DocumentCode
2134093
Title
Estimating of surface spectral values by feed-forward neural networks training with remote-field radiometer data
Author
Gonzalo, Consuelo ; Arquero, Agueda ; Martínez, Estíbaliz
Author_Institution
Dep. de Arquitectura y Tecnologia de Sistemas Informaticos, Univ. Politecnica de Madrid, Spain
Volume
5
fYear
2001
fDate
2001
Firstpage
2361
Abstract
A new method (ES2N2) for estimating surface spectral values based on feed-forward neural networks, has been developed. The neural network has been trained with pairs of remote-field data. Good estimations have been obtained, especially for land covers with low spectral response
Keywords
feedforward neural nets; geophysical signal processing; geophysical techniques; multidimensional signal processing; remote sensing; terrain mapping; vegetation mapping; ES2N2; IR; feed-forward neural network; feedforward neural net; geophysical measurement technique; infrared; land cover; land surface; low spectral reponse; multispectral remote sensing; remote-field radiometer data; surface spectral values; terrain mapping; trained; training; visible; Feedforward neural networks; Feedforward systems; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International
Conference_Location
Sydney, NSW
Print_ISBN
0-7803-7031-7
Type
conf
DOI
10.1109/IGARSS.2001.978002
Filename
978002
Link To Document