Pest and disease scouting in major New Zealand crops: evaluating remote sensing and machine learning tools

Host Faculty: Science
General Subject Area: Mathematics and Statistics
Project Level: PhD
View the Research Website
B3 Image

New Zealand's primary industry is constantly under biosecurity threats. Once an introduced species is established, precise detection of affected plants by pests and diseases is fundamental to make a quicker biosecurity response.

Remote sensing is used as an effective and accurate tool for the detection, forecasting, and management of insect pests and plant diseases on different crops worldwide. Within its intensive agricultural land, New Zealand presents unique case studies to investigate how recent remote sensing technologies combined with new machine learning algorithms can develop much-needed remote sensing capability for New Zealand biosecurity.

A joint project between newly funded transdisciplinary University of Canterbury Biosecurity Innovations (UCBI) research cluster and Better Border Biosecurity (B3). The PhD is supervised by Dr Blair Robertson and Associate Professor Marco Reale (School of Mathematics and Statistics,) from UCBI and by Dr Federico Tomasetto and Dr Craig Phillips from our B3 AgResearch partner. Additional advised advisors from University of Canterbury (Dr Steve Pawson, School of Forestry) and from AgResearch (Senior GIS Analyst Peter Pletnyakov). 

The applicant will build on overseas research and data from collaborating end-users to study how remote sensing coupled with machine learning algorithms could identify biosecurity threats in maize, pasture and wheat crops at the landscape level, enabling government and industry to allocate surveillance resources to the most appropriate locations, searches and treatments during potential eradication programs and also estimate crop losses. A practical field-based component to test specific hypotheses may be included and tailored to the interests of the applicant.

Supervisors

Supervisor: Blair Robertson

Key qualifications and skills

The ideal candidate will have an interest in sample design, classification algorithms and quantitative ecology, and have a Masters level qualification in mathematics, statistics or closely related subject.

Biologists that have a strong affinity for, and proven experience in, applied mathematical problems and are wanting to expand on this as a PhD may be considered.

Does the project come with funding

Yes - $28K per annum for 3 years plus study fees

Final date for receiving applications

Ongoing

Keywords

remote sensing, machine learning, mathematics, statistics, agriculture