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

Date

2023

Authors

Yang, Kun
Li, Haiyan
Perrie, William
Scharien, Randall Kenneth
Wu, Jin
Zhang, Menghao
Xu, Fan

Journal Title

Journal ISSN

Volume Title

Publisher

Remote Sensing

Abstract

A new method of sea ice classification based on feature selection from Gaofen-3 polarimetric Synthetic Aperture Radar (SAR) observations was proposed. The new approach classifies sea ice into four categories: open water (OW), new ice (NI), young ice (YI), and first-year ice (FYI). Seventy parameters that have previously been applied to sea ice studies were re-examined for sea ice classification in the Okhotsk Sea near the melting point on 28 February 2020. The ‘separability index (SI)’ was used for the selection of optimal features for sea ice classification. Full polarization parameters (the backscatter intensity contains the horizontal transmit-receive intensity (σ⁰ₕₕ), Shannon entropy (SEᵢ), the spherical scattering component of Krogager decomposition (Kₛ)), and hybrid polarization parameters (horizontal receive intensity(σ⁰ᵣₕ), hybrid-pol Shannon entropy (CPSEᵢ), the correlation coefficient (pᵣₕ−ᵣᵥ) between the σ⁰ᵣᵥ and σ⁰ᵣₕ, and the surface scattering component of m − α decomposition (αₛ)) were determined as the optimal parameters for the different work modes of SAR. The selected parameters were used to classify sea ice by the random forest classifier (RFC), and classification results were validated by manually interpreted ice maps derived from Landsat-8 data. The classification accuracy of OW, NI, YI and FYI reached 95%, 96%, 98% and 85%, respectively.

Description

Keywords

fine sea ice classification, random forest classifier, polarization SAR, Gaofen-3, feature selection

Citation

Yang, K., Li, H., Perrie, W., Scharien, R. K., Wu, J., Zhang, M., & Xu, F. (2023). Fine resolution classification of new ice, young ice, and first-year ice based on feature selection from Gaofen-3 quad-polarization SAR. Remote Sensing, 15(9), 2399. https://doi.org/10.3390/rs15092399