Integrating clustering algorithms and machine learning to optimize regional snapshot municipal solid waste management for achieving sustainable development goals
Issued Date
2025-04-01
Resource Type
ISSN
26667657
Scopus ID
2-s2.0-85211981608
Journal Title
Environmental Advances
Volume
19
Rights Holder(s)
SCOPUS
Bibliographic Citation
Environmental Advances Vol.19 (2025)
Suggested Citation
Taweesan A., Kanabkaew T., Surinkul N., Polprasert C. Integrating clustering algorithms and machine learning to optimize regional snapshot municipal solid waste management for achieving sustainable development goals. Environmental Advances Vol.19 (2025). doi:10.1016/j.envadv.2024.100607 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/102809
Title
Integrating clustering algorithms and machine learning to optimize regional snapshot municipal solid waste management for achieving sustainable development goals
Author(s)
Author's Affiliation
Corresponding Author(s)
Other Contributor(s)
Abstract
Effective municipal solid waste management (MSWM) is essential for sustainable urban development, significantly impacting environmental health, economic efficiency, and social well-being. It aligns with Sustainable Development Goal 11 (SDG11), which aims to make cities inclusive, safe, resilient, and sustainable by ensuring waste is safely managed from collection to disposal. This study evaluates the performance of MSWM practices across various cities in different regions, updated as of March 2023, to assess the achievement of SDG11. By reviewing published literature and conducting questionnaire surveys and key informant interviews with government authorities and service providers, data on access to managed MSW facilities were collected from 470 cities across various income-level regions to monitor MSWM progress toward SDG11 targets. Clustering algorithms and machine learning were employed to identify patterns and enhance MSWM practices across these regions, focusing on achieving SDG11. Hierarchical cluster analysis identified four clusters based on MSWM performance: high-income, upper-middle-income, lower-middle-income, and low-income regions. The developed decision-tree models provided a comprehensive analysis of effective MSW collection and disposal, achieving accuracies of approximately 75 % and 73 %, respectively. The models highlighted the importance of high collection coverage, proper disposal facilities, and robust institutional frameworks in achieving effective MSWM. The findings emphasize the need for targeted interventions and advanced analytical methods to enhance regional MSWM strategies, supporting the attainment of SDG11.