Embedded Files
주요 연구분야
물리화학 (Physical Chemistry)
이론화학 (Theoretical Chemistry)
계산화학 (Computational Chemistry)
화학정보학 (Cheminformatics)
화학에서의 딥 러닝 (Deep Learning in Chemistry)
재생에너지 (Renewable Energy)
지속가능성을 위한 화학 (Chemistry for Sustainability)
Research Projects
Research Projects
Development of an AI-Assisted Integrated Biomass Fractionation-Conversion Process Technology Based on Renewable Electrification (2026/4/1 - ) / Korea Ministry of Science and ICT, National Research Foundation in Korea
Leading Research Institution: KRICT
유기 재료 분해 에너지 예측 AI 기술 개발 (2026/2/1 - ) / Samsung Display
Research on technology development for tracking and confirming unknown terrorist substances and predicting their characteristics - 미지테러물질 추적확인 및 특성예측 기술개발 연구 (II) (2025/8 - ) / National Institute of Chemical Safety
Leading Research Institution: Korea Military Academy
Development of on-board reformer and H2/e-fuel dual-fueled engine integrated system with plasma-assisted catalysis and high-efficiency H2/CO2 storage technology (2025/4/1 - ) / Korea Ministry of Science and ICT, National Research Foundation in Korea
Leading Research Institution: Prof. Oh's lab
Research projects supported by the KISTI Supercomputing Center
Designing materials for H2/CO2 storage and catalysts for producing e-fuel by leveraging computational chemistry and machine learning
(2026/1/1 - 2026/12/31)Predicting temperature dependence of thermochemical properties by building computational databases and graph neural networks for NASA7 polynomial parameters (2025/01/01 - 2025/12/31)
Computational design of alternative fuel compounds through chemically-explainable machine-learning model with inductive bias (2024/01/01 - 2024/12/31)
Research Interests
Research Interests
Catalyst Design for Clean Energy
Density functional theory (DFT)-based mechanistic studies of reactions pertinent to homogeneous/ heterogeneous catalysis to produce renewable energy and value-added chemicals
Statistical modeling to predict catalytic activities as a function of chemistry-informed descriptors identified from mechanistic studies
ACS Catalysis, 2020, 10, 14707 | Chem. Eng. J., 2022, 446, 136965 | Small. 2024, Accepted. DOI: 10.1002/smll.202405559
Designing Value-added Chemicals for Clean Energy
De novo design of value-added chemicals using machine learning (ML) predictive models for physicochemical properties
Chemically explainable ML models
Seamless integration of computational and experimental databases to improve ML models for chemistry
Chem. Sci., 2024, 15, 923 | Green Chem., 2024, Accepted. DOI: 10.1039/D4GC01994F | Proc. Combust. Inst. 2023, 39, 4969.
Page updated
Google Sites
Report abuse