IGB

Connexion

(Article of periodic en Anglais - 2007)

Document title

Derivative-neural spectroscopy for hyperspectral bathymetric inversion

Authors(s) and Affiliation(s)

FILIPPI A.M. ;

Abstract

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

Source

Article of periodic

published at : The Professional geographer / ISSN 0033-0124

Editor : Blackwell, Cambridge, MA - ETATS-UNIS (1946)

Millesime : 2007, vol. 59, no2 [pp. 236-255]

Bibliographic references : 42 ref.

Collation : Illustration ;

Language

Anglais

Localisation

Laboratoire INTERGEO - Paris

INIST-CNRS, Cote INIST : 9188

Tous droits réservés © Prodig - Bibliographie Géographique Internationale (BGI), 2007.
Refdoc record number (ud4) : 19027166 : Permanent link - XML version
Powered by Pxxo