PRISM
ENKO

Earth Observation AI

We train deep learning models on satellite and radar data to monitor and forecast the atmosphere, oceans, polar regions, and farmland.

Arctic sea ice concentration maps: observed, random forest, and CNN prediction
Kim et al. (2020), The Cryosphere, CC BY 4.0
Radar rainfall nowcasts over South Korea from several deep learning models next to the radar observation
Han et al. (2023), Geoscientific Model Development, CC BY 4.0

Topics

  • Precipitation nowcasting and flood analysis
  • Sea surface temperature and salinity reconstruction
  • Arctic sea ice prediction
  • Crop monitoring with radar

Team

  • Daehyeon Han (PI)
  • Geonwoo Lee
  • Amin

Selected papers

  • Exploring the potential of machine learning post-processing to generate ERA5-consistent atmospheric profiles from geostationary satellite retrievals

    D. Han, M. Choo, S. Jung, J. Lee, H. Choi, J. Im

    Remote Sensing 18(14), 2310, 2026

  • CARE-SST: Context-aware reconstruction diffusion model for sea surface temperature

    M. Choo, S. Jung, J. Im, D. Han

    ISPRS Journal of Photogrammetry and Remote Sensing 220, 454–472, 2025

  • Precipitation nowcasting using ground radar data and simpler yet better video prediction deep learning

    D. Han, M. Choo, J. Im, Y. Shin, J. Lee, S. Jung

    GIScience & Remote Sensing 60(1), 2203363, 2023

All publications →