A FUZZY ALLOCATION SCHEME FOR THE AUSTRALIAN GREAT SOIL GROUPS CLASSIFICATION-SYSTEM

Conventional methods of soil classification are based largely on hiera rchies and treat soil attribute value ranges as exactly specifiable qu antities. Misclassification may result from ignoring the continuous co mplex nature of soil variation, and the inability to sample and measur e every aspect of soil. The Australian Great Soil Groups (GSG) system of classification is essentially a fuzzy classification, and for the m ost part central concepts have not been defined explicitly. Centroids were generated, together with fuzzy group membership, using data from the 147 soil profile descriptions in The Handbook of Australian Soils. Some of the GSG, such as Siliceous Sands and Red and Brown Hardpan So ils, were divided into their component parts for better and easier qua ntification and allocation. The centroids of GSG were examined, and th e method of fuzzy k-means was then used to allocate unknown profiles t o the GSG. The results show that the system is intuitively reasonable.