Classification of forest change by integration of remote sensing data with Neural Network techniques

Forest is a major resource and play vital role in maintaining the ecological balance and environmental setup. Over utilization of forest resources has resulted in the depletion. The changes in forest cover (encroachment) are the matter of global concern due to its ability of promoting role in carbon cycle. This paper will focus into the application of artificial intelligence used in remote sensing such as Neural Network worldwide for assessing and monitoring the changes in forest cover (encroachment). However, advances in the spectral resolutions of sensors are available for ecologist which mainly feasible, to study the certain aspects of biological diversity through direct remote sensing. Global and regional scale of multispectral remote sensed data such as QuickBird, will be used in this study for monitoring the changes in forest cover (encroachment) over the last few decades. Monitoring the changes in forest cover at global and regional scale can contribute to reducing the uncertainties in estimates of emissions of green house gases from forest encroachment. Remote sensing coupled with one of artificial intelligence techniques will use as a potential tool, for classification of the forest encroachment at regional as well as global scale in developing countries such as Malaysia; mainly this research will assist many sectors to monitoring and identify forest encroachment.