Proceedings of the KSRS Conference (대한원격탐사학회:학술대회논문집)
- 2008.10a
- /
- Pages.133-136
- /
- 2008
- /
- 1226-9743(pISSN)
ARTIFICIAL NEURAL NETWORKS IN FOREST BIOMASS ESTIMATION
- Amini, Jalal (Department of Surveying engineering, Faculty of Engineering, University of Tehran) ;
- Sumantyo, Josaphat Tetuko Sri (Centre for Environmental Remote sensing, Chiba University) ;
- Falahati, Mahdi (Department of Surveying engineering, Faculty of Engineering, University of Tehran) ;
- Shams, Reza (Department of Surveying engineering, Faculty of Engineering, University of Tehran)
- Published : 2008.10.29
Abstract
In this paper, ALOS-AVNIR, PRISM, and JERS-1 images are used in a multilayer perceptron neural network (MLPNN) that relates them to forest variable measurements on the ground. The structure of this MLPNN is a three layers neural network that contains eight input neurons, 10 hidden neurons and five output neurons. It is shown that the biomass estimation accuracy is significantly improved when the MLPNN is used in comparison with Maximum Likelihood algorithm.