Artificial Intelligence: How AI Makes Waste Management Forecasts Easier

April 13, 2021 | Artificial Intelligence, News

Researchers at the University of Johannesburg found AI beats Excel at forecasting solid waste volumes and landfill requirements.

Cities across the world are grappling with the problem of finding landfill sites and new land as solid waste tonnage rises with population and economic growth. How does one forecast, over the long term, solid waste volumes and landfill requirements? AI could be the answer to the problem. (Eurekalert)

Dr. Olusola Olaitan Ayeleru and Mr. Lanrewaju Ibrahim Fajimi, researchers at the Department of Chemical Engineering at the University of Johannesburg, conducted a study to demonstrate whether AI could more efficiently provide city waste managers with the data and projections to address the issue.

AI to help manage waste

Spreadsheets have limitations in waste projections. They are hard to understand because they need to build in macros and formulas. It is also difficult to conduct scenario analysis with spreadsheets, as also is accounting for data such as population growth, waste types, weather, and other variables.

Another problem is the paucity of full data, particularly in developing countries.

The city of Johannesburg received a wake-up call in September 2020 when the COO of Pickitup, the city’s waste management company, warned that only four and a half years of capacity was left at the city’s four landfill sites.

Fajimi deployed AI to analyze the city’s waste problem. He found that a 10 neuron artificial neural network, an AI model that could learn from new data, produced the best forecasts.

Model forecasts

The 10-neuron model forecasted that the population in Johannesburg is likely to increase from 5.3 million in 2021 to 6.4 million in 2031, and to 8.4 million in 2050.

It also forecasted an increase in total annual waste from 1.61 million tonnes in 2021 to 1.72 million tonnes in 2031, and to 1.95 million tonnes in 2050.

“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,” says Ayeleru.

“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.”

Related Story:   KKR is Buying Recycling Firm Viridor for £4.2 Billion in Cash                                               

Free Industry News

Subscribe to our free newsletter for updates and news about alternatives investments.

  • This field is for validation purposes and should be left unchanged.


Latest Alternative Investment News
Digital Assets: Colonial Pipeline Caved; Paid $5M Ransom To Hackers
May 14, 2021     Digital Assets, News

Though initial reports said that Colonial Pipeline would not pay a ransom to the hackers that brought the nation’s largest fuel pipeline to a halt, Bloomberg reported Thursday that the…
Artificial Intelligence: A Molecule For Alzheimer’s Created By Exscientia’s AI Enters Clinical Trials

Oxford, UK-based Exscientia uses AI to design and create drug candidate molecules satisfying complex therapeutic requirements with revolutionary efficiency. Joint research by Exscientia with Sumitomo Dainippon Pharma Co., Ltd. (TYO:…
Venture Capital: Vinted, The Marketplace For Previously Owned Clothing, Raises $303M
May 13, 2021     News, Venture Capital

Vinted, a European startup that runs a marketplace for used clothing and home goods, announced its raise of $303 million at a valuation of $4.5 billion, post-money. That valuation is…
FinTech: German Regulator BaFin Hauls Up N26 On Money Laundering Lapses
May 13, 2021     FinTech, News

On Wednesday, Germany’s Federal Financial Supervisory Authority (BaFin) ordered challenger bank N26 to implement appropriate internal controls and safeguards and comply with general due diligence requirements to prevent money laundering…