Deep-Learning Potentials for Proton Transport in Double-Sided Graphanol

There is a need to develop new materials for proton exchange mem- branes that can operate at higher temperatures and low humidities. Designing and evaluating novel membrane materials using density func- tional theory (DFT) is infeasible because of length and time scale limitations of the method. We have developed a deep-learning potential (DP) to evaluate double-sided graphanol (DSG), which is a poten- tial anhydrous proton conducting material. Our DP was trained on DFT data by employing an active learning approach. Our DP is com- putationally efficient and has near-DFT accuracy. We have analyzed DSG by computing phonon properties, estimating thermal fluctuations, and calculate self-diffusivity using our DP. Our results for DSG are compared with single-sided graphanol (SSG). We observed lower ther- mal fluctuation and similar proton self-diffusivity at 800 K in DSG compared to SSG. Our DP simulations show that the structural dif- ferences in DSG compared to SSG do not impact proton transport. DSG is a promising membrane material deserving of synthetic efforts.