EGU24-2666, updated on 08 Mar 2024
https://doi.org/10.5194/egusphere-egu24-2666
EGU General Assembly 2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Fine resolution classification of new ice, young ice, and first-year ice based on feature selection from Gaofen-3 quad-polarization SAR

Haiyan Li and Kun Yang
Haiyan Li and Kun Yang
  • University of Chinese Academy of Sciences, College of Earth and Planetery Sciences, BeiJing, China (lihaiyan@ucas.ac.cn)

Sea ice in the high latitude is an indicator of climate change and has undergone dramatic changes because of recent global warming. Synthetic aperture radar (SAR) is a relatively practical tool for sea ice monitoring because of its low sensitivity to clouds, rain, and fog, as well as its capability for high-resolution earth observation in daylight or darkness. With the progression in SAR systems from single-pol to dual-pol, quad-pol and hybrid-pol, large numbers of parameters have been proposed for sea ice classification. Even though a large number of SAR characteristics have been used to classify sea ice, it remains unclear which parameters are the most effective for different regions and seasonal or environmental conditions. Meanwhile, classification studies for fine sea ice with high spatial resolution and many sub-types of sea ice, particularly in the case of rapidly changing first-year ice (FYI), which includes new ice (NI), young ice (YI), and FYI, are rather few. NI and YI have comparatively thinner thickness, and are often classified as FYI in these studies[1].

A new method of sea ice classification based on feature selection from Gaofen-3 polarimetric SAR observations is proposed. The new approach classifies sea ice into four categories: open water, NI, YI, and FYI. Seventy parameters that have previously been applied to sea ice studies are re-examined for sea ice classification in the Okhotsk Sea near the melting point on 28 February 2020. The ‘separability index’ is used for the selection of optimal features for sea ice classification. Full polarization (σohh, SEi, Ks) and hybrid polarization parameters (σorl, CPSEirh-rv, αs) are determined as optimal. The selected parameters are used to classify NI, YI, and FYI using a SVM machine learning classifier; and classification results are validated by manually interpreted ice maps derived from Landsat-8 data.

 


[1]Sea ice: types and forms - Canada.ca

How to cite: Li, H. and Yang, K.: Fine resolution classification of new ice, young ice, and first-year ice based on feature selection from Gaofen-3 quad-polarization SAR, EGU General Assembly 2024, Vienna, Austria, 14–19 Apr 2024, EGU24-2666, https://doi.org/10.5194/egusphere-egu24-2666, 2024.

Supplementary materials

Supplementary material file

Comments on the supplementary material

AC: Author Comment | CC: Community Comment | Report abuse

supplementary materials version 1 – uploaded on 16 Apr 2024, no comments

Post a comment