Evaluating different machine learning models for predicting municipal solid waste generation: a case study of Malaysia

Sarmad Dashti Latif, Nur Alyaa Binti Hazrin, Mohammad K. Younes, Ali Najah Ahmed () and Ahmed Elshafie
Additional contact information
Sarmad Dashti Latif: Soran University, Soran
Nur Alyaa Binti Hazrin: Universiti Tenaga Nasional
Mohammad K. Younes: Philadelphia University
Ali Najah Ahmed: Universiti Tenaga Nasional
Ahmed Elshafie: University of Malaya (UM)

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, 2024, vol. 26, issue 5, No 59, 12489-12512

Abstract: Abstract It is crucial for developing countries such as Malaysia to be able to accurately predict future municipal solid waste generations in order to achieve high-quality waste management. The previous machine algorithm applied in the proposed study area Malaysia was an artificial neural network using NARX inputs to accommodate the need of forecasting municipal solid waste generations in Malaysia. However, this approach is not highly accurate in today’s higher progressive state. Therefore, one of the aims of this research was to investigate the use of machine learning algorithms and its benefits. The machine learning algorithms investigated are specifically Gaussian process regression (GPR), ensemble of trees and neural networks. Each of these algorithms has its many strengths that could be altered according to the needs of users. For instance, various versions of neural networks are widely used for predicting municipal solid waste which includes the current approach adapted in the proposed study area. The findings indicated that the bagged tree model currently developed is not suitable for plotting a linear prediction although it managed to obtain a high performance of coefficient of determination (R2) = 0.92. Regarding GPR and neural network, the accuracy of the models was very high when every variable is included as a scenario which gives a perfect R2 = 1.00. The findings also showed that GPR and neural networks had the least error with root mean square error (RMSE) of 0.00009748 and 0.00099684, and mean absolute error (MAE) of 0.000071824 and 0.000672810, respectively. This study managed to fill in the gap of using GPR for predicting municipal solid waste generation. The outcome of this study could be of direct interest to public and private solid waste management companies in order to effectively manage solid waste through predicting the municipal solid waste generation accurately.

Keywords: Municipal solid waste; Waste management; Prediction model; Machine learning (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10668-023-03882-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:endesu:v:26:y:2024:i:5:d:10.1007_s10668-023-03882-x

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/10668

DOI: 10.1007/s10668-023-03882-x

Access Statistics for this article

Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development is currently edited by Luc Hens

More articles in Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().