CROPPING

Aussie team advances weed recognition technology

Australian research is helping to develop artificial machine intelligence for weed control.

Staff writer

This article is 3 years old. Images might not display.

The new technologies are being worked on by Australian researchers who are developing an image bank that will help deliver ‘green-on-green' weed recognition.

With investment from the Grains Research and Development Corporation (GRDC), a team of researchers led by Dr Michael Walsh, director weed research at the University of Sydney, has recently completed the pilot phase of crucial work that will underpin future developments for machine learning and weed recognition.

Dr Walsh said there are several commercial interests developing machine learning technologies for site-specific weed control in Australia, but they all need access to a collection of relevant images to essentially ‘train' computers in the development of weed recognition algorithms that can differentiate between crop and weed plants.

"We have set out to establish protocols for collecting and annotating images that will be stored in an open-source database that anyone with commercial or academic interests can contribute to and also use for future developments in this technology," Dr Walsh said.

"The pilot project has centred on collecting images and developing weed recognition algorithms to detect representative grass and weed species in wheat and chickpea crops."

The WeedAI database currently contains thousands of images of annual ryegrass and turnip weed growing in chickpea and wheat crops. These images have been manually annotated and used to develop and test weed recognition algorithms for their accuracy in correctly identifying weeds growing in-crop.

"We are hoping to fast-track developments and take advantage of the machine learning technologies that have capability to accurately recognise and locate in-crop weeds to ultimately provide growers with the opportunity to specifically target these weeds with a range of weed control options."

Dr Walsh said Australia is leading the way in developing weed recognition technologies for grain production systems and he believes the open-source database will reduce replication of effort and encourage technology companies to address more challenging scenarios, such as recognition of grass weeds in cereal crops.

Ground speed can be the enemy of real-time weed recognition systems, as accuracy increases considerably with speeds slower than those currently used for blanket spraying. With increasing computing processing speeds, the expectation is that in-crop weed recognition systems will be accurate at 10 to 15 km/h.

A number of commercial companies are bringing in-crop spot spraying to market and will be on-hand at WeedSmart Week, Esperance, Western Australia, in mid-August to showcase their technology.

For more information about weed control tactics or to register for WeedSmart Week, please visit: www.weedsmart.org.au

A growing series of reports, each focused on a key discussion point for the farming sector, brought to you by the Kondinin team.

A growing series of reports, each focused on a key discussion point for the farming sector, brought to you by the Kondinin team.

editions

Research Report: Cordless Impact Wrenches (July 2025)

Six battery-powered impact wrenches were bench tested in this month's Research Report, focusing on their ability to get nuts done up and undone.

editions

Research Report: Mouse Bait Applications (June 2025)

Mice remain a significant issue for cropping regions and the June Research Report, supported by an investment from the Grains Research and Development Corporation, brings together the latest research and practical recommendations for bait spreading and machinery performance to help growers improve mouse control strategies.

editions

Research Report: Farm Labour (May 2025)

Farm labour, whether temporary, casual, contract or permanent staff, is an essential part of agriculture. This Research Report provides insights to help better source and manage one of the farm’s most valuable assets – its people.

editions

Research Report: Sheep Yards (April 2025)

This month's Research Report includes more than a dozen case studies of new sheep yard builds and renovations from around the country. There are plenty of ideas to make the handling of stock more efficient and stress-free.