An ensemble learning method to retrieve sea ice roughness from Sentinel-1 SAR images

• Published in: Acta oceanologica Sinica Vol. 43; no. 5; pp. 78 - 90
• Main Authors: Chen, Pengyi, Chen, Zhongbiao, Sun, Runxia, He, Yijun
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2024; Springer Nature B.V
• Subjects: Airborne radar; Climatology; Continuous wavelet transform; Earth and Environmental Science; Earth Sciences; Ecology; Energy transfer; Engineering Fluid Dynamics; Ensemble learning; Environmental Chemistry; Error analysis; Information processing; Information retrieval; Learning curves; Machine learning; Marine & Freshwater Sciences; Oceanography; Radar; Radar backscatter; Radar imaging; Regression models; SAR (radar); Sea ice; Spatial data; Spatial discrimination learning; Spatial resolution; Surface roughness; Synthetic aperture radar; Teaching methods; Transfer learning; Wavelet transforms; 2-D Cauchy continuous wavelet transform (CWT); sea ice surface roughness; Adaboost Regression; sea ice
• ISSN: 0253-505X; 1869-1099
• DOI: 10.1007/s13131-023-2248-9

Sea ice surface roughness (SIR) affects the energy transfer between the atmosphere and the ocean, and it is also an important indicator for sea ice characteristics. To obtain a small-scale SIR with high spatial resolution, a novel method is proposed to retrieve SIR from Sentinel-1 synthetic aperture radar (SAR) images, utilizing an ensemble learning method. Firstly, the two-dimensional continuous wavelet transform is applied to obtain the spatial information of sea ice, including the scale and direction of ice patterns. Secondly, a model is developed using the Adaboost Regression model to establish a relationship among SIR, radar backscatter and the spatial information of sea ice. The proposed method is validated by using the SIR retrieved from SAR images and comparing it to the measurements obtained by the Airborne Topographic Mapper (ATM) in the summer Beaufort Sea. The determination of coefficient, mean absolute error, root-mean-square error and mean absolute percentage error of the testing data are 0.91, 1.71 cm, 2.82 cm, and 36.37%, respectively, which are reasonable. Moreover, K-fold cross-validation and learning curves are analyzed, which also demonstrate the method’s applicability in retrieving SIR from SAR images.