Centre de documentation
scientifique

Super-resolution of VIIRS-measured ocean color products using deep convolutional neural network / Xiaoming Liu in IEEE Transactions on geoscience and remote sensing, vol 59 n° 1 (January 2021)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 59 n° 1 (January 2021) . - pp 114 - 127 Titre : Super-resolution of VIIRS-measured ocean color products using deep convolutional neural network Type de document : Article/Communication Auteurs : Xiaoming Liu, Auteur ; Menghua Wang, Auteur Année de publication : 2021 Article en page(s) : pp 114 - 127 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse spectrale [Termes IGN] apprentissage profond [Termes IGN] bande infrarouge [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] couleur de l'océan [Termes IGN] image infrarouge couleur [Termes IGN] image multibande [Termes IGN] image NPP-VIIRS [Termes IGN] rayonnement Résumé : (auteur) Since its launch in October 2011, the Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (SNPP) satellite has provided high quality global ocean color products, which include normalized water-leaving radiance spectra nLw ( λ ) of six moderate (M) bands (M1–M6) at the wavelengths of 410, 443, 486, 551, 671, and 745 nm with a spatial resolution of 750-m, and one imagery (I) band at a wavelength of 638 nm with a spatial resolution of 375-m. Because the high-resolution I-band measurements are highly correlated spectrally to those of M-band data, it can be used as a guidance to super-resolve the M-band nLw ( λ ) imagery from 750- to 375-m spatial resolution. Super-resolving images from coarse spatial resolution to finer ones have been a field of very active research in recent years. However, no previous studies have been applied to satellite ocean color remote sensing, in particular, for VIIRS ocean color applications. In this study, we employ the deep convolutional neural network (CNN) technique to glean the high-frequency content from the VIIRS I1 band and transfer to super-resolved M-band ocean color images. The network is trained to super-resolve each of the VIIRS six M-bands nLw ( λ ) separately. In our results, the super-resolved (375-m) nLw ( λ ) images are much sharper and show finer spatial structures than the original images. Quantitative evaluations show that biases between the super-resolved and original nLw ( λ ) images are small for all bands. However, errors in the super-resolved nLw ( λ ) images are wavelength-dependent. The smallest error is found in the super-resolved nLw (551) and nLw (671) images, and error increases as the wavelength decreases from 486 to 410 nm. The results show that the networks have the capability to capture the correlations of the M-band and the I1 band images to super-resolved M-band images. Numéro de notice : A2021-031 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2992912 Date de publication en ligne : 20/05/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2992912 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96726 [article]