[en] A neural network with the architecture of a convolutional autoencoder is used to reconstruct missing data in satellite images of the Southern North Sea. The technique is applied to a multi-satellite data product of chlorophyll-a and total suspended particulate matter (SPM) concentration (representing 20 years of data). The presence of clouds significantly reduces the extent of the ocean that can be measured by satellite sensors using the visible or infrared spectrum. The accuracy of the reconstruction is assessed using cross-validation (i.e. increasing the actual extent of the cloud coverage). The results of the neural network compare favourably the data withheld for cross-validation.
Research Center/Unit :
FOCUS - Freshwater and OCeanic science Unit of reSearch - ULiège
Disciplines :
Earth sciences & physical geography
Author, co-author :
Barth, Alexander ; Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > GeoHydrodynamics and Environment Research (GHER)
Alvera Azcarate, Aida ; Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > GeoHydrodynamics and Environment Research (GHER)
Troupin, Charles ; Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > GeoHydrodynamics and Environment Research (GHER)
Beckers, Jean-Marie ; Université de Liège - ULiège > Département d'astrophys., géophysique et océanographie (AGO) > GeoHydrodynamics and Environment Research (GHER)
Van der Zande, Dimitry; RBINS
Language :
English
Title :
Reconstruction of missing data in satellite images of the Southern North Sea using a convolutional neural network (DINCAE)
Publication date :
2021
Event name :
2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Event date :
from 2021-07-12 to 2021-07-16
Audience :
International
Main work title :
2021 IGARSS: IEEE International Geoscience & Remote Sensing Symposium. Proceedings : July 12-16, 2021, Brussels (Belgium)
Peer reviewed :
Peer reviewed
Tags :
CÉCI : Consortium des Équipements de Calcul Intensif
Name of the research project :
MultiSync
Funders :
BELSPO - Politique scientifique fédérale F.R.S.-FNRS - Fonds de la Recherche Scientifique
D. Wylie, D. L. Jackson, W. P. Menzel, and J. J. Bates, “Trends in Global Cloud Cover in Two Decades of HIRS Observations,” Journal of Climate, vol. 18, no. 15, pp. 3021-3031, 2005.
B. Buongiorno Nardelli, S. Colella, R. Santoleri, M. Guarracino, and A. Kholod, “A re-analysis of black sea surface temperature,” Journal of Marine Systems, vol. 79, no. 1-2, pp. 50-64, 2010.
A. Alvera-Azcárate, Q. Vanhellemont, K. Ruddick, A. Barth, and J.-M. Beckers, “Analysis of high frequency geostationary ocean colour data using DINEOF,” Estuarine, Coastal and Shelf Science, vol. 159, pp. 28 - 36, 2015.
D. Van der Zande, H. Lavigne, A. Blauw, T. Prins, X. Desmit, M. Eleveld, F. Gohin, S. Pardo, G. Tilstone, and J. F. Cardoso Dos Santos, “Enhance coherence in eutrophication assessments based on chlorophyll, using satellite data as part of the EU project 'Joint monitoring programme of the eutrophication of the North Sea with satellite data',” Tech. Rep., Royal Belgian Institute of Natural Sciences, 2019, Activity 2 Report, 106 pp.
H. Lavigne, D. Van der Zande, K. Ruddick, J. F. Cardoso Dos Santos, F. Gohin, V. Brotas, and S. Kratzer, “Quality-control tests for OC4, OC5 and NIR-red satellite chlorophyll-a algorithms applied to coastal waters,” Remote Sensing of Environment, 2021, In press.
B. Nechad, K. Ruddick, and Y. Park, “Calibration and validation of a generic multisensor algorithm for mapping of total suspended matter in turbid waters,” Remote Sensing of Environment, vol. 114, no. 4, pp. 854 - 866, 2010.
A. Alvera-Azcárate, D. Van der Zande, A. Barth, C. Troupin, S. Martin, and J.-M. Beckers, “Analysis of 23 years of daily cloud-free chlorophyll and suspended particulate matter in the Greater North Sea,” Frontiers in Marine Science, 2021, submitted.
A. Alvera-Azcárate, A. Barth, C. Troupin, J.-M. Beckers, and D. V. der Zande, “Creation of high resolution suspended particulate matter data in the North Sea from Sentinel-2 and Sentinel-3 data,” in IEEE International Symposium on Geoscience and Remote Sensing IGARSS. 2021, p. 4, IEEE, submitted.
A. Barth, A. Alvera-Azcárate, M. Licer, and J.-M. Beckers, “DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations,” Geoscientific Model Development, vol. 13, no. 3, pp. 1609-1622, 2020.
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, “Going deeper with convolutions,” in Computer Vision and Pattern Recognition (CVPR), 2015.
J. Bezanson, A. Edelman, S. Karpinski, and V. B. Shah, “Julia: A fresh approach to numerical computing,” SIAM review, vol. 59, no. 1, pp. 65-98, 2017.
D. Yuret, “Knet: beginning deep learning with 100 lines of julia,” in Machine Learning Systems Workshop at NIPS, 2016.
