Remote sensing of biodiversity: using neural networks to estimate the diversity and composition of a Bornean tropical rainforest from Landsat TM data

Author

Foody, Giles M. ; Cutler, Mark E.

Author_Institution

Dept. of Geogr., Southampton Univ., UK

Volume

1

fYear

2002

fDate

2002

Firstpage

497

Abstract

Two types of neural network were used to derive measures of biodiversity from Landsat TM data of a tropical rainforest. A feedforward neural network was used to estimate species richness while a Kohonen neural network was used to provide information on species composition. The results indicate the potential of remote sensing as a source of maps of biodiversity.

Keywords

ecology; forestry; geophysical signal processing; geophysical techniques; neural nets; vegetation mapping; Danum Valley; IR; Indonesia; Kohonen neural network; Landsat TM; biodiversity neural network; biological diversity; feedforward neural network; forestry; geophysical measurement technique; infrared; multispectral remote sensing; neural net; neural network; rainforest; remote sensing; self organizing feature map; species composition; species richness; tropical forest; vegetation mapping; visible; Atmospheric waves; Biodiversity; Clouds; Feedforward neural networks; Geography; Neural networks; Remote sensing; Satellites; Sustainable development; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International

Print_ISBN

0-7803-7536-X

Type

conf

DOI

10.1109/IGARSS.2002.1025085

Filename

1025085