Optimizing NiMo Electrocatalyst Coatings for Hydrogen Evolution in Alkaline Electrolysis With The Machine Learning‐Guided Autonomous Platform CatBot

The discovery of efficient, durable, and platinum group metal‐free electrocatalysts for alkaline water electrolysis is essential to reduce the cost of green hydrogen. Efficient exploration of the vast possible synthetic space is nevertheless hindered by the slow pace of manual experimentation. Here, a closed‐loop optimization is presented that combines an automated electrocatalyst synthesis and testing system, CatBot, with Bayesian optimization and accelerated stress testing at industrial conditions for the rapid discovery of active and durable NiMo coatings. Distinct regions with exceptionally high activity and stability are identified within limited experimental budgets on a nickel wire substrate, using different search strategies to efficiently navigate the six‐dimensional synthesis space exceeding possible combinations. The most promising coatings are upscaled onto technological nickel foam electrodes showing platinum‐level catalytic activity with overpotentials of 173 mV at –1 in 30 wt.% KOH at for the hydrogen evolution reaction. This work establishes a generalizable strategy for the autonomous optimization of functional electrocatalyst coatings under realistic operating conditions.