Forecasting Tree Volume Growth using Artificial Neural Networks: The case of Cypresses Lusitania Species
No Thumbnail Available
Date
2006-09
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
Neural networks are computational models with the capacity to
learn or generalize complex relationships that exist among data.
Although there are different kinds of networks, the multi-layered
feed-forward neural network is the most widely used network that
is capable of representing non-linear functional mappings between
inputs and outputs. The training of this network is accomplished
by the method of error back-propagation In this paper, the feed-forward neural network with back
propagation learning algorithm is presented for forecasting tree
volume growth of Cupressus lustanica species. The data set for
training the neural network was obtained from the Forestry
Research Center (FRC). As an input to the neural network, the
historical tree volumes are used to train the network. After training
the network, the results of forecasting is evaluated using test data
set. The result indicates that the model yields good prediction with
independent test data set, providing about 86.7% correct forecasts
within ±2cm3 of the observed values. This suggests that the neural
network is a good candidate for forecasting future value of tree
volume given properly and accurately measured historical data.
Description
Keywords
Information Science