Optimizing High-Throughput Synthesis of PGM-Free ORR Electrocatalyst Using Machine Learning Approach

Abstract

Over the past decades, significant improvement has been achieved in the performance of platinum group metal-free (PGM-free) materials as an alternative to Pt-based electrocatalysts for oxygen reduction reaction (ORR). However, further progress in ORR activity requires new precursors and synthesis approaches. In response to this challenge, we generated a first of its kind experimental dataset of 36 samples using high-throughput synthesis and activity measurements. Numerous control parameters (e.g., Fe precursor identity, the precursor content, and pyrolysis temperature) were varied. We then developed several state-of-the-art machine learning (ML)-based regression models to predict ORR activity, dependent on selected synthesis variables. Through a novel iterative algorithm, higher prediction accuracy (smaller root-mean square error) was achieved. We identified that gradient boosting regression (GBR) and support vector regression (SVR), among several methods, work best for this dataset. Aided by our ML-based surrogate models, we decided to alter catalyst synthesis conditions, which resulted in a 36% increase in measured ORR activity in comparison to the maximum ORR mass activity value of 22 A/g catalyst in the original dataset. This combined experiment and machine learning approach represents a novel and promising path towards developing highly efficient next generation ORR electrocatalysts and, more generally, functional materials.