INTELLIGENT WATER LEAKAGE DETECTION AND MONITORING SYSTEM

Abstract

Water leakage in pipeline distribution systems is a major challenge that affects efficient water resource management and leads to significant water loss, increased maintenance costs, and reduced operational efficiency. This paper presents an Intelligent Water Leakage Detection and Monitoring System using machine learning for accurate leakage prediction. The proposed system analyzes multiple pipeline parameters, including pressure, flow rate, temperature, vibration, rotational speed (RPM), operational hours, zone, block, pipe identification, location code, latitude, and longitude. A Random Forest classifier is employed to classify pipeline conditions as leakage or nonleakage. The system is developed using Python and the Streamlit framework, providing an interactive interface for data input, leakage prediction, and result visualization. Model performance is evaluated using accuracy, precision, recall, F1-score, and confusion matrix. Experimental results demonstrate reliable predictions with high accuracy, enabling early leakage detection, reducing water wastage, minimizing maintenance costs, and supporting sustainable water distribution systems for smart city applications. KEYWORDS— The Water Leakage Detection, Machine Learning, Random Forest Classifier, Pipeline Monitoring, Smart Water Management, IoT Sensors, Predictive Analytics, Water Distribution Network, Leak Detection System.