Published Paper Details:

Efficient water resource management is essential for sustainable urban development, particularly in rapidly growing cities where demand patterns are influenced by environmental and demographic factors. This paper presents a data-driven water demand prediction framework using Random Forest regression to forecast future water consumption. The proposed system integrates historical water usage data, environmental parameters such as rainfall and temperature, reservoir storage levels, and population growth information obtained through external APIs. The framework consists of data collection, preprocessing, feature engineering, model training, prediction, and visualization modules. Time-series features and lag-based variables are generated to capture seasonal and temporal consumption patterns. The Random Forest regression model is employed due to its ability to handle nonlinear relationships, reduce overfitting through ensemble learning, and provide feature importance insights. Experimental evaluation demonstrates improved prediction accuracy compared to traditional statistical approaches. The predicted outputs are presented through an interactive dashboard to support water distribution planning and resource allocation. The proposed system provides a scalable and adaptive solution for smart water management, enabling authorities to make data-driven decisions for efficient and sustainable water supply management.