Four-dimensional temperature, salinity and mixed-layer depth in the Gulf Stream, reconstructed from remote-sensing and in situ observations with neural networks
-
Published:2022-08-25
Issue:4
Volume:18
Page:1221-1244
-
ISSN:1812-0792
-
Container-title:Ocean Science
-
language:en
-
Short-container-title:Ocean Sci.
Author:
Pauthenet EtienneORCID, Bachelot Loïc, Balem Kevin, Maze GuillaumeORCID, Tréguier Anne-MarieORCID, Roquet FabienORCID, Fablet RonanORCID, Tandeo PierreORCID
Abstract
Abstract. Despite the ever-growing number of ocean data, the interior of the ocean remains undersampled 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 lowest confidence in the prediction 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 stratification, it is also a tool to study how the ocean stratification relates to 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 demonstrate the potential of machine learning methods to improve predictions of ocean interior properties from observations of the ocean surface.
Publisher
Copernicus GmbH
Subject
Cell Biology,Developmental Biology,Embryology,Anatomy
Reference98 articles.
1. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M.,
Ghemawat, S., Irving, G., and Isard, M.: Tensorflow: A system for large-scale
machine learning, in: 12th {USENIX} symposium on operating systems
design and implementation ({OSDI} 16), Savannah, GA, USA, 2–4 November 2016,
265–283, ISBN 978-1-931971-33-1, 2016. a 2. Argo: Argo float data and metadata from Global Data Assembly Centre (Argo
GDAC), SEANOE [data set], https://doi.org/10.17882/42182, 2022. a 3. Boutin, J., Reul, N., Köhler, J., Martin, A., Catany, R., Guimbard, S.,
Rouffi, F., Vergely, J.-L., Arias, M., and Chakroun, M.: Satellite‐Based
Sea Surface Salinity Designed for Ocean and Climate Studies, J.
Geophys. Res.-Oceans, 126, e2021JC017676, https://doi.org/10.1029/2021JC017676, 2021. a, b, c, d, e 4. Boutin, J., Vergely, J.-L., Reul, N., Catany, R., Koehler, J., Martin, A., Rouffi, F., Arias, M., Chakroun, M., Corato, G., Estella-Perez, V., Guimbard, S., Hasson, A., Josey, S., Khvorostyanov, D., Kolodziejczyk, N., Mignot, J., Olivier, L., Reverdin, G., Stammer, D., Supply, A., Thouvenin-Masson, C., Turiel, A., Vialard, J., Cipollini, P., and Donlon, C.:
ESA Sea Surface Salinity Climate Change Initiative (Sea_Surface_Salinity_cci): weekly and monthly sea surface salinity products, v2.31, for 2010 to 2019, Centre for Environmental Data Analysis, [data set],
https://doi.org/10.5285/4ce685bff631459fb2a30faa699f3fc5, last access: 27 June 2022. a 5. Breiman, L.: Bagging predictors, Mach. Learn., 24, 123–140,
https://doi.org/10.1007/BF00058655, 1996. a
Cited by
15 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|