Article Dans Une Revue Optics Express Année : 2020

Accurate deep-learning estimation of chlorophyll-a concentration from the spectral particulate beam-attenuation coefficient

Sebastian Graban
  • Fonction : Auteur
  • PersonId : 1219163
Giorgio Dall’olmo
Stephen Goult
  • Fonction : Auteur

Résumé

Different techniques exist for determining chlorophyll-a concentration as a proxy of phytoplankton abundance. In this study, a novel method based on the spectral particulate beam-attenuation coefficient (c p) was developed to estimate chlorophyll-a concentrations in oceanic waters. A multi-layer perceptron deep neural network was trained to exploit the spectral features present in c p around the chlorophyll-a absorption peak in the red spectral region. Results show that the model was successful at accurately retrieving chlorophyll-a concentrations using c p in three red spectral bands, irrespective of time or location and over a wide range of chlorophyll-a concentrations.

Domaines

Fichier principal
Vignette du fichier
oe-28-16-24214.pdf (1.87 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte
Licence

Dates et versions

hal-03954535 , version 1 (18-12-2023)

Licence

Identifiants

Citer

Sebastian Graban, Giorgio Dall’olmo, Stephen Goult, Raphaëlle Sauzède. Accurate deep-learning estimation of chlorophyll-a concentration from the spectral particulate beam-attenuation coefficient. Optics Express, 2020, 28 (16), pp.24214-24228. ⟨10.1364/oe.397863⟩. ⟨hal-03954535⟩
129 Consultations
122 Téléchargements

Altmetric

Partager

  • More