As larvae, black soldier flies are an invaluable waste transformer which will eat almost anything, from food waste to manure, before they become adults and lose their mouths.
To make their recycling process more efficient, ARC Ento Tech needs more fly larvae to be produced by adult flies in the recycling hatch. But until now, there has been no accurate way to measure the reproductive behaviour of the fly.
“While ARC Ento Tech has created ideal conditions for the black soldier fly larvae to flourish in the recycling hatch, they don’t know the speed at which black soldier flies can breed larvae and the number of larvae they produce,” project lead Alexandre Marcireau, from the International Centre for Neuromorphic Systems at Western Sydney University, said.
“Optimising the breeding of the flies requires precise knowledge of the number of flies that move from the ‘growing area’ where they eat waste, into the ‘breeding room’ where they breed and deposit larvae eggs.
“If we can count these fast-moving objects, then the recycler can systematically quantify the impact of breeding parameters such as temperature, light intensity and amount of food, and engineer an optimised system with significantly higher yields of larvae.”
Traditionally it has been difficult for conventional cameras and sensors to capture reliable data due to the high speed and number of flies. The system designed by the team is based on a neuromorphic camera: technology which uses sensors to collect only useful data and which has been inspired by biology to accurately observe fast-moving objects, including flies.
The High Speed Counting of Black Soldier Flies project utilised the world-leading neuromorphic vision capabilities at Western Sydney University, in collaboration with Macquarie University researchers who delivered the hardware which allowed the sensor to operate inside the breeding cages.
“The FlyCount system was developed with neuromorphic vision sensors and a custom spike detection algorithm for real-time, accurate fly counting, which ensures 95 per cent accuracy in dynamic lighting,” Professor Subhas Mukhopadhyay from the School of Engineering at Macquarie University said.
“By integrating neuromorphic sensing technologies to an IoT enabled system, the system demonstrates the effectiveness and accuracy of the event-based counting system for tracking and analysing the movements of black soldier flies remotely.
“Collaborating with ARC Ento Tech, we have adapted advanced neuromorphic sensing to improve operational efficiency in fly breeding, showcasing how practical innovation can reduce environmental impact and support sustainable agriculture."
The recycling process involving the black soldier fly is a critical piece in achieving a circular economy which significantly reduces the amount of mixed solid waste going into landfill.
“Once all the organic waste is eaten, the larvae are recovered and converted into commercial products, including a highly nutrient insect meal for chickens, and organic fertiliser, while the inorganic waste is converted into an innovative industrial reductant which can replace coking coal.
“This is a great example of a genuine collaboration between all parties,” NSW Smart Sensing Network Environment and Agriculture theme lead Tom Hu said.
“Western Sydney University had developed their neuromorphic sensing expertise from the space domain, and the mechatronic engineering capability at Macquarie University helped bring this into a new environment.
“The technology looks to now improve operational efficiencies in breeding flies, aiding ARC Ento Tech.”
The solution comes as Greater Sydney is on the brink of a waste crisis due to a lack of landfill space. Almost 70 per cent of the mixed solid waste generated in Australia in 2018 was buried in landfill.
The techniques and insights that will come out of the project are scalable and may open the door to other applications, such as beehive monitoring.
