Scalable Cloud-Edge AI Framework for Precision Irrigation and Crop Health Monitoring using IOT Data Streams

Precision agriculture requires timely insights derived from heterogeneous sensor data to improve irrigation efficiency and maintain crop health. Traditional centralized monitoring systems often suffer from high latency, limited scalability, and delayed decision-making when handling continuous agricultural data streams. This paper presents the design and implementation of a scalable cloud-edge integrated framework for real-time agricultural monitoring. The proposed system combines IoT-based sensor data collection at the field level with cloud-based stream processing and analytics to enable continuous monitoring of environmental parameters such as temperature, humidity, soil moisture, light intensity, pH, and nutrient levels. A distributed ingestion pipeline using MQTT and Apache Kafka ensures reliable and scalable data transmission, while real-time stream processing enables dynamic alert generation and decision support for irrigation and crop health assessment. Historical data is stored in a time-series format to support trend analysis and visualization. Experimental evaluation using a simulated agricultural environment demonstrates the system’s ability to process sensor data in real time, detect abnormal conditions, and provide actionable recommendations. The results highlight the effectiveness of cloud–edge integration in supporting precision irrigation and proactive crop health management.