COMPUTER game-like modelling could help orchardists design and plan their farms of the future.
University of Queensland researchers are utilising "digital horticulture" which involves the optimisation of orchard management practice by modelling in detail real or planned orchards with slow growing crops, like mangoes and macadamias.
Using technology familiar to computer gamers, the scientists are creating "digital twins" of mango and macadamia orchards to boost food production.
Centre of Horticultural Science at Queensland Alliance for Agriculture and Food Innovation (QAAFI) director Professor Neena Mitter says developing a digital model for an orchard with slow growing crops lets researchers conduct virtual experiments at a scale and speed never before possible.
In one example, the time needed to understand how to prune a fruit orchard to optimise sunlight capture was cut from decades to days or hours.
"The result is an acceleration in innovation that will help make food production more productive, resilient, and sustainable," Professor Mitter said.
The digital twins project lead researcher Dr Liqi Han recently developed software to simulate experiments on mango orchards.
- Avocado industry tastes fruit from tissue culture-grown plants
- Researcher takes a trip into world of Australian native "magic mushrooms"
- Slowing the sugar rush to yield better grapes
Dr Han said slow growing crops like fruit trees will especially benefit from the technology.
"We call this technology DigiHort, short for digital horticulture," he said.
"The technology provides untapped opportunities for users to rapidly trial new ideas and acquire a reliable indicator of how to best optimise production systems."
The computer simulations take three different forms:
- Conceptual designs: A conceptual orchard design is based on an orchard that does not yet exist in reality but can be created within a computer.
- Digital twins: A digital twin is a replica of a real-world orchard, mirroring it in fine detail.
- Digital variants: Orchard management can be applied to the digital twin, creating a 'digital variant'.
"All three forms can be integrated with environmental and management simulators," Dr Han said.
"This might include sunlight and chemical spray simulations, for example, to allow for evaluation and optimisation of orchard management practice."
Virtual trials are possible across all aspects of orchard management. It starts with the design of an orchard, with the software allowing users to decide where in a landscape to plant trees, the density of the canopies and the configuration of the rows.
It then extends to options for how the trees are maintained, allowing users to wield virtual pruners and test the impact of different - and even unconventional - tree training systems.
In addition, the QAAFI team can scan an actual orchard to generate a digital twin that mirrors a real-world production system.
This innovation is based on new LiDAR scanning technology applications that were undertaken with industry partner, Riegl Australia, and state government research stations in Queensland, Western Australia and Northern Territory.
The laser-based technology captures the architectural features of trees allowing the creation of a digital twin, down to the level of individual leaves.
These advances rely on High Performance Computing (HPC), which allows Dr Han to run extremely fast virtual experiments without loss of accuracy.
"These days, we talk more and more about precision agriculture," Dr Han said.
"We enhance precision by looking at the details, such as how much light can be captured by each leaf or fruit, or the distribution of sprayed chemicals across the canopy.
"We can accumulate small benefits into big benefits or prevent big losses from occurring. Small differences can have a big impact."
The DigiHort platform was designed as a decision-support service for industry and its simulation-evaluation-optimisation components will be accessible via the internet.
Sign up here to Good Fruit and Vegetables weekly newsletter for all the latest horticulture news each Thursday...