Guided deep learning by subaperture decomposition: ocean patterns from SAR imagery
This work addresses the need for efficient data processing in oceanographic applications using SAR imagery, though it is incremental as it focuses on enhancing existing deep learning models through improved preprocessing.
The study tackled the challenge of automatically processing and extracting geophysical parameters from Sentinel 1 SAR ocean imagery by proposing subaperture decomposition as a preprocessing stage for deep learning models, resulting in a 0.7 improvement over the baseline and achieving state-of-the-art performance on the TenGeoPSARwv dataset.
Spaceborne synthetic aperture radar can provide meters scale images of the ocean surface roughness day or night in nearly all weather conditions. This makes it a unique asset for many geophysical applications. Sentinel 1 SAR wave mode vignettes have made possible to capture many important oceanic and atmospheric phenomena since 2014. However, considering the amount of data provided, expanding applications requires a strategy to automatically process and extract geophysical parameters. In this study, we propose to apply subaperture decomposition as a preprocessing stage for SAR deep learning models. Our data centring approach surpassed the baseline by 0.7, obtaining state of the art on the TenGeoPSARwv data set. In addition, we empirically showed that subaperture decomposition could bring additional information over the original vignette, by rising the number of clusters for an unsupervised segmentation method. Overall, we encourage the development of data centring approaches, showing that, data preprocessing could bring significant performance improvements over existing deep learning models.