Abstract
Dredging operations are essential for maintaining navigable waterways, but determining the ideal time to dredge requires a multifaceted approach, incorporating both environmental and operational variables. This paper presents the Dredging Analysis and Decision Support System (DADSS), a data-driven solution that employs historical sedimentation data, weather patterns, and water flow statistics to optimize dredging decisions. The system leverages Random Forest Classifier and Regressor models to predict the need for dredging and estimate associated costs. Key inputs include sedimentation depth, water flow rate, sediment type, and precipitation levels. By providing real-time insights and cost-effective guidance without reliance on physical sensors, this solution enhances waterway management efficiency while reducing environmental impact. Results demonstrate a clear optimization in dredging operations with a reduced frequency of unnecessary dredging.