About GAIA GAIA Case Studies Global GIS Agenda 21 Country Data Model Database

ABSTRACT

Artificial Neural Networks (ANN) are new technologies for classification. ANN can process incomplete and imprecise data and detect non-linear relations in the data. ANN learning algorithms can be divided into 2 types, supervised and unsupervised. Neural networks learn in massively parallel and self-organizing way. Unsupervised learning neural networks, like Kohonen's self-organizing feature maps (Kohonen, 1989), learn the structure of high-dimensional data by mapping it on low-dimensional topologies, preserving the distribution and topology of the data. In this thesis Kohonen's self-organizing feature map is applied to the classification of a land cover data set. The data was collected from an existing expertly labeled database of land cover regions in Cambodia. Rule extraction derives land cover classes produced by self-organizing methods. Geological experts can use the rule generation algorithm of rule extraction produced by neural networks.


Copyright 1995-2002 by:   ESS   Environmental Software and Services GmbH AUSTRIA