RESEARCH
📚 Representative Works
* Staying the mouse over the screen stops the movement
Deep learning-based Arctic melt pond detection
Arctic melt ponds play a significant role in the reduction of sea ice extent and changes in the Arctic climate, and their accurate monitoring is important. However, their observation methods may suffer from reduced accuracy under varying weather conditions. To address this, different approaches capable of providing high-resolution data are needed. ICESat-2 measures surface elevation with high precision, enabling the detection of smaller melt ponds that were previously undetectable by CryoSat-2. Altimetry data can be utilized for polar research regardless of weather conditions, making it a valuable tool for studying the Arctic cryosphere.
In this study, we developed a method to detect Arctic summer melt ponds using ICESat-2 altimetry data. For each ICESat-2 point, we analyzed the standard deviation of elevation and the number of photons within each segment to distinguish between sea ice and melt ponds. Since melt ponds have smoother surfaces than sea ice, they exhibit lower elevation variation and different photon counts, which were used to classify melt ponds covered by water and those covered by ice. The proposed detection method was validated using Sentinel-2 optical imagery and effectively identified various types of melt ponds.
Han et al., 2021
📝 Publications
Last updated : 2026/03/08
Kim, W., Sim, S., Lee, S., Stroeve, J., Han, D., & Im, J. (2025). A novel sea ice floe fragmentation index using Sentinel-2 and AMSR2 satellite data based on machine learning. International Journal of Applied Earth Observation and Geoinformation, 144, 104911.
Kim, Y. J., Kim, H. C., Han, D., Stroeve, J., & Im, J. (2025). Long-term prediction of Arctic sea ice concentrations using deep learning: Effects of surface temperature, radiation, and wind conditions. Remote Sensing of Environment, 318, 114568.
Kim, M., Kim, H. C., Im, J., Lee, S., & Han, H. (2020). Object-based landfast sea ice detection over West Antarctica using time series ALOS PALSAR data. Remote Sensing of Environment, 242, 111782.
Kim, Y. J., Kim, H. C., Han, D., Lee, S., & Im, J. (2020). Prediction of monthly Arctic sea ice concentrations using satellite and reanalysis data based on convolutional neural networks. Cryosphere, 14(3), 1083-1104.
Lee, S., Kim, H. C., & Im, J. (2018). Arctic lead detection using a waveform mixture algorithm from CryoSat-2 data. Cryoshpere, 12(1), 1665-1679.
Han, D., Kim, Y. J., Im, J., Lee, S., Lee, Y., & Kim, H. C. (2018). The estimation of arctic air temperature in summer based on machine learning approaches using IABP buoy and AMSR2 satellite data. Korean Journal of Remote Sensing, 34(6_2), 1261-1272.
Lee, S., Im, J., Kim, J., Kim, M., Shin, M., Kim, H. C., & Quackenbush, L. J. (2016). Arctic sea ice thickness estimation from CryoSat-2 satellite data using machine learning-based lead detection. Remote Sensing, 8(9), 698.
Han, H., Im, J., & Kim, H. C. (2016). Variations in ice velocities of Pine Island Glacier Ice Shelf evaluated using multispectral image matching of Landsat time series data. Remote Sensing of Environment, 186, 358-371.
Han, H., Im, J., Kim, M., Sim, S., Kim, J., Kim, D. J., & Kang, S. H. (2016). Retrieval of melt ponds on arctic multiyear sea ice in summer from terrasar-x dual-polarization data using machine learning approaches: A case study in the chukchi sea with mid-incidence angle data. Remote Sensing, 8(1), 57.
Kim, M., Im, J., Han, H., Kim, J., Lee, S., Shin, M., & Kim, H. C. (2015). Landfast sea ice monitoring using multisensor fusion in the Antarctic. GIScience & Remote Sensing, 52(2), 239-256.