Extraction of Sea Ice Cover by Sentinel-1 SAR Based on Support Vector Machine With Unsupervised Generation of Training Data

In this article, we focus on developing a novel method to extract sea ice cover (i.e., discrimination/classification of sea ice and open water) using Sentinel-1 (S1) cross-polarization [vertical horizontal (VH) or horizontal vertical (HV)] data in extra-wide (EW) swath mode based on the support vector machine (SVM) method. The classification basis includes the S1 radar backscatter and texture features, which are calculated from S1 data using the gray level co-occurrence matrix (GLCM). Different from previous methods where appropriate samples are manually selected to train the SVM to classify sea ice and open water, we proposed a method of unsupervised generation of the training samples based on two GLCM texture features, i.e., entropy and homogeneity, that have contrasting characteristics on sea ice and open water. We eliminate the most uncertainty of selecting training samples in machine learning and achieve automatic classification of sea ice and open water by using S1 EW data. The comparisons based on a few cases show good agreements between the synthetic aperture radar (SAR)-derived sea ice cover using the proposed method and visual inspections, of which the accuracy reaches approximately 90 5. Besides this, compared with the analyzed sea ice cover data Ice Mapping System (IMS) based on 728 S1 EW images, the accuracy of the extracted sea ice cover by using S1 data is more than 80.

Automated summary

This study introduced a novel method to extract sea ice cover using S1 data and the SVM method, achieving automatic classification of sea ice and open water with an accuracy of over 90%. The proposed approach eliminated uncertainties in selecting training samples and showed good agreement with visual inspections in SAR-derived sea ice cover.