Prediction of Flood in Bangladesh Using Different Classifier Model

Abstract

Abstract: Different machine learning classifier models including Decision Tree, Naive Bayes, k-NN, and Random Forest are applied with a view to predicting the occurrence of flood in Bangladesh. It is seen that the Decision Tree model has performed well by achieving an accuracy of 94.23%. Bangladesh is a highly flood-prone country where flooding events cause significant damage to life, agriculture, infrastructure, and socio-economic stability each year. With limited resources and a major portion of the population living below the poverty line, flood impacts are severe. This study applies and compares multiple machine learning classifiers to predict flooding events in Bangladesh using historical meteorological data, providing a comparative analysis to understand which model delivers better prediction accuracy for practical flood management applications.