Virtual StatsPD@Waite meeting

Every month, the professional development meetings of statisticians and data scientists at Waite, known as StatsPD@Waite, bring together specialists in various aspects of data sciences in agriculture from Waite, Roseworthy and Adelaide.

Please join us for the next Virtual StatsPD@Waite seminar where Dr Matthew Knowling from the University of Adelaide will present on process-based models, diverse data streams and uncertainty.

Please note that the StatsPD@Waite meetings are recorded. If you have a question to the speaker but would rather not be recorded, please send me your question via chat during the meeting and it will be asked on your behalf.

Please email Beata Sznajder for details of the Zoom meeting.

Presenter: Dr Matthew Knowling (University of Adelaide)

Title: Bridging the gap between data and decisions: Process-based models, diverse data streams and uncertainty

Farmers now have more and more diverse data streams at their disposal. However, it is not a forgone conclusion that these will enable them to make better operational decisions. There is a critical need to be able to combine diverse data streams in real time to establish a unified representation what is happening on the farm, why and what is likely to happen in the future. To this end, we develop and apply an innovative crop model data assimilation framework. Our framework uses farm observations to update dynamically both model input parameters and states variables, while also mapping these updates to forecasts of end-of-season yield, which represents a decision-critical metric. This study considers a viticulture example, where we assimilate daily climate/weather data as well as ground-based leaf area index (LAI) data into a grapevine growth and development model. Both the crop model and the DA algorithm employed are open source and freely available.