Modeling Training Site Vegetation Coverage Probability with a Random OptimizingProcedure: An Artificial Neural Network Approach

摘要

The objective of this project was to examine the feasibility of applying feed-forward neural networks to estimate training site vegetation coverage probability based on past disturbance pattern and vegetation coverage history. The rationale behind this project was the excellent approximation and generalization ability of feed-forward neural networks. Data used to train the networks were collected from Fort Sill, Oklahoma, using the U.S. Army's Land Condition Trend Analysis (LCTA) standard data collection methodology. Two types of vegetation covers were modeled in this project: ground cover and canopy cover. For both types of vegetation cover, the input vector of a transect point consisted of several variables; namely, the past disturbance, past vegetation cover, plant community type, and vegetation life form. The output from the model was the estimated conditional probability of a transect point having vegetation cover. Results from this project suggest that artificial neural networks are a suitable tool for predicting training site vegetation coverage probability.