AI/Machine Learning

University of South Australia researchers are using AI in bins to improve waste management

- April 7, 2023 2 MIN READ
UniSA PhD student Sabbir Ahmed. Photo: Supplied
Researchers from the University of South Australia (UniSA) are shaking up the waste management game by deploying artificial intelligence (AI) in rubbish bins to keep tabs on public bin collections.

The tech will be used to predict which spots generate more garbage so authorities can plan how frequently public bins should be emptied.

UniSA PhD student Sabbir Ahmed is designing a deep learning model that uses algorithms to analyse data from smart bin sensors. 

“Sensors in the public smart bins can give us a lot of information about how busy specific locations are, what type of rubbish is being disposed of, and even how much methane gas is being produced from food waste in bins,” Ahmed said.

By feeding all the data into a neural network model, the design can predict which public bin locations will fill up quickly and which ones are barely used. 

The insights can help councils optimise their waste management services, schedule bin clearances, and even relocate bins to areas with more demand. 

Ahmed is collaborating with Wyndham Council in Victoria for a pilot project that uses smart bin data to develop an AI model. 

The research has been published in the International Journal of Environmental Research and Public Health. 

Co-author of the paper, UniSA lecturer Dr Sameera Mubarak said waste management is a growing concern around the world.

“Many urban areas are struggling to cope with an increase in garbage due to rapid population growth, and waste services are becoming increasingly difficult for local governments to manage,” she said. 

The researchers are examining sensor data from public bin sites, routing paths, and pick-up locations to develop their AI model. 

The sensors can detect various types of waste, including solid, organic, industrial or chemical, medical, and recycling.

AI can quickly predict patterns of waste generation in public areas, like identifying busy days and upcoming events that could lead to more garbage. 

This will help schedule waste collection more effectively and avoid overflowing bins.