Flood Prediction using Supervised Machine Learning Algorithms

The most frequent type of calamity is flooding, which happens when water overflows and submerges normally dry terrain. Flood prediction models, which are typically based on historic data and specified thresholds, are intended to forecast when the water level will exceed a predetermined threshold. To minimize the complex numerical articulations of actual flood cycles, Machine Learning (ML) methods generate predictions about future events that are far more accurate than predictions made by humans. In this paper, various supervised machine learning algorithms are implemented. Among many ML techniques, classification is a widely used one. This paper uses various supervised learning algorithms, such as Logistic Regression, Random Forest, XGB classifier, ExtraTree classifier, LGBM classifier, and CatBoost classifier. Based on performance, supervised learning algorithm for flood prediction is analyzed and most appropriate models is predicted. This particular model can be effectively utilized by both the government and the general public to properly predict floods in advance.