<![CDATA[Air pollution poses a critical challenge in urban areas, including Indonesia, significantly affecting public health and the environment. While machine learning (ML) has been used to predict air pollution levels, integrating ML with urban management strategies for actionable policy recommendations remains underexplored. This study employs structural equation modeling (SEM) using SmartPLS to analyze air pollution metrics, ML predictive analytics, urban management strategies, environmental data sources, and policy recommendations. Based on responses from 400 experts in environmental science and urban management, the findings reveal that ML-driven insights significantly enhance urban management strategies and policy effectiveness. The study concludes by providing evidence-based recommendations for policymakers to improve air quality in urban areas, emphasizing the importance of integrating ML and data-driven approaches into sustainable urban management. These findings contribute to addressing Indonesia urgent air pollution crisis and advancing urban sustainability.]]>
Copyrights © 2024
