Flood prediction using machine learning models

Abstract

Floods are one of nature’s most catastrophic calamities which cause irreversible and immense damage to human life, agriculture, infrastructure and socio-economic system. Floods are one of Bangladesh’s most common natural catastrophes, causing modest to large-scale devastation every year. As a poor-economy developing country, taking structural steps to manage floods in the world’s great rivers is a major problem. Several studies on flood catastrophe management and flood forecasting systems have been conducted. The accurate prediction of the onset and progression of floods in real time is challenging. To estimate water levels and velocities across a large area, it is necessary to combine data with computationally demanding flood propagation models. This paper aims to reduce the extreme risks of this natural disaster and also contributes to policy suggestions by providing a prediction for floods using different machine learning models. This prediction will be done by analyzing different parameters like temperature, area, water level, soil moisture, rainfall, etc which are some of the hydrological and climatic factors that influence flooding. This research will use Binary Logistic Regression, K-Nearest Neighbour (KNN), Support Vector Classifier (SVC), Decision tree Classifier and Stacked Generalization (Stacking) to provide an accurate prediction. With the outcome, a comparative analysis will be conducted to understand which model delivers a better accuracy.