Developing a sustainable waste-to-energy framework for Saudi Arabia through an artificial intelligence-driven systematic review

Municipal solid waste (MSW) generation in Saudi Arabia has increased rapidly due to urbanization, population growth, and religious tourism, creating significant challenges for sustainable waste management and energy recovery. This study presents a systematic review of artificial intelligence (AI)-enabled predictive analytics for municipal solid waste management and waste-to-energy (WtE) systems, with a particular focus on Saudi Arabia. Following the PRISMA framework, literature published between 2020 and 2025 was systematically reviewed to evaluate the applications of artificial intelligence, machine learning (ML), and deep learning (DL) in waste classification, waste generation forecasting, energy yield prediction, operational optimization, and smart-grid integration. The reviewed literature indicates that AI-based models achieved waste-classification accuracies of up to 96% and process-level prediction performance exceeding R² = 0.99, while deep learning and hybrid models consistently outperformed conventional statistical approaches in forecasting, classification, and operational optimization. Quantitative evidence further highlights Saudi Arabia’s unique waste-management context, including annual MSW generation of approximately 15–16 million tons, an organic waste fraction of 40–60%, seasonal waste surges exceeding 473,000 tons during Hajj, and environmental challenges associated with temperatures above 45 °C and frequent dust storms. Compared with previous review studies, this review provides a comprehensive regional perspective by integrating AI applications with Saudi Arabia’s environmental conditions, smart-city infrastructure, and national sustainability priorities. Furthermore, it critically evaluates the strengths, limitations, scalability, and practical applicability of existing AI approaches while identifying key research gaps and future opportunities. A Saudi-specific AI–WtE framework is proposed, supported by an integrated data-to-decision pipeline incorporating Explainable AI (XAI) and uncertainty-aware analytics to enhance transparent and adaptive decision-making. A scenario-based conceptual analysis using Riyadh as a representative case study demonstrates the potential of AI-enabled strategies to improve energy recovery, operational efficiency, and infrastructure planning compared with conventional approaches. Finally, a phased implementation roadmap aligned with Saudi Vision 2030 and circular economy objectives is presented to facilitate the transition from conventional waste management to intelligent, resilient, and sustainable AI-enabled Waste-to-Energy systems.