Supported by

PhD scholarships to build agriculture’s data-driven future

A new postgraduate scholarhship program, worth $250,000, is now calling for applications for full or top-up scholarships to carry out data-driven science projects relevant to agriculture.

The program is a joint initiative between Curtin University and CSIRO’s newly established Data61, Australia’s leading digital research powerhouse, and aims to build agriculture’s capacity in the big data field.

To apply for a full scholarship, students must be Australian citizens or permanent residents. International students can apply for top-up scholarships.

Available projects in detail:

For more information on each of the available scholarship projects and instructions on how to apply, contact Professor Mark Gibberd, CCDM Director, at T: (08) 9266 7907, E: m.gibberd@curtin.edu.au.

1. Advanced analytics to forecast the world food supply by fusing models with remote sensing.

Australia supplies 15% of the worlds traded grain, and provides a food buffer for much of the world when shortages occur.  Better forecasting technologies are required to track Australian crop production and this project would contribute to some of the fundamental science behind crop forecasting. The project would:

  • Develop an analytical approach using a combination of satellite imagery and crop models to predict crop yields
  • Explore the sensitivities of the model to climate extremes and soil type

2. Sensing pathogens in food crops with multispectral imaging systems and mechanistic models

Pathogens such as septoria, stem rust, leaf rust and powdery mildew all cause significant damage to Australian cereal crops in the productive high rainfall zone.  Identifying and monitoring these diseases is vitally important for farmers, grain traders and consultants. This project would:

  • Identify whether sensors can detect crop pathogens in cereal crops
  • Determine the impact crop pathogens have on crop production, using mathematical models of crop yield and information generation from the next generation of sensors.

3. Exploiting novel data streams and big data to manage spatially variable field crops.

Crop yields often vary by 50% or more due various to landscape factors.  Untangling the cause of this variation presents a challenging problem for a data scientist, who must integrate multiple streams of data from crop models, remote sensing satellites, drones, soil moisture probes and geophysical information.  The project would:

  • Integrate digital information sources to understand the spatial variation of crop yield
  • Develop management strategies based on these new data models of crop yield

4. Integrating multiple data sources to predict the crop response to fertiliser.

The crops response to fertiliser varies with season and soil type, which complicates the decision to apply fertiliser.  Multiple data streams, from crop models, remote sensing, soil surveys, drones and soil moisture probes may be synthesised to develop the ultimate fertiliser decision aid for farmers that identifies when and where a crop will respond to applied fertiliser.  The project would:

  • Integrate digital information from multiple sources to determine how responsive the crop is to applied fertiliser.
  • Develop management strategies based on these new data models of crop responsiveness to fertiliser.