Earthquake monitoring is vital for evaluating seismic risks and facilitating prompt responses to seismic events. However, traditional methods often struggle with real-time detection and accurate alerting due to limitations in data processing and communication. Machine learning and Deep learning technologies offer promise in addressing these challenges. This study introduces an innovative earthquake monitoring system that harnesses the power of IoT devices alongside advanced machine and deep learning models. The system integrates hardware components to establish a robust monitoring infrastructure. Machine learning algorithms are used for rapid earthquake event classification, enabling timely alerts and effective risk mitigation strategies. Deep learning techniques enhance the system's ability to recognize complex seismic patterns efficiently. The Deep learning model is structured with multiple dense layers, including a SoftMax output layer for multi-class classification tasks. In addition to the hardware and modelling components, a dynamic web interface has been developed to provide users with real-time access to earthquake data, alerts, and monitoring status. The results of this study demonstrate significant advancements in earthquake detection accuracy and alerting efficiency. By combining IoT technologies with machine and deep learning algorithms, the system offers a comprehensive solution for enhancing earthquake monitoring practices.