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

Simple item page
dc.citedby1
dc.contributor.authorLatif S.D.en_US
dc.contributor.authorHazrin N.A.B.en_US
dc.contributor.authorYounes M.K.en_US
dc.contributor.authorAhmed A.N.en_US
dc.contributor.authorElshafie A.en_US
dc.contributor.authorid57216081524en_US
dc.contributor.authorid58550394200en_US
dc.contributor.authorid55966376900en_US
dc.contributor.authorid57214837520en_US
dc.contributor.authorid16068189400en_US
dc.date.accessioned2025-03-03T07:43:15Z
dc.date.available2025-03-03T07:43:15Z
dc.date.issued2024
dc.description.abstractIt 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. ? The Author(s), under exclusive licence to Springer Nature B.V. 2023.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.1007/s10668-023-03882-x
dc.identifier.epage12512
dc.identifier.issue5
dc.identifier.scopus2-s2.0-85173004744
dc.identifier.spage12489
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85173004744&doi=10.1007%2fs10668-023-03882-x&partnerID=40&md5=170f574f3167bba7045765e1faf97cc9
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/36590
dc.identifier.volume26
dc.pagecount23
dc.publisherSpringer Science and Business Media B.V.en_US
dc.sourceScopus
dc.sourcetitleEnvironment, Development and Sustainability
dc.subjectMalaysia
dc.subjectmachine learning
dc.subjectmunicipal solid waste
dc.subjectnumerical model
dc.subjectprediction
dc.subjectwaste management
dc.titleEvaluating different machine learning models for predicting municipal solid waste generation: a case study of Malaysiaen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS