Synergy between Observation Systems Oceanic in Turbulent Regions
This research aims to improve the understanding of internal ocean structures for climate scientists by providing more precise 3D oceanic data in turbulent regions, which is an incremental step towards better climate modeling.
This paper addresses the challenge of precisely determining 3D oceanic data in turbulent regions by modeling ocean dynamics in the Gulf Stream and Kuroshio currents. It utilizes latent class regressions and deep regression neural networks to understand ocean characteristics like salinity and temperature across spatial and temporal dimensions.
Ocean dynamics constitute a source of incertitude in determining the ocean's role in complex climatic phenomena. Current observation systems have limitations in achieving sufficiently statistical precision for three-dimensional oceanic data. It is crucial knowledge to describe the behavior of internal ocean structures. We present the data-driven approaches which explore latent class regressions and deep regression neural networks in modeling ocean dynamics in the extensions of Gulf Stream and Kuroshio currents. The obtained results show a promising data-driven direction for understanding the ocean's characteristics, including salinity and 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.