Skip to Main content Skip to Navigation
Conference papers

Sea surface temperature prediction and reconstruction using patch-level neural network representations

Said Ouala 1, 2 Cédric Herzet 3 Ronan Fablet 1, 2
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
3 SIMSMART - SIMulation pARTiculaire de Modèles Stochastiques
IRMAR - Institut de Recherche Mathématique de Rennes, Inria Rennes – Bretagne Atlantique
Abstract : The forecasting and reconstruction of ocean and atmosphere dynamics from satellite observation time series are key challenges. While model-driven representations remain the classic approaches, data-driven representations become more and more appealing to benefit from available large-scale observation and simulation datasets. In this work we investigate the relevance of recently introduced bilinear residual neural network representations, which mimic numerical integration schemes such as Runge-Kutta, for the forecasting and assimilation of geophysical fields from satellite-derived remote sensing data. As a case-study, we consider satellite-derived Sea Surface Temperature time series off South Africa, which involves intense and complex upper ocean dynamics. Our numerical experiments demonstrate that the proposed patch-level neural-network-based representations outperform other data-driven models, including analog schemes, both in terms of forecasting and missing data interpolation performance with a relative gain up to 50\% for highly dynamic areas.
Document type :
Conference papers
Complete list of metadatas
Contributor : Said Ouala <>
Submitted on : Thursday, September 27, 2018 - 6:52:24 PM
Last modification on : Wednesday, September 23, 2020 - 9:56:10 AM

Links full text



Said Ouala, Cédric Herzet, Ronan Fablet. Sea surface temperature prediction and reconstruction using patch-level neural network representations. IGARSS 2018 : IEEE International Geoscience and Remote Sensing Symposium, Jul 2018, Valence, Spain. pp.1-4, ⟨10.1109/IGARSS.2018.8519345⟩. ⟨hal-01883209⟩



Record views