New cropping technology can dramatically reduce chemical run off produced by cane farmers running into the Great Barrier Reef.
Research trials led by James Cook University have found the sprayer machine, which uses artificial intelligence to find weeds and spray them, reduces herbicide run off by up to two thirds.
"You basically only spray where it needs to be sprayed, that means that less herbicide has been put down so less chemicals would be running out of the paddock," lead researcher Mostafa Rahimi Azghadi told AAP.
The AutoWeed AI sprayer was tested across four cane farms in the Burdekin region of Queensland.
The method was found to be 97 per cent as effective as blanket spraying while it reduced herbicide by an average of 35 per cent, with some results even better.
Water quality testing produced during the trials found that paddocks which used the sprayer reduced their chemical concentration in water run-off by an average of 46 per cent.
“In the best cases where weed infestation has been lower, we have saved up to 65 per cent in herbicide usage," Dr Azghadi said.
The machine was fed thousands of paddock images with and without weeds to train the AI algorithm to properly identify them.
“In the field, the AI model will then see a similar image via its cameras and because it has learned what a weed looks like, it will activate the sprayer only when needed,” he said.
The machine was designed by JCU researchers in partnership with the agricultural technology company AutoWeed and Sugar Research Australia.
AutoWeed's Jake Wood said each camera could control several spray nozzles.
“The machine might see a weed in a different part of the image, meaning that only a single nozzle might need to be activated instead of all of them each time,” he said.
Further research is now being carried out on the economic implications of the technology for specific sugarcane weed species and crop situations.
