Guided deep learning by subaperture decomposition: ocean patterns from SAR imagery

TL;DR

This paper introduces a subaperture decomposition preprocessing technique for SAR imagery that enhances deep learning models' ability to analyze ocean surface patterns, achieving state-of-the-art results.

Contribution

It demonstrates that subaperture decomposition as a data preprocessing step improves deep learning performance on ocean pattern recognition in SAR images.

Findings

Achieved a 0.7 improvement over baseline on TenGeoPSARwv dataset.

Subaperture decomposition increases the number of clusters in unsupervised segmentation.

Data preprocessing significantly enhances deep learning model accuracy.

Abstract

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.