Space is at a premium in most cities around the world, and few would actively choose to devote more of it to waste management than was strictly necessary. Landfill sites are filling and there’s little desire to find new sites, and so recycling is being turned to in order to extend the lives of existing sites.
Recent research from the University of Johannesburg explores how AI can give waste managers a helping hand in forecasting the landfill requirements of their city in the medium to long-term. The researchers used machine learning to forecast solid waste in a large African city.
Traditionally, such forecasting would be done using a humble spreadsheet, but not only might the approach be inaccurate, it’s also hard to maintain and hugely time-consuming. It’s also complicated to introduce new data sources into the picture as well as things like population changes or the types of waste are updated.
AI to the rescue
This is where machine learning comes in, as it can learn from the data by itself, even as more is added. The research focused on the City of Johannesburg, whose population grew from 2.59 million to 3.22 million between 1996 and 2001. By the time of the census in 2011, it had mushroomed to 4.43 million people.
Also in 2011, it was estimated that 90% of the 59 million tonnes of waste produced in South Africa went to landfill, with the remaining 10% recycled. With the population of Johannesburg predicted to rise to 5.3 million by this year, the city’s four landfill sites have just a few years left.
The models predicted that the population of the city would grow to 6.4 million by 2031 and to 8.4 million by 2050. It didn’t expect waste to grow at the same pace, however, with annual waste growing from 1.61 million tonnes in 2021 to 1.72 million tonnes in 2031 and 1.95 million tonnes in 2050.
“One may expect that waste generation ought to increase as population increases, but this is also dependent on factors like low or high purchasing power or source of income,” the researchers say.
“When citizens lose their source of income or the purchasing power is low, the amount of waste generated would be reduced since they would be doing cooking of food at home compared to buying ready-made food at restaurant, for example.”
The researchers next plan to explore how AI can be used to forecast the various different waste types, and how the city could generate income from each of these.
“The City of Johannesburg is currently doing much better in its waste management compared to other large cities on the continent. This AI forecast can help facilitate the city’s design of future waste management infrastructure,” they conclude.
“In the short term, the first step the city can take is educating people, so they start recycling more. Secondly, the city may need to look beyond what they are doing at the moment to generate income from solid waste.”
