates, effectively bridging theoretical computations with the dynamic behavior of molecules in catalyst layers. We validate our model by comparing it with the experimental polarization curve of the IrOx-based anode catalyst layer in a functioning electrolyzer. The observed Tafel slope and exchange current density unequivocally confirm that the oxygen evolution reaction (OER) occurs through a well-defined electrochemical pathway, with oxygen generation proceeding according to the charge transfer mechanism predicted by the DFT-DLS framework.