February 27, 2023
Artificial intelligence has made a huge leap into our trash cans thanks to new technologies being used at the University of South Australia.
UniSA PhD student Sabbir Ahmed uses algorithms to analyze data from smart bin sensors and develops a deep learning model to predict where in cities trash accumulates and how often public trash cans should be emptied.
“Sensors in the public smart bins can give us a lot of information about how busy certain places are, what type of garbage is being disposed of, and even how much methane gas is being produced from food waste in garbage cans,” says Ahmed.
“All of this data can be fed into a neural network model to predict where trash cans in parks, malls and other public places are likely to fill up quickly and which places are rarely visited.
“This can help municipalities optimize their waste management services, schedule bin emptying, and even move infrequently used bins to where they are needed most.”
Ahmed is working with Wyndham Council in Victoria on a pilot, using their Smart Bin data to develop an AI model that could be used by local governments across the country to make waste collection more efficient.
Details of the research are published in the International Journal of Environmental Research and Public Health.
The co-author of the paper, UniSA lecturer Dr. Sameera Mubarak says waste management is a growing problem worldwide.
“Many urban areas are struggling with the increase in garbage due to rapid population growth, and managing waste disposal is becoming increasingly difficult for local governments,” says Dr. Mubarak.
In developing an AI model, the researchers analyzed sensor data from public dumps, routes, and pickup locations. The sensors detect different types of waste: solid, organic, industrial or chemical waste, medical waste and recycling waste.
“Human planning takes time, but with the help of artificial intelligence, we can predict patterns of waste generation in public places.
“This includes predicting which days will be busier in certain locations, flagging upcoming events that will lead to increases in litter, and scheduling litter collection around those predictions.
“Improper waste collection can lead to serious health and environmental hazards for cities, especially when bins overflow. This research ticks many boxes, including addressing challenges related to sustainability, environmental and health issues, and efficient resource sourcing.”
Researchers plan to examine the impact of socioeconomic factors and public utility investments on waste generation in future work.
Notes for editors
“Forecasting the status of Municipal Waste in Smart Bins Using Deep Learning” was written by Sabbir Ahmed, Dr. Sameera Mubarak, Associate Professor Tina Du and Associate Professor Santoso Wibowo from Central Queensland University.
Media contact: Candy Gibson M: 0434 605 142 E: [email protected]
