FN Archimer Export Format
PT J
TI Neural Network Based Kalman Filters for the Spatio-Temporal Interpolation of Satellite-Derived Sea Surface Temperature
BT 
AF OUALA, Said
   FABLET, Ronan
   HERZET, Cedric
   CHAPRON, Bertrand
   PASCUAL, Ananda
   COLLARD, Fabrice
   GAULTIER, Lucile
AS 1:1;2:1;3:1,2;4:3;5:4;6:5;7:5;
FF 1:;2:;3:;4:PDG-ODE-LOPS-SIAM;5:;6:;7:;
C1 UBL, IMT Atlantique, Lab STICC, F-29280 Brest, France.
   SIMSMART, INRIA Bretagne Atlantique, F-35042 Rennes, France.
   IFREMER, LOPS, F-29280 Brest, France.
   UIB, CSIC, IMEDEA, Esporles 07190, Spain.
   ODL, F-29280 Brest, France.
C2 IMT ATLANTIQUE, FRANCE
   INRIA, FRANCE
   IFREMER, FRANCE
   IMEDEA, SPAIN
   OCEANDATALAB, FRANCE
SI BREST
SE PDG-ODE-LOPS-SIAM
UM LOPS
IN WOS Ifremer jusqu'en 2018
   DOAJ
   copubli-france
   copubli-europe
IF 4.118
TC 21
UR https://archimer.ifremer.fr/doc/00481/59286/61979.pdf
LA English
DT Article
DE ;data assimilation;dynamical model;Kalman filter;neural networks;data-driven models;interpolation
AB The forecasting and reconstruction of oceanic dynamics is a crucial challenge. While model driven strategies are still the state-of-the-art approaches in the reconstruction of spatio-temporal dynamics. The ever increasing availability of data collections in oceanography raised the relevance of data-driven approaches as computationally efficient representations of spatio-temporal fields reconstruction. This tools proved to outperform classical state-of-the-art interpolation techniques such as optimal interpolation and DINEOF in the retrievement of fine scale structures while still been computationally efficient comparing to model based data assimilation schemes. However, coupling this data-driven priors to classical filtering schemes limits their potential representativity. From this point of view, the recent advances in machine learning and especially neural networks and deep learning can provide a new infrastructure for dynamical modeling and interpolation within a data-driven framework. In this work we adress this challenge and develop a novel Neural-Network-based (NN-based) Kalman filter for spatio-temporal interpolation of sea surface dynamics. Based on a data-driven probabilistic representation of spatio-temporal fields, our approach can be regarded as an alternative to classical filtering schemes such as the ensemble Kalman filters (EnKF) in data assimilation. Overall, the key features of the proposed approach are two-fold: (i) we propose a novel architecture for the stochastic representation of two dimensional (2D) geophysical dynamics based on a neural networks, (ii) we derive the associated parametric Kalman-like filtering scheme for a computationally-efficient spatio-temporal interpolation of Sea Surface Temperature (SST) fields. We illustrate the relevance of our contribution for an OSSE (Observing System Simulation Experiment) in a case-study region off South Africa. Our numerical experiments report significant improvements in terms of reconstruction performance compared with operational and state-of-the-art schemes (e.g., optimal interpolation, Empirical Orthogonal Function (EOF) based interpolation and analog data assimilation). 
PY 2018
PD DEC
SO Remote Sensing
SN 2072-4292
PU Mdpi
VL 10
IS 12
UT 000455637600006
DI 10.3390/rs10121864
ID 59286
ER

EF