Machine learning filters out efficient electrocatalysts in the massive ternary alloy space for fuel cells

Youngtae Park, Chang Kyu Hwang, Kihoon Bang, Doosun Hong, Hyobin Nam, Soonho Kwon, Byung Chul Yeo, Dohyun Go, Jihwan An, Byeong Kwon Ju, Sang Hoon Kim, Ji Young Byun, Seung Yong Lee, Jong Min Kim, Donghun Kim, Sang Soo Han, Hyuck Mo Lee

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


Despite their potential promise, multicomponent materials have not been actively considered as catalyst materials to date, mainly due to the massive compositional space. Here, targeting ternary electrocatalysts for fuel cells, we present a machine learning (ML)-driven catalyst screening protocol with the criteria of structural stability, catalytic performance, and cost-effectiveness. This process filters out only 10 and 37 candidates out of over three thousand test materials in the alloy core@shell (X3Y@Z) for each cathode and anode of fuel cells. These candidates are potentially synthesizable, lower-cost and higher-performance than conventional Pt. A thin film of Cu3Au@Pt, one of the final candidates for oxygen reduction reactions, was experimentally fabricated, which indeed outperformed a Pt film as confirmed by the approximately 2-fold increase in kinetic current density with the 2.7-fold reduction in the Pt usage. This demonstration supports that our ML-driven design strategy would be useful for exploring general multicomponent systems and catalysis problems.

Original languageEnglish
Article number123128
JournalApplied Catalysis B: Environmental
Publication statusPublished - 2023 Dec 15

Bibliographical note

Publisher Copyright:
© 2023 Elsevier B.V.


  • Catalyst design protocol
  • Electrocatalyst
  • Fuel cells
  • Machine learning
  • Ternary alloy

ASJC Scopus subject areas

  • Catalysis
  • General Environmental Science
  • Process Chemistry and Technology


Dive into the research topics of 'Machine learning filters out efficient electrocatalysts in the massive ternary alloy space for fuel cells'. Together they form a unique fingerprint.

Cite this