Machine-Learning Assisted Exploration: Toward the Next-Generation Catalyst for Hydrogen Evolution Reaction

Abstract

The development of active catalysts for hydrogen evolution reaction (HER) made from low-cost materials constitutes a crucial challenge in the utilization of hydrogen energy. Earth-abundant molybdenum disulfide (MoS 2 ) has been discovered recently with good activity and stability for HER. In this report, we employ a hydrothermal technique for MoS 2 synthesis which is a cost-effective and environmentally friendly approach and has the potential for future mass production. Machine-learning (ML) techniques are built and subsequently used within a Bayesian Optimization framework to validate the optimal parameter combinations for synthesizing high-quality MoS 2 catalyst within the limited parameter space. Compared with the heavy-labor and time-consuming trial-and-error approach, the ML techniques provide a more efficient toolkit to assist exploration of the most effective HER catalyst in hydrothermal synthesis. To investigate the structure-property relationship, scanning electron microscope (SEM), transmission electron microscope (TEM), X-ray diffraction (XRD), Raman spectroscopy, X-ray photoelectron spectroscopy (XPS), and various electrochemical characterizations have been conducted to investigate the superiority of the ML validated optimized sample. A strong correlation between the material structure and the HER performance has been observed for the optimized MoS 2 catalyst.