The University of QueenslandSecuring our future food: the digital agricultural revolution

Securing our future food: the digital agricultural revolution

The University of Queensland (UQ) continues to break new ground in agriculture innovation, driving new digital solutions in its mission to feed the world and prevent global food shortage.

From artificial intelligence and GPS technology to remote sensing, genomics, and blockchain, UQ scientists are pioneering data-driven technology to improve decision-making and productivity across all stages of food production.

In fact, UQ is Australia’s leading agricultural research institution and is ranked fourth globally, according to NTU rankings 2018.

With the world’s population expected to exceed nine billion by 2050 according to the United Nation’s Department of Economic and Social Affairs, food production will need to increase by 70 per cent in order to sustain the ever-growing number of humans on our planet.

At the same time, research is showing that climate change is already negatively impacting global crop yields.

Therefore, how the world continues to grow enough food, while developing more resilient crops, has never been more important.

UQ’s Chair in Prediction Based Crop Improvement Professor Mark Cooper said privateand public-sector research collaboration was fast-tracking breeders’ progress towards increasingly higher-performing crops.

“Public breeding programs can overcome the need for large datasets and financial investment by implementing aspects of predictive breeding that have the highest pay-off,” Professor Cooper said.

“The technology allows for more strategic, cost-effective investment in crop improvement in the public sector.

“UQ is the obvious choice when it comes to bridging public- and private-sector capabilities with new breeding technology. It is where artificial intelligence is being trained to deliver ‘genomic prediction’ capability.”

The prediction-based methods developed at UQ involve melding two different modelling capabilities – the quantitative genetics model and crop-growth model.

The quantitative genetics model relies on comparing the performance of genetically diverse plants in field trials to detect the DNA sequences that account for high-performing traits.

While this model has predictive capability when plants are grown under standard conditions, it struggles to predict how plants will respond to environmental variations or to varied management practices.

The crop-growth model is a computational tool that UQ researchers first started to develop in the 1990s.

The software simulates physiological processes essential to crop growth, including availability of light, water and soil nutrients.

As such, the crop-growth model does not deal with ‘genetic traits’, but rather with ‘intermediate traits’, like photosynthesis or nutrient and water uptake.

“The advantage of the combined models is that we can better predict how genes selected during a breeding program are likely to interact with seasonal weather variation and agronomy,” Professor Cooper said.

“We can preview unique trait combinations and understand which traits increase crop performance. This allows us to scale a breeding program even when it involves complex traits, such as drought tolerance.”

Professor Cooper said past UQ partnerships were essential to the evolution of this technology.

In the 1990s, US crop producer DuPont Pioneer jump-started its modelling capability via a research partnership with UQ.

The company built an internal research and development team that continued the partnership and developed parallel modelling capability more suited to an industrial breeding program. It is now in its third iteration of prediction-based breeding technology.

“When people ask us to demonstrate that this technology will work, industry has already answered that question and moved on,” Professor Cooper said.

“It has already decided this technology is the future.”

Read more about UQ’s work in digital agriculture.

Brought to you by