inscription
PORTAIL D'INFORMATION GÉOGRAPHIQUE

Derivative-neural spectroscopy for hyperspectral bathymetric inversion

Auteur :
FILIPPI, A.M.

Description :
The aims in this study were to estimate bathymetry based on derivative reflectance spectra used as input to a multilayer perceptron artificial neural network (ANN) and to evaluate the efficacy of field and simulated training/testing data. ANNs were used to invert reflectance field data acquired in optically shallow coastal waters. This study identifies circumstances under which derivative spectra are useful in bathymetry estimation, and thus increases the likelihood of obtaining accurate inversions.


Type de document :
Article de périodique

Source :
The Professional geographer, issn : 0033-0124, 2007, vol. 59, n°. 2, p. 236-255, nombre de pages : 20, Collation : Illustration, Références bibliographiques : 42 ref.

Date :
2007

Editeur :
Pays édition : Etats-Unis, Cambridge, MA, Blackwell

Langue :
Anglais
Droits :
Tous droits réservés © Prodig - Bibliographie Géographique Internationale (BGI)