Research Thesis Topic
Machine Learning to Facilitate and Enhance the Parametrisation of Agricultural/Cropping Systems Mode
Supervisory team:
Cropping systems models are becoming increasingly important tools in agricultural research, polcy development and implementation and on farm decision making. They are being applied to explore and address challenges in adaptation and mitigation to climate change, production system risk analysis, and resource use efficiency and precision and prescription agriculture. A fundamental aspect when using models is their initial parametrisation and considerable effort is expended to identify and estimate appropriate input/initialisation parameters. This project will develop and apply machine learning methodologies directly within agricultural systems models to accurately estimate hard to measure/spatially variable parameters (e.g. soil parameters) from easy to measure data like crop growth, development and yield. The application of these methodologies will mean that agricultural system models can be easily and appropriately parametrised and will enhance their accuracy and application.
- Computational Engineering and Science Research Centre
- Institute for Agriculture and the Environment
- Crop and Pasture Production
- Numerical and Computational Mathematics
- Doctor of Philosophy (DPHD)
Please review the admission requirements for the academic program associated with this Thesis Topic