{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T05:34:41Z","timestamp":1772343281401,"version":"3.50.1"},"reference-count":40,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2018,11,22]],"date-time":"2018-11-22T00:00:00Z","timestamp":1542844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>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).<\/jats:p>","DOI":"10.3390\/rs10121864","type":"journal-article","created":{"date-parts":[[2018,11,22]],"date-time":"2018-11-22T09:18:25Z","timestamp":1542878305000},"page":"1864","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Neural Network Based Kalman Filters for the Spatio-Temporal Interpolation of Satellite-Derived Sea Surface Temperature"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0554-3971","authenticated-orcid":false,"given":"Said","family":"Ouala","sequence":"first","affiliation":[{"name":"IMT Atlantique, Lab-STICC, UBL, 29280 Brest, France"}]},{"given":"Ronan","family":"Fablet","sequence":"additional","affiliation":[{"name":"IMT Atlantique, Lab-STICC, UBL, 29280 Brest, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3039-2669","authenticated-orcid":false,"given":"C\u00e9dric","family":"Herzet","sequence":"additional","affiliation":[{"name":"IMT Atlantique, Lab-STICC, UBL, 29280 Brest, France"},{"name":"INRIA Bretagne-Atlantique, SIMSMART, 35042 Rennes, France"}]},{"given":"Bertrand","family":"Chapron","sequence":"additional","affiliation":[{"name":"Ifremer, LOPS, 29280 Brest, France"}]},{"given":"Ananda","family":"Pascual","sequence":"additional","affiliation":[{"name":"IMEDEA, UIB-CSIC, 07190 Esporles, Spain"}]},{"given":"Fabrice","family":"Collard","sequence":"additional","affiliation":[{"name":"ODL, 29280 Brest, France"}]},{"given":"Lucile","family":"Gaultier","sequence":"additional","affiliation":[{"name":"ODL, 29280 Brest, France"}]}],"member":"1968","published-online":{"date-parts":[[2018,11,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.pocean.2003.07.005","article-title":"Relating sardine recruitment in the Northern Benguela to satellite-derived sea surface height using a neural network pattern recognition approach","volume":"59","author":"Richardson","year":"2003","journal-title":"Prog. Oceanogr."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Le Traon, P.Y. (2011). Satellites and operational oceanography. Operational Oceanography in the 21st Century, Springer.","DOI":"10.1007\/978-94-007-0332-2_2"},{"key":"ref_3","first-page":"s235","article-title":"The copernicus marine environment monitoring service ocean state report","volume":"9","author":"Axell","year":"2016","journal-title":"J. Oper. Oceanogr."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2148","DOI":"10.1002\/grl.50324","article-title":"Improvement of coastal and mesoscale observation from space: Application to the northwestern Mediterranean Sea","volume":"40","author":"Escudier","year":"2013","journal-title":"Geophys. Res. Lett."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.rse.2010.10.017","article-title":"The Operational Sea Surface Temperature and Sea Ice Analysis (OSTIA) system","volume":"116","author":"Donlon","year":"2012","journal-title":"Remote Sens. Environ."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1175\/1520-0426(1998)015<0522:AIMMOM>2.0.CO;2","article-title":"An improved mapping method of multisatellite altimeter data","volume":"15","author":"Nadal","year":"1998","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"84","DOI":"10.3389\/fmars.2018.00084","article-title":"A New Global Sea Surface Salinity and Density Dataset From Multivariate Observations (1993\u20132016)","volume":"5","author":"Droghei","year":"2018","journal-title":"Front. Mar. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.rse.2015.04.025","article-title":"Evaluation of different covariance models for the operational interpolation of high resolution satellite Sea Surface Temperature data over the Mediterranean Sea","volume":"164","author":"Nardelli","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"19477","DOI":"10.1029\/2000JC900063","article-title":"Global high-resolution mapping of ocean circulation from TOPEX\/Poseidon and ERS-1 and-2","volume":"105","author":"Ducet","year":"2000","journal-title":"J. Geophys. Res. Oceans"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/S0967-0637(00)00060-1","article-title":"Diagnostic analysis of the 3D ageostrophic circulation from a multivariate spatial interpolation of CTD and ADCP data","volume":"48","author":"Gomis","year":"2001","journal-title":"Deep Sea Res. Part I Oceanogr. Res. Pap."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ping, B., Su, F., and Meng, Y. (2016). An Improved DINEOF Algorithm for Filling Missing Values in Spatio-Temporal Sea Surface Temperature Data. PLoS ONE, 11.","DOI":"10.1371\/journal.pone.0155928"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Olmedo, E., Taupier-Letage, I., Turiel, A., and Alvera-Azc\u00e1rate, A. (2018). Improving SMOS Sea Surface Salinity in the Western Mediterranean Sea through Multivariate and Multifractal Analysis. Remote Sens., 10.","DOI":"10.3390\/rs10030485"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.rse.2016.02.044","article-title":"Analysis of SMOS sea surface salinity data using DINEOF","volume":"180","author":"Barth","year":"2016","journal-title":"Remote Sens. Environ."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1175\/1520-0426(2003)020<1839:ECADFF>2.0.CO;2","article-title":"EOF Calculations and Data Filling from Incomplete Oceanographic Datasets","volume":"20","author":"Beckers","year":"2003","journal-title":"J. Atmos. Ocean. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1111\/j.1751-5823.2003.tb00194.x","article-title":"Sequential Data Assimilation Techniques in Oceanography","volume":"71","author":"Bertino","year":"2007","journal-title":"Int. Stat. Rev."},{"key":"ref_16","first-page":"2991","article-title":"The Met. Office global three-dimensional variational data assimilation scheme","volume":"126","author":"Lorenc","year":"2000","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4410","DOI":"10.1175\/2009MWR2863.1","article-title":"Limitation of One-Dimensional Ocean Models for Coupled Hurricane\u2013Ocean Model Forecasts","volume":"137","author":"Yablonsky","year":"2009","journal-title":"Mon. Weather Rev."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1991","DOI":"10.1002\/qj.699","article-title":"Nonlinear data assimilation in geosciences: An extremely efficient particle filter","volume":"136","year":"2010","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4093","DOI":"10.1175\/MWR-D-16-0441.1","article-title":"The Analog Data Assimilation","volume":"145","author":"Lguensat","year":"2017","journal-title":"Mon. Weather Rev."},{"key":"ref_20","unstructured":"Tandeo, P., Ailliot, P., Chapron, B., Lguensat, R., and Fablet, R. (2015, January 24\u201325). The analog data assimilation: Application to 20 years of altimetric data. Proceedings of the 5th International Workshop on Climate Informatics, Boulder, CO, USA."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Lguensat, R., Huynh Viet, P., Sun, M., Chen, G., Fenglin, T., Chapron, B., and Fablet, R. (2018, November 22). Data-Driven Interpolation of Sea Level Anomalies Using Analog Data Assimilation. Available online: https:\/\/hal.archives-ouvertes.fr\/hal-01609851.","DOI":"10.3390\/rs11070858"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1109\/TCI.2017.2749184","article-title":"Data-Driven Models for the Spatio-Temporal Interpolation of Satellite-Derived SST Fields","volume":"3","author":"Fablet","year":"2017","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1387","DOI":"10.1002\/qj.2204","article-title":"Modelling of local length-scale dynamics and isotropizing deformations","volume":"140","author":"Pannekoucke","year":"2013","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"31547","DOI":"10.3402\/tellusa.v68.31547","article-title":"Parametric Kalman filter for chemical transport models","volume":"68","author":"Pannekoucke","year":"2016","journal-title":"Tellus A Dyn. Meteorol. Oceanogr."},{"key":"ref_25","unstructured":"Rezende, D.J., Mohamed, S., and Wierstra, D. (arXiv, 2014). Stochastic Backpropagation and Approximate Inference in Deep Generative Models, arXiv."},{"key":"ref_26","unstructured":"Matthews, A.G.d.G., Rowland, M., Hron, J., Turner, R.E., and Ghahramani, Z. (arXiv, 2018). Gaussian Process Behaviour in Wide Deep Neural Networks, arXiv."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Fablet, R., Ouala, S., and Herzet, C. (arXiv, 2017). Bilinear residual Neural Network for the identification and forecasting of dynamical systems, arXiv.","DOI":"10.23919\/EUSIPCO.2018.8553492"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2279","DOI":"10.1016\/S0031-3203(01)00178-9","article-title":"Image processing with neural networks\u2014A review","volume":"35","author":"Handels","year":"2002","journal-title":"Pattern Recognit."},{"key":"ref_29","unstructured":"Braakmann-Folgmann, A., Roscher, R., Wenzel, S., Uebbing, B., and Kusche, J. (arXiv, 2017). Sea Level Anomaly Prediction using Recurrent Neural Networks, arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1788","DOI":"10.1016\/j.jhydrol.2015.08.008","article-title":"Neural network river forecasting through baseflow separation and binary-coded swarm optimization","volume":"529","author":"Taormina","year":"2015","journal-title":"J. Hydrol."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Evensen, G. (2009). Data Assimilation, Springer.","DOI":"10.1007\/978-3-642-03711-5"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2741","DOI":"10.1175\/1520-0493(1999)127<2741:AMCIOT>2.0.CO;2","article-title":"A Monte Carlo Implementation of the Nonlinear Filtering Problem to Produce Ensemble Assimilations and Forecasts","volume":"127","author":"Anderson","year":"1999","journal-title":"Mon. Weather Rev."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1175\/1520-0493(1998)126<0796:DAUAEK>2.0.CO;2","article-title":"Data Assimilation Using an Ensemble Kalman Filter Technique","volume":"126","author":"Houtekamer","year":"1998","journal-title":"Mon. Weather Rev."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1002\/qj.49712555417","article-title":"Construction of correlation functions in two and three dimensions","volume":"125","author":"Gaspari","year":"1999","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1175\/1520-0493(2001)129<0123:ASEKFF>2.0.CO;2","article-title":"A Sequential Ensemble Kalman Filter for Atmospheric Data Assimilation","volume":"129","author":"Houtekamer","year":"2001","journal-title":"Mon. Weather Rev."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1002\/qj.2711","article-title":"Localization and the iterative ensemble Kalman smoother","volume":"142","author":"Bocquet","year":"2016","journal-title":"Q. J. R. Meteorol. Soc."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1175\/1520-0493(1993)121<3123:DOSTUF>2.0.CO;2","article-title":"Dynamics of Short-Term Univariate Forecast Error Covariances","volume":"121","author":"Cohn","year":"1993","journal-title":"Mon. Weather Rev."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Forsyth, D.A., Mundy, J.L., di Ges\u00fa, V., and Cipolla, R. (1999). Object Recognition with Gradient-Based Learning. Shape, Contour and Grouping in Computer Vision, Springer. Lecture Notes in Computer Science.","DOI":"10.1007\/3-540-46805-6"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ouala, S., Herzet, C., and Fablet, R. (arXiv, 2018). Sea surface temperature prediction and reconstruction using patch-level neural network representations, arXiv.","DOI":"10.1109\/IGARSS.2018.8519345"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2518","DOI":"10.1109\/TGRS.2017.2750491","article-title":"Improving Mesoscale Altimetric Data From a Multitracer Convolutional Processing of Standard Satellite-Derived Products","volume":"56","author":"Fablet","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/12\/1864\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:31:20Z","timestamp":1760196680000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/10\/12\/1864"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,22]]},"references-count":40,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2018,12]]}},"alternative-id":["rs10121864"],"URL":"https:\/\/doi.org\/10.3390\/rs10121864","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,22]]}}}