Flood prediction near Yamuna express way a case study on Delhi

The area lies near Yamuna River in Delhi faces a frequent flood event, and with the increasing frequency and intensity of flood events highly impacted the human lives, infrastructure, and agriculture. Hence, there is a great need of accurate and timely flood prediction models. Traditional hydrological models are useful but often inaccurate for effective disaster management. The new technologies like machine learning are showing a prominent solution for the complex problems like flood. Therefore, this study conducts a comprehensive analysis of advanced ML(machine learning) techniques: Logistic Regression or named as LR, Support Vector Machines named as SVM, Random Forest named as (RF)and XG-Boost, in predicting floods in the area lies near Yamuna River by using GIS, Remote sensing data and seven flood influencing factors. The performance of the models is tested by using performance metrics such as accuracy, recall, Fl-score and precision. Further, the models were also validated using curve of AUC-ROC. The outputs reveal that XG-Boost out performs the other models in prediction accuracy. Logistic Regression and SVM also perform well, giving them viable options depending on the application scenario. This study examines the benefits and weaknesses of each model and recommends their use in flood-prone area near Yamuna River.