Dataset Information

Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence.

ABSTRACT: Mesoscale eddies have strong signatures in sea surface height (SSH) anomalies that are measured globally through satellite altimetry. However, monitoring the transport of heat associated with these eddies and its impact on the global ocean circulation remains difficult as it requires simultaneous observations of upper-ocean velocity fields and interior temperature and density properties. Here we demonstrate that for quasigeostrophic baroclinic turbulence the eddy patterns in SSH snapshots alone contain sufficient information to estimate the eddy heat fluxes. We use simulations of baroclinic turbulence for the supervised learning of a deep Convolutional Neural Network (CNN) to predict up to 64% of eddy heat flux variance. CNNs also significantly outperform other conventional data-driven techniques. Our results suggest that deep CNNs could provide an effective pathway towards an operational monitoring of eddy heat fluxes using satellite altimetry and other remote sensing products.

SUBMITTER: George TM

PROVIDER: S-EPMC7865057 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence.

George Tom M TM Manucharyan Georgy E GE Thompson Andrew F AF

Nature communications 20210205 1

Mesoscale eddies have strong signatures in sea surface height (SSH) anomalies that are measured globally through satellite altimetry. However, monitoring the transport of heat associated with these eddies and its impact on the global ocean circulation remains difficult as it requires simultaneous observations of upper-ocean velocity fields and interior temperature and density properties. Here we demonstrate that for quasigeostrophic baroclinic turbulence the eddy patterns in SSH snapshots alone ...[more]

PMID: 33547299

Similar Datasets

Project description:It is widely recognized that the mesoscale eddies play an important part in the biogeochemical cycle in ocean ecosystem, especially in the oligotrophic tropical zones. So here a heterogeneous cyclonic eddy in its flourishing stage was detected using remote sensing and in situ biogeochemical observation in the western South China Sea (SCS) in early September, 2007. The high-performance liquid chromatography method was used to identify the photosynthetic pigments. And the CHEMical TAXonomy (CHEMTAX) was applied to calculate the contribution of nine phytoplankton groups to the total chlorophyll a (TChl a) biomass. The deep chlorophyll a maximum layer (DCML) was raised to form a dome structure in the eddy center while there was no distinct enhancement for TChl a biomass. The integrated TChl a concentration in the upper 100 m water column was also constant from the eddy center to the surrounding water outside the eddy. However the TChl a biomass in the surface layer (at 5 m) in the eddy center was promoted 2.6-fold compared to the biomass outside the eddy (p < 0.001). Thus, the slight enhancement of TChl a biomass of euphotic zone integration within the eddy was mainly from the phytoplankton in the upper mixed zone rather than the DCML. The phytoplankton community was primarily contributed by diatoms, prasinophytes, and Synechococcus at the DCML within the eddy, while less was contributed by haptophytes_8 and Prochlorococcus. The TChl a biomass for most of the phytoplankton groups increased at the surface layer in the eddy center under the effect of nutrient pumping. The doming isopycnal within the eddy supplied nutrients gently into the upper mixing layer, and there was remarkable enhancement in phytoplankton biomass at the surface layer with 10.5% TChl a biomass of water column in eddy center and 3.7% at reference stations. So the slight increasing in the water column integrated phytoplankton biomass might be attributed to the stimulated phytoplankton biomass at the surface layer.

Dataset Information

Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence.

Publications

Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets