eAgriculture techniques and methodologies for application to agriculture data
The importance of increasing agricultural production and sustainability is reliant on an understanding of the variability in crop varieties grown under different agricultural conditions. This project is evaluating current eAgriculture methodologies for their application in Australian agricultural industry. The application of artificial intelligence techniques, such as data mining, to agricultural data can improve the interrogation of agricultural research data and lead to developing better agricultural systems which can respond to climate change and other environmental factors such as soil salinity and drought.
The project is investigating a number of factors including the development of specific agriculture data mining frameworks and feature selection for these large agricultural data sets. Novel data mining algorithms are being developed that can be applied to sample and agriculture data sets to validate these methods. The research will focus on identifying the major sources of variability and validate the results through simulations. This research will provide the insight investigation of the various agriculture data sets including soils, climate, crop data at farm, catchment and regional levels. The project will provide the techniques to improve the decision making of farmers and agricultural industry in respect to crop variety selection and responses to environmental and agricultural concerns. This research is being carried out with the support of iVec.
Dr Leisa Armstrong
Post Doctoral Research Fellow, Dr Jinsong Leng
University of New England, Dr Neil Dunstan
Department of Agriculture and Food, Western Australia, Mr Dean Diepeveen
Mr Yunous Vagh
Mr Aiden Sehovic