Sharpened mapping of tropical forest biophysical properties from coarse spatial resolution satellite sensor data
Sharpened mapping of tropical forest biophysical properties from coarse spatial resolution satellite sensor data
Forest biophysical properties are typically estimated and mapped from remotely sensed data through the application of a vegetation index. This generally does not make full use of the information content of the remotely sensed data, using only the data acquired in a limited number of spectral channels, and may provide a relatively crude spatial representation of the biophysical variable of interest. Using imagery acquired by the NOAA AVHRR, it is shown that a standard neural network may use all the spectral channels available in a remotely sensed data set to derive more accurate estimates of the biophysical properties of tropical forests in Ghana than a series of vegetation indices. Additionally, the spatial representation derived can be refined by fusion with finer spatial resolution imagery, achieved with the application of a further neural network.
62-70
Foody, G.M.
06e50027-603d-4a5b-88f5-af2bb6235a37
Boyd, D.S.
cc3e74df-9587-4328-a591-f67144fffa82
2002
Foody, G.M.
06e50027-603d-4a5b-88f5-af2bb6235a37
Boyd, D.S.
cc3e74df-9587-4328-a591-f67144fffa82
Foody, G.M. and Boyd, D.S.
(2002)
Sharpened mapping of tropical forest biophysical properties from coarse spatial resolution satellite sensor data.
Neural Computing and Applications, 11 (1), .
Abstract
Forest biophysical properties are typically estimated and mapped from remotely sensed data through the application of a vegetation index. This generally does not make full use of the information content of the remotely sensed data, using only the data acquired in a limited number of spectral channels, and may provide a relatively crude spatial representation of the biophysical variable of interest. Using imagery acquired by the NOAA AVHRR, it is shown that a standard neural network may use all the spectral channels available in a remotely sensed data set to derive more accurate estimates of the biophysical properties of tropical forests in Ghana than a series of vegetation indices. Additionally, the spatial representation derived can be refined by fusion with finer spatial resolution imagery, achieved with the application of a further neural network.
This record has no associated files available for download.
More information
Published date: 2002
Identifiers
Local EPrints ID: 14912
URI: http://eprints.soton.ac.uk/id/eprint/14912
PURE UUID: d2bb6f12-5c82-40ee-921d-0caf7bd461d8
Catalogue record
Date deposited: 09 Mar 2005
Last modified: 08 Jan 2022 00:58
Export record
Contributors
Author:
G.M. Foody
Author:
D.S. Boyd
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics