AI-Enhanced adaptive flood management: integrating multi-objective evolutionary optimization and real-time SCADA for the Muda River Basin

Mainly during the monsoon season, the Muda River Basin in northern Malaysia faces significant flood risks, threatening community safety, local infrastructure, and agricultural activities. Traditional flood management methods, which often rely on simplified empirical models, fall short in addressing the complex and dynamic nature of flood events in this region which prevents the hydromechanical infrastructure from being operated optimally. This study introduces an innovative AI-powered framework designed to enhance mechanical flood gates optimally in the Muda River Basin by integrating advanced machine learning techniques, real-time hydrological data, and automation technologies within an intelligent control system. The system features mechanical improvements such as automated hydraulic gate control for optimized discharge management and dynamic flood routing, all facilitated by a sophisticated SCADA architecture. These mechanical automation enhancements, combined with AI-driven models, improve the accuracy of flood predictions, enabling more effective, data-driven decision-making and adaptive flood control strategies. The results of this research demonstrate that AI-based flood management systems can significantly enhance operational resilience through optimal hydromechanical operation, improve flood prediction accuracy, and optimize water flow management, providing a scalable solution for mitigating flood risks in tropical river basins.