Satellite imagery and artificial intelligence have been found to be effective tools in detecting two invasive weed species
A research project conducted by two Australian universities has revealed a new method to accurately detect the invasive African lovegrass and bitou bush.
Charles Darwin University (CDU) and Charles Sturt University (CSU) explored the potential for SkySat satellite imagery and AI algorithms to detect and map both of these invasive weed species.
The project fed SkySat satellite imagery of locations across New South Wales into two machine learning algorithms, with one model detecting African lovegrass with 89.9 per cent accuracy and bitou bush with 86.1 per cent accuracy.
Detecting these species, particularly African lovegrass, can be complicated and expensive due to infestations occurring at large scales and in mixed landscapes.
African lovegrass is described as a highly invasive perennial grass which contributes significantly to the $4 billion required annually for direct control of all agricultural and environmental weeds.
Bitou bush has been identified by the Australian Government as a Weed of National Significance and is an aggressive shrub which invades coastal dune vegetation and smothers native plants.
CDU spatial analyst and co-author Glen Shennan, who has expertise in African lovegrass, says this new method could become a critical component in detecting and monitoring these invasive plants in Australia.
“Ground sampling is very labour intensive,” he says.
“If we can make drones and satellites work, it can cut down the cost enormously and you can do this repeatedly to see where the species are spreading.
“You can identify vulnerable areas you want to prevent these species from spreading to, and you can direct management funds and mitigation funds to where it’s most needed.”
Shennan also describes African lovegrass as being “opportunistic” and says the difficulty in identifying it makes these results a significant breakthrough.
“There’s a lot of work going into managing it, but it is herbicide resistant and the only thing that will kill it, it adapts to very quickly,” he says.
“It’s very fast growing, and grows whenever the weather is right, especially in droughty summers.
“It likes disturbed ground so if you have a fire come through, it’s the first thing that will come back.
“It looks a lot like poa tussock when it’s young. Even experienced botanists have trouble differentiating the two, which is where satellites and some types of drones come in.
“They can identify different colours we can’t see, and with this we hope we can identify its growth patterns.”
Researchers say future avenues will include expanding the dataset, collaborating with public agencies, and refining the models to reliably differentiate between lookalike species.