Ocean dynamics constitute a source of incertitude in determining the ocean's role in complex climatic phenomena. Current observation systems have difficulty achieving sufficiently statistic precision for three-dimensional oceanic data. It is crucial knowledge to describe the behavior of internal ocean structures. We present a data-driven approach that explores latent class regressions and deep neural networks in modeling ocean dynamics in the extensions of Gulf Stream and Kuroshio currents. The obtained results show a promising direction of data-driven for understanding the ocean's characteristics (salinity, temperature) in both spatial and temporal dimensions in the turbulent regions. Our source codes are publicly available at https://github.com/v18nguye/gulfstream-lrm and at https://github.com/sagudelor/Kuroshio.

Video shows how narwhals use their iconic tusks to hunt fish. Filmed near Nunavut, Canada, a narwhal can be seen tapping a fish with its tusk. The unicorn of the sea just got a little less mysterious. Until now, how narwhals used their long tusks had been subject to much speculation by scientists. Behavior captured for the first time on camera shows narwhals using the long tusks protruding from their heads to stun Arctic cod by hitting them, using jagged, quick movements.