Date of Award


Degree Type


Degree Name

Bachelor of Science Honours


School of Computer and Security Science


Faculty of Computing, Health and Science

First Advisor

Dr Leisa Armstrong


The advances in computing and information storage have provided vast amounts of data. The challenge has been to extract knowledge from this raw data; this has led to new methods and techniques such as data mining that can bridge the knowledge gap. The research aims to use these new data mining techniques and apply them to a soil science database to establish if meaningful relationships can be found. A data set extracted from the WA Department of Agriculture and Food (DAFW A) soils database has been used to conduct this research. The database contains measurements of soil profile data from various locations throughout the south west agricultural region of Western Australia. The research established that meaningful relationships can be found in the soil profile data at different locations. In addition, comparison was made between current cluster techniques and statistical methods to establish the most effective method. The research compared two data mining algorithms against a benchmark that was established using standard statistical analysis in use at the DAFW A. The EM and FarthestFirst data mining algorithms were tested in five case studies and it was found that FarthestFirst was more accurate at clustering instances than EM in all cases when tested against actual known clusters groups. The known groups were two traits EC and Clay within two soil types. It was concluded that data mining had a number of advantages over current statistical methods but the methods research can not completely replace them at this stage. The outcome of the research may have many benefits: to agriculture in general, to soil management and to environmental management. The research has been collaboration between the Edith Cowan University and the DAFW A, with the results and outcomes to be shared between the two organizations.