Recent advances in the data-driven development of emerging electrocatalysts

Data-driven strategies have proven efficient for the design of high-performance electrocatalysts in the vast material search space. In this review, we present an overview of data-driven approaches to emerging electrocatalyst design: high-throughput experiments, high-throughput calculations, and machine learning. High-throughput experiments facilitate rapid synthesis and characterization of electrocatalysts, leading to efficient exploration of various materials. High-throughput calculations predict and screen materials' properties, allowing for the identification of promising electrocatalysts. The integration of machine learning further augments these high-throughput approaches through critical insight extracted from the large dataset, fast prediction of materials’ performance, and optimization of material discovery. Employing these data-driven strategies synergistically could accelerate the development of electrocatalysts. Such advancements could promote green energy technologies and substantially contribute to mitigating the grand challenges posed by global climate change.