Agile Research Methods Lead to Rapid Commercialisation
Food Agility's Predicting Harvest Timing and Yield in Intensive Cropping project team have used agile research methods to achieve rapid commercialisation just 6 months in to a 2-year collaborative project.
Major Australian grower, Costa Group, announced the roll-out of The Yield’s Sensing+, an innovative weather prediction and yield prediction solution, across 8 of their berry farms in New South Wales, Queensland and Tasmania.
The commercial arrangement comes just six months into a two year collaborative research project with Food Agility CRC, demonstrating how ‘agile’ methods can expedite research out of the lab and into field for maximum impact.
Developed as part of Food Agility’s Predicting Harvest Timing and Yield in Intensive Cropping project with AgTech company, The Yield Technology Solutions, and The University of Technology, Sensing + uses AI models to provide information and predictions that help growers make important on-farm decisions.
Ros Harvey, Founder and Managing Director of The Yield says “the success of this project was recognition of our efforts in delivering a world-class solution in weather predictions and yield predictions for our customers.”
“Our Sensing+ solution combines sensors and analytics to provide information and predictions in easy-to-use apps that help large commercial growers make important on-farm decisions like when to irrigate, feed, plant, protect and harvest,” she said.
“Using Costa’s extensive data sets, our Sensing+ Enterprise Analytics platform enables us to quickly and efficiently combine data to create AI models for things like Yield Predictions that will drive significant commercial benefit for Costa Group.”
Rolling out Sensing + will enable Costa Group to transform manual aspects of their business to automated, data-driven processes 18 months sooner than anticipated.
According to the project’s Lead Researcher, Associate Professor Daniel Ramp, traditional manual methods of yield prediction can be somewhat inaccurate up to 50% of the time.
“The vagaries of production create a whole lot of uncertainty in what [growers] are going to produce. Our goal in this project is to reduce uncertainty by using artificial intelligence and data analytics to enable us to quantify yield in a much more certain way than what growers have been able to do in the past.”
“Let's say we improve accuracy by 5%,” Professor Ramp says. “The financial benefit of that improvement is going to be substantial. Particularly when these improvements begin to accumulate over time as the models are updated.”
UTS researchers embedded at The Yield’s office in Sydney will be continually improving the predictive models and will release them into the commercial product. This iterative approach is a core principle of agile research.
The project team regularly update the growers on their progress, which Professor Ramp says “enables us to test assumptions that we’ve made about the way their businesses work. It also enables us more clarity around the expectations of the end user to make sure that the outcomes of the work that we’re doing is readily able to be adopted within their organisation and [will] lead to success.”
Food Agility Chief Scientist, Professor David Lamb, believes the Predicting Harvest Timing and Yield in Intensive Cropping Project “exemplifies the wonderful outcomes when you have alignment of values and practice between partners. The incorporation of the research team with an industry partner, the co-design of the fundamental questions, and the agile approach to project delivery is guaranteed to ensure a direct pathway to impact – and fast impact.”