Artificial Intelligence for Australian Grain Farmers
Location: Nedlands, WA (Based at CERI – The Centre for Entrepreneurial Research and Innovation)
Duration: 5 months
Proposed start date: August 2019
Globally, close to 300 million hectares of wheat, barley and canola are grown annually. Australia grows close to 19 million hectares annually. Global consumption of nitrogen fertiliser is 120 million tonnes per year and growing at 1.5% per year. Australian grain farmers invest close to $1.5 billion a year in nitrogen fertiliser. Individual farmers typically invest $40 – 80 per hectare, making nitrogen fertiliser their single largest operating expense.
Most nitrogen fertiliser is applied at a uniform rate across whole paddocks and even across whole farms. This is despite known differences in likely crop yield which is the biggest determinant of nitrogen requirement. This ‘blanket’ approach to fertilising causes economic losses in two ways: (i) reduced yield and lost profit due to underfertilisation where the application rate is less than crop requirement, and (ii) overfertilisation and waste of fiscally and environmentally expensive nitrogen in areas where the application is greater than crop requirement.
Laconik’s technology quickly calculates nitrogen rates for many small areas (0.1 hectare each) across the thousands of hectares of a broadacre farm. It does this using existing information sources and with minimal cost.
Laconik is looking for expertise in machine learning, artificial intelligence, data science and computer programming. Knowledge of agriculture is not essential for this project. Students with these skills and a background in physics, mathematics, statistics, medical and engineering are strongly encouraged to apply.
Research to be Conducted
By 1 February 2020, Laconik has algorithms that improve fertiliser decisions for Australian farmers.
- By 1 February 2020, Laconik has accurate algorithms for predicting;
- Grain yield in wheat, barley and canola
- Wheat, barley and canola responses to nitrogen, phosphorus and potassium.
Laconik has some of the data required for the project, with more to be gathered as the project progresses.
Laconik is looking for expertise in machine learning, data science and computer programming. Knowledge of agriculture is not essential. Students with these skills and a background in physics, mathematics, statistics and engineering are strongly encouraged to apply.
Laconik has already invested and developed grain yield and nutrition response algorithms. This project is to improve the current prediction models. The final outcome from this project will be a software model, written in python, which can be integrated into Laconik’s existing systems.
The intern will receive $3,000 per month of the internship, usually in the form of stipend payments.
It is expected that the intern will primarily undertake this research project during regular business hours, spending at least 80% of their time on-site with the industry partner. The intern will be expected to maintain contact with their academic mentor throughout the internship either through face-to-face or phone meetings as appropriate.
The intern and their academic mentor will have the opportunity to negotiate the project’s scope, milestones and timeline during the project planning stage.
31 July 2019
APR – 0952