A Deep Learning Approach to Extract Internal Tides Scattered by Geostrophic Turbulence
Han Wang, Nicolas Grisouard, Hesam Salehipour, Alice Nuz, M.C. Poon, Aurélien Ponte
Abstract
Abstract Extraction of internal tidal (IT) signals is central to the interpretation of Sea Surface Height (SSH) data. The increased spatial resolution of future wide‐swath satellite missions poses a challenge for traditional harmonic analysis, due to prominent and unsteady wave‐mean interactions at finer scales. However, the wide swaths will also produce spatially two‐dimensional SSH snapshots which allows us to treat IT extraction as an image translation problem for the first time. We design and train TITE (Toronto Internal Tide Emulator), a conditional Generative Adversarial Network, which, given a snapshot of raw SSH from an idealized eddying simulation, generates a snapshot of the embedded IT component. We test it on data whose dynamical regimes are different from the data provided during training. Despite the diversity and complexity of data, it accurately extracts ITs in most individual snapshots considered and reproduces physically meaningful statistical properties. Predictably, TITE's performance decreases with the intensity of the turbulent flow.