An integrated AI-IoT framework for urban pollution source detection and sustainable Smart-City Governance

Abstract

Urban air pollution remains a major challenge to sustainable city development because traditional monitoring systems have limited capacity to address complex and dynamic urban environments. Although Artificial Intelligence (AI) and Internet of Things (IoT) technologies have demonstrated considerable potential for environmental monitoring, existing approaches often emphasize individual technical capabilities while giving limited attention to governance transparency, ethical deployment, and sustainability alignment. This study proposes an integrated AI-IoT conceptual framework for urban pollution source detection and sustainable smart-city governance. The framework integrates multi-source environmental sensing, data processing, AI-driven forecasting and pollution source attribution, intelligent decision support, ethical AI governance, and Sustainable Development Goal (SDG) alignment within a unified six-layer architecture. Its conceptual grounding is assessed through structured literature mapping, comparative analysis of existing AI-based urban monitoring frameworks, and case-study mapping using a published IoT-enabled environmental monitoring application. The framework establishes an end-to-end pathway connecting environmental observations with pollution intelligence, policy-oriented decision support, responsible governance, and measurable sustainability outcomes. It also identifies key implementation challenges involving data privacy, algorithmic bias, explainability, interoperability, scalability, and deployment constraints. The proposed architecture provides a structured foundation for future implementation and empirical evaluation of intelligent, ethical, and sustainability-oriented urban pollution management systems.