End-to-End Neural Interpolation of Satellite-Derived Sea Surface Suspended Sediment Concentrations

被引:5
作者
Vient, Jean-Marie [1 ,2 ]
Fablet, Ronan [2 ]
Jourdin, Frederic [3 ]
Delacourt, Christophe [1 ]
机构
[1] UBO, Technopole Brest Iroise, F-29238 Brest, France
[2] IMT Atlantique Bretagne Pays Loire, Technopole Brest Iroise, F-29238 Brest, France
[3] Serv Hydrograph & Oceanograph Marine SHOM, F-29603 Brest, France
关键词
interpolation; data-driven models; neural networks; variational data assimilation; missing data; suspended particulate matter; observing system experiment; Bay of Biscay; CONTINENTAL-SHELF; COASTAL WATERS; BAY; VARIABILITY; PARTICLES; TURBIDITY; MATTER;
D O I
10.3390/rs14164024
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The characterization of suspended sediment dynamics in the coastal ocean provides key information for both scientific studies and operational challenges regarding, among others, turbidity, water transparency and the development of micro-organisms using photosynthesis, which is critical to primary production. Due to the complex interplay between natural and anthropogenic forcings, the understanding and monitoring of the dynamics of suspended sediments remain highly challenging. Numerical models still lack the capabilities to account for the variability depicted by in situ and satellite-derived datasets. Through the ever increasing availability of both in situ and satellite-derived observation data, data-driven schemes have naturally become relevant approaches to complement model-driven ones. Our previous work has stressed this potential within an observing system simulation experiment. Here, we further explore their application to the interpolation of sea surface sediment concentration fields from real gappy satellite-derived observation datasets. We demonstrate that end-to-end deep learning schemes-namely 4DVarNet, which relies on variational data assimilation formulation-apply to the considered real dataset where the training phase cannot rely on gap-free references but only on the available gappy data. 4DVarNet significantly outperforms other data-driven schemes such as optimal interpolation and DINEOF with a relative gain greater than 20% in terms of RMSLE and improves the high spatial resolution of patterns in the reconstruction process. Interestingly, 4DVarNet also shows a better agreement between the interpolation performance assessed for an OSSE and for real data. This result emphasizes the relevance of OSSE settings for future development calibration phases before the applications to real datasets.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Analysis of high frequency geostationary ocean colour data using DINEOF
    Alvera-Azcarate, Aida
    Vanhellemont, Quinten
    Ruddick, Kevin
    Barth, Alexander
    Beckers, Jean-Marie
    [J]. ESTUARINE COASTAL AND SHELF SCIENCE, 2015, 159 : 28 - 36
  • [2] DINCAE 2.0: multivariate convolutional neural network with error estimates to reconstruct sea surface temperature satellite and altimetry observations
    Barth, Alexander
    Alvera-Azcarate, Aida
    Troupin, Charles
    Beckers, Jean-Marie
    [J]. GEOSCIENTIFIC MODEL DEVELOPMENT, 2022, 15 (05) : 2183 - 2196
  • [3] DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations
    Barth, Alexander
    Alvera-Azcarate, Aida
    Licer, Matjaz
    Beckers, Jean-Marie
    [J]. GEOSCIENTIFIC MODEL DEVELOPMENT, 2020, 13 (03) : 1609 - 1622
  • [4] Intercomparison of Data-Driven and Learning-Based Interpolations of Along-Track Nadir and Wide-Swath SWOT Altimetry Observations
    Beauchamp, Maxime
    Fablet, Ronan
    Ubelmann, Clement
    Ballarotta, Maxime
    Chapron, Bertrand
    [J]. REMOTE SENSING, 2020, 12 (22) : 1 - 29
  • [5] Beckers JM, 2003, J ATMOS OCEAN TECH, V20, P1839, DOI 10.1175/1520-0426(2003)020<1839:ECADFF>2.0.CO
  • [6] 2
  • [7] Global Variability of Optical Backscattering by Non-algal particles From a Biogeochemical-Argo Data Set
    Bellacicco, M.
    Cornec, M.
    Organelli, E.
    Brewin, R. J. W.
    Neukermans, G.
    Volpe, G.
    Barbieux, M.
    Poteau, A.
    Schmechtig, C.
    D'Ortenzio, F.
    Marullo, S.
    Claustre, H.
    Pitarch, J.
    [J]. GEOPHYSICAL RESEARCH LETTERS, 2019, 46 (16) : 9767 - 9776
  • [8] Borja A, 2019, WORLD SEAS: AN ENVIRONMENTAL EVALUATION, VOL I: EUROPE, THE AMERICAS AND WEST AFRICA, 2ND EDITION, P113, DOI 10.1016/B978-0-12-805068-2.00006-1
  • [9] Marine management - Towards an integrated implementation of the European Marine Strategy Framework and the Water Framework Directives
    Borja, Angel
    Elliott, Mike
    Carstensen, Jacob
    Heiskanen, Anna-Stiina
    van de Bund, Wouter
    [J]. MARINE POLLUTION BULLETIN, 2010, 60 (12) : 2175 - 2186
  • [10] Relationship between hydrology and seasonal distribution of suspended sediments on the continental shelf of the Bay of Biscay
    Castaing, P
    Froidefond, JM
    Lazure, P
    Weber, O
    Prud'homme, R
    Jouanneau, JM
    [J]. DEEP-SEA RESEARCH PART II-TOPICAL STUDIES IN OCEANOGRAPHY, 1999, 46 (10) : 1979 - 2001