A Research-Reviewed, Data-Driven Insight into Flood Risk Mapping and Analysis

Evaluating flood hazards using hydromechanical and hydrodynamic models to create flood risk maps is an ordinary non-structural way of directing floods. However, the absence of different types of data and the high rate of computational resources make it tough to apply in places with limited resources. Flood risk mapping is critical for minimizing the damage caused/occurring by floods and guarding communities. In this research, the aim is to enhance flood prediction and risk mapping by studying some known machine learning models like Random Forest (RF), Classification and Regression Tree (CART), and Support Vector Machine (SVM). Using a dataset [6] [7] that includes numerous features applicable to flood prediction. By examining these factors, the aim is to find accurate models that can help locate areas prone to flooding and which will eventually increase decision-making in flood management.