Filtering Internal Tides From Wide-Swath Altimeter Data Using Convolutional Neural Networks
This work addresses a crucial filtering challenge for physical oceanographers using SWOT data, though it is incremental as it applies existing ConvNet methods to a new domain-specific task.
The paper tackles the problem of filtering internal tides from high-resolution sea surface height data for the SWOT satellite mission by using convolutional neural networks, achieving a significant reduction in internal wave imprint even in unseen regions.
The upcoming Surface Water Ocean Topography (SWOT) satellite altimetry mission is expected to yield two-dimensional high-resolution measurements of Sea Surface Height (SSH), thus allowing for a better characterization of the mesoscale and submesoscale eddy field. However, to fulfill the promises of this mission, filtering the tidal component of the SSH measurements is necessary. This challenging problem is crucial since the posterior studies done by physical oceanographers using SWOT data will depend heavily on the selected filtering schemes. In this paper, we cast this problem into a supervised learning framework and propose the use of convolutional neural networks (ConvNets) to estimate fields free of internal tide signals. Numerical experiments based on an advanced North Atlantic simulation of the ocean circulation (eNATL60) show that our ConvNet considerably reduces the imprint of the internal waves in SSH data even in regions unseen by the neural network. We also investigate the relevance of considering additional data from other sea surface variables such as sea surface temperature (SST).