Current advances and applications of artificial intelligence for smart municipal solid waste management: A review

Abstract

Globally, the rapid increase in industrialisation and urbanisation has led to exponential increase in municipal solid waste (MSW) generation rate, resulting in long-term environmental implications and hazardous. Artificial intelligence (AI) has emerged as a promising optimisation tool to address the complexities related to various aspects of MSW management. Presently, most of the review studies have primarily synthesised AI applications in a descriptive and stage-specific manner, offering limited assessment of cross-context model transferability, system integration, and interpretability challenges affecting real-world AI adoption in MSW management. Addressing these gaps, this review provides a comprehensive system-level synthesis of AI applications across the MSW management value chain. It also underscores the application of multi-fusion AI models in addressing critical challenges related to waste segregation accuracy, heterogeneous waste characterisation, dynamic route optimisation, treatment process variability, landfill emission forecasting, and real-time decision support for adaptive urban MSW management. It was evident that AI-driven model outperformed conventional methods by improving forecasting precision, enhancing waste classification, and process optimisation. Such as application of convolutional neural networks and ensemble learner models achieved high performance efficiency (90–95%) in automated waste segregation and forecasting. Similarly, AI-based routing and smart bin systems reduced travel distances, and fuel consumption by 20–30%, resulting in smooth operational management and environmental benefits. Overall, this article provides a foundational resource for researchers, policymakers, and practitioners striving to design innovative, data-driven solutions that support sustainable MSW management.