Interrogation of Water Catchment Data Sets Using Data Mining TechniquesECU Publications Pre. 2011
Document TypeConference Proceeding
PublisherEdith Cowan University
FacultyComputing, Health and Science
SchoolSchool of Computer & Security Science
AbstractCurrent environmental challenges such as increasing dry land salinity, water logging, eutrophication and high nutrient runoff in south western regions of Western Australia (WA) may have both cultural and environmental implications in the near future. Advances in computing through the application of data mining ,and geographic information services provide the tools to conduct •studies that can indicate possible changes in these water catchment areas of WA. The research examines the existing spatial data mining techniques that can be used to interpret trends in WA water catchment land use. Large GIS data sets of the water catchments on Peel-Harvey region have been collected by the Western Australian government. This paper describes the techniques that will be used to explore the large GIS -data sets and provides cluster analysis of a sample subset of the data set as a proof of concept. This research will contribute to the later development of a data mining interrogation tool that measures and validates the effectiveness of different data mining techniques such as: classical statistical methods, cluster analysis and principal component analysis on the sample water catchment data set. The interrogation tool will incorporate some of the geospatial data mining techniques described in this paper to discover meaningful and useful patterns specific to current agricultural problem domain of dry land salinity. This research will contribute towards an understanding of the data mining techniques that can be used in the tool. The tool is expected to be used by government agencies, such as Department of Agriculture and Food, Western Australia researchers and other agricultural industry stakeholders.
Citation InformationAjdin Sehovic, Leisa Armstrong and Dean Diepeveen. "Interrogation of Water Catchment Data Sets Using Data Mining Techniques" (2010)
Available at: http://works.bepress.com/leisa_armstrong/13/