Machine-Learning Enabled Search for The Next-Generation Catalyst for Hydrogen Evolution Reaction

TL;DR

This paper combines machine learning with experimental synthesis to optimize the production of MoS₂ catalysts for hydrogen evolution, aiming to improve efficiency and reduce costs in hydrogen energy applications.

Contribution

It introduces a machine-learning framework within Bayesian Optimization to identify optimal synthesis parameters for MoS₂ catalysts for HER.

Findings

Strong structure-property relationship identified

ML-guided synthesis predicts optimal parameters

Potential for scalable, cost-effective catalyst production

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 employed the hydrothermal technique for MoS$_2$ synthesis which is a cost-effective and environmentally friendly approach and has the potential for future mass production. 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. A strong correlation between the material structure and the HER performance has been observed. Moreover, machine-learning (ML) techniques were 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. The model will be able to guide the wet chemical synthesis of MoS$_2$ and produce the most effective HER catalyst eventually.