Adoption of Machine Learning for Sustainable Solid Waste Management

Abstract

Currently, Mauritius is adopting landfilling as the main waste management method, which makes the waste sector the second biggest emitter of greenhouse gas (GHG) in the country. This presents a challenge for the island to attain its commitments to reduce its GHG emissions to 30% by 2030 to cater for SDG 13 (Climate Action). Moreover, issues like eyesores caused by littering and overflowing of bins and low recycling rates due to low levels of waste segregation are adding to the obstacles for Mauritius to attain other SDGs like SDG 11 (Make Cities & Human Settlements Inclusive, Safe, Resilient & Sustainable) and SDG 12 (Guarantee Sustainable Consumption & Production Patterns). Therefore, together with an optimisation of waste collection, transportation and sorting processes, it is important to establish a solid waste characterisation to determine more sustainable waste management options for Mauritius to divert waste from the landfill. However, traditional waste characterisation is time consuming and costly. Thus, this chapter consists of looking at the feasibility of adopting machine learning to forecast the solid waste characteristics and to improve the solid waste management processes as per the concept of smart waste management for the island of Mauritius in line with reducing the current challenges being faced to attain SDGs 11, 12 and 13.

Citation

Jeetah, P., Somaroo, G., Surroop, D., Ragen, A.K. and Amode, N.S. (2024), "Adoption of Machine Learning for Sustainable Solid Waste Management", Fowdur, T.P., Rosunee, S., Ah King, R.T.F., Jeetah, P. and Gooroochurn, M. (Ed.) Artificial Intelligence, Engineering Systems and Sustainable Development, Emerald Publishing Limited, Leeds, pp. 17-28. https://doi.org/10.1108/978-1-83753-540-820241002