TRR181 Seminar Series: "A deep learning approach to extract internal tides....", by Han Wang скачать в хорошем качестве

TRR181 Seminar Series: "A deep learning approach to extract internal tides....", by Han Wang

July 6, 2023 "A deep learning approach to extract internal tides scattered by geostrophic turbulence" by Han Wang (University of Edinburgh) Abstract: Internal tides (ITs) are inertia-gravity waves generated by large-scale oceanic tidal currents flowing over topography, important to oceanographers due to their roles in problems such as deep/upper ocean mixing. Conventionally, for altimetric observations of Sea Surface Height (SSH) data, ITs have been extracted by harmonically fitting over observed time sequences. However, in presence of strong time-dependent phase shifts induced by interactions with mean flows or changes in stratifications, harmonic fits do not work well for data with coarse temporal sampling. Such problem would be exacerbated in the upcoming Surface Water Ocean Topography (SWOT) satellite mission due to the finer spatial scales to be resolved. However, SWOT’s wide swaths will un-precedentedly produce SSH snapshots that are spatially two-dimensional, which allows the community to treat tidal extraction as an operation on two-dimensional images. Here, we regard tidal extraction purely as an image translation problem. We design and train what we call ”Toronto Internal Tide Emulator” (TITE), a conditional Generative Adversarial Network, which, given a snapshot of raw SSH, generates a snapshot of the embedded tidal component. The presentation will introduce a recent work (see (Wang et al., 2021)) where we train and test TITE on a set of idealized numerical eddying simulation . No temporal information or physical knowledge is required for TITE to work in this scenario. We test TITE on data whose dynamical regimes are different from the data provided during training. Despite the diversity and complexity of data, it accurately extracts tidal components in most individual snapshots considered and reproduces physically meaningful statistical properties. Predictably, TITE’s performance decreases with the intensity of the turbulent flow. Ongoing work where we simplify and improve the algorithm will be discussed too.