Site mapping using GIS tools and fuzzy clustering in Wetlands

Abstract

This paper describes the first results of our study on modelling the site conditions of North Hanság. Supposing that the environmental factors are the driving forces of soil development at a given location through complex interactions, we tried to sort out the key elements of the soil-environment system, to predict the soil properties for every spatial unit within the study area at a spatial resolution of 20 by 20 m. We used fuzzy classification to assess the main soil types and their central concepts concerning both the soil property domain and the environmental condition domain. A maximum likelihood classification was applied to assign discrete class membership values to each pixel of the study area. Finally, we applied multiple regression equations for each class to derive the soil property map from the map of environmental conditions.