FN Archimer Export Format
PT J
TI Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks
BT 
AF Pauthenet, Etienne
   Bachelot, Loic
   Balem, Kevin
   Maze, Guillaume
   Tréguier, Anne-Marie
   Roquet, Fabien
   Fablet, Ronan
   Tandeo, Pierre
AS 1:1;2:2;3:1;4:1;5:5;6:3;7:4;8:4;
FF 1:PDG-ODE-LOPS-OH;2:PDG-IRSI-ISI;3:PDG-ODE-LOPS-OH;4:PDG-ODE-LOPS-OH;5:;6:;7:;8:;
C1 Ifremer, Univ. Brest, CNRS, IRD, Laboratoire d’Océanographie Physique et Spatiale (LOPS), IUEM, 29280, Plouzané, France
   Ifremer, Univ. Brest, CNRS, IRD, Service Ingénierie des Systèmes d’Information (PDG-IRSI-ISI), IUEM, 29280, Plouzané, France
   Department of Marine Sciences, University of Gothenburg, Gothenburg, Sweden
   IMT Atlantique, CNRS UMR Lab-STICC, Brest, France
   Ifremer, Univ. Brest, CNRS, IRD, Laboratoire d’Océanographie Physique et Spatiale (LOPS), IUEM, 29280, Plouzané, France
C2 IFREMER, FRANCE
   IFREMER, FRANCE
   UNIV GOTHENBURG, SWEDEN
   IMT ATLANTIQUE, FRANCE
   CNRS, FRANCE
SI BREST
SE PDG-ODE-LOPS-OH
   PDG-IRSI-ISI
UM LOPS
IN WOS Ifremer UPR
   WOS Ifremer UMR
   DOAJ
   copubli-france
   copubli-europe
IF 3.2
TC 13
UR https://archimer.ifremer.fr/doc/00759/87125/92621.pdf
   https://archimer.ifremer.fr/doc/00759/87125/95820.pdf
LA English
DT Article
AB Despite the ever-growing amount of ocean’s data, the interior of the ocean remains under sampled in regions of high variability such as the Gulf Stream. In this context, neural networks have been shown to be effective for interpolating properties and understanding ocean processes. We introduce OSnet (Ocean Stratification network), a new ocean reconstruction system aimed at providing a physically consistent analysis of the upper ocean stratification. The proposed scheme is a bootstrapped multilayer perceptron trained to predict simultaneously temperature and salinity (T-S) profiles down to 1000 m and the Mixed Layer Depth (MLD) from surface data covering 1993 to 2019. OSnet is trained to fit sea surface temperature and sea level anomalies onto all historical in-situ profiles in the Gulf Stream region. To achieve vertical coherence of the profiles, the MLD prediction is used to adjust a posteriori the vertical gradients of predicted T-S profiles, thus increasing the accuracy of the solution and removing vertical density inversions. The prediction is generalized on a 1/4◦ daily grid, producing four-dimensional fields of temperature and salinity, with their associated confidence interval issued from the bootstrap. OSnet profiles have root mean square error comparable with the observation-based Armor3D weekly product and the physics-based ocean reanalysis Glorys12. The maximum of uncertainty is located north of the Gulf Stream, between the shelf and the current, where the thermohaline variability is large. The OSnet reconstructed field is coherent even in the pre-ARGO years, demonstrating the good generalization properties of the network. It reproduces the warming trend of surface temperature, the seasonal cycle of surface salinity and mesoscale structures of temperature, salinity and MLD. While OSnet delivers an accurate interpolation of the ocean’s stratification, it is also a tool to study how the interior of the ocean’s behaviour reflects on surface data. We can compute the relative importance of each input for each T-S prediction and analyse how the network learns which surface feature influences most which property and at which depth. Our results are promising and demonstrate the power of machine learning methods to improve the prediction of ocean interior properties from observations of the ocean surface. 
PY 2022
PD AUG
SO Ocean Science
SN 1812-0784
PU European Geosciences Union (EGU)
VL 18
IS 4
UT 000844104000001
BP 1221
EP 1244
DI 10.5194/os-18-1221-2022
ID 87125
ER

EF