The rapid urbanization of cities worldwide has intensified environmental challenges such as air pollution, water contamination, noise pollution, and climate variability. These challenges necessitate the adoption of intelligent and scalable monitoring systems to support sustainable urban development. This study proposes an AI-based Environmental Monitoring System designed to enhance real-time data collection, analysis, and decision-making within smart city ecosystems. The proposed system integrates Internet of Things (IoT) sensors, cloud computing, and artificial intelligence algorithms to monitor environmental parameters including air quality, temperature, humidity, water quality, and noise levels. Machine learning models are employed to analyze large-scale environmental data, detect anomalies, and generate predictive insights for proactive environmental management. The framework introduces a multi-layer architecture comprising data acquisition, data processing, analytics, and decision-support layers. This architecture enables efficient data flow, scalability, and real-time responsiveness. The system also incorporates sustainability indicators aligned with global environmental standards to support policy formulation and urban planning. The findings highlight that AI-driven monitoring significantly improves environmental awareness, reduces response time to environmental hazards, and supports data-driven governance. This research contributes to the development of sustainable smart cities by providing a scalable and intelligent environmental monitoring framework that enhances urban resilience and environmental sustainability.