Modern agricultural production systems and enterprises are data rich environments. In theory the availability of data enhances decision making and allows producers to readily identify and address production constraints. However, the volume of data available and a lack of easy to apply methodologies to ingest and analyse this data often leads to a paralysis in decision making. Agricultural production system models have traditionally been used to explore complex interactions between climate/weather, soils, crops, livestock and management. This makes such models ideally suited for ingesting an interpreting complex and large agricultural data flows in a way that facilitates decision making. This project will use yield maps coupled with other on-farm data flows that are ingested through agricultural models within a machine learning/artificial intelligence framework to diagnose areas of constraint within cropping systems and develop prescriptive agricultural strategies to help producers overcome these constraints.

Professor Keith Pembleton

• Dr Duc-Anh An-Vo

• Computational Engineering and Science Research Centre
• Institute for Agriculture and the Environment

• Crop and Pasture Production
• Numerical and Computational Mathematics

• Doctor of Philosophy (DPHD)