Junseok Moon

jsmoon0311@snu.ac.kr

311–315, 1, Gwanak-ro, Gwanak-gu,

Seoul, Republic of Korea

Hello! I am a Ph.D. candidate in Chemical and Biological Engineering at Seoul National University, specializing in the intersection of artificial intelligence and materials science.

My research capability was demonstrated early in my doctoral journey, highlighted by a sole first-author publication in Nature Materials achieved in my second year (submitted during the first).

By synergizing deep learning frameworks with hands-on synthesis and electrochemical characterization, I accelerate the discovery of next-generation solutions—ranging from clean-energy catalysts to bio-inspired materials.

I am deeply committed to translating abstract algorithms into real-world impact for sustainable energy and green hydrogen technologies, while advocating for explainable, human-centered AI.

My ultimate vision is to pioneer automated laboratories where AI, robotics, and scientists collaborate to engineer a sustainable future.

Education

Mar. 2022 – Aug. 2026 (Expected)	Seoul National University (SNU), Seoul, Republic of Korea Ph.D. candidate in Chemical and Biological Engineering Supervisor: Prof. Taeghwan Hyeon (Hyeon Research Group)
Mar. 2017 – Feb. 2022	Seoul National University (SNU), Seoul, Republic of Korea B.S. in Chemical and Biological Engineering

Research Interests

Machine learning-driven materials discovery

Battery, catalysis, biomedical applications, lab automation, and more

Synthesis and characterization of inorganic functional nanomaterials

Metal oxides, halides, alloys, single-atom catalysts, clusters, metal-organic-frameworks, and more

Representative Publications

Nat. Mater.

Active learning guides discovery of a champion four-metal perovskite oxide for oxygen evolution electrocatalysis

Junseok Moon^†, Wiktor Beker, Marta Siek, Jiheon Kim, Hyeon Seok Lee, Taeghwan Hyeon^*, and Bartosz A. Grzybowski^*

Nature Materials, Nov 2023

Abs DOI

Multi-metal oxides in general and perovskite oxides in particular have attracted considerable attention as oxygen evolution electrocatalysts. Although numerous theoretical studies have been undertaken, the most promising perovskite-based catalysts continue to emerge from human-driven experimental campaigns rather than data-driven machine learning protocols, which are often limited by the scarcity of experimental data on which to train the models. This work promises to break this impasse by demonstrating that active learning on even small datasets—but supplemented by informative structural-characterization data and coupled with closed-loop experimentation—can yield materials of outstanding performance. The model we develop not only reproduces several non-obvious and actively studied experimental trends but also identifies a composition of a perovskite oxide electrocatalyst exhibiting an intrinsic overpotential at 10 mA cm^–2_oxide of 391 mV, which is among the lowest known of four-metal perovskite oxides.