Prediction of Flood in Bangladesh using k-Nearest Neighbors Algorithm

Noushin Gauhar, Sunanda Das, Khadiza Sarwar Moury

20212021 2nd International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST)40 citationsDOI

Abstract

Bangladesh is a flood-prone country. With limited resources and a major portion of the population living below the poverty line, flood impacts are severe. Deaths, malnutrition, widespread diseases, damage to infrastructure, disruption in the economy are some of the after-effects of this cataclysm. In order to put a flood management system into effect, it is essential to predict flooding events ahead of time. In this work, we applied different correlation coefficients for feature selection and k-nearest neighbors (k-NN) algorithm for the prediction of flood. The detailed result analysis shows that we achieved a high testing accuracy of 94.91%, average precision of 92.00% and an average recall of 91.00% using the k-NN machine learning model.

Topics & Concepts

Flood mythFlooding (psychology)Computer sciencePovertyPopulationk-nearest neighbors algorithmAlgorithmFeature selectionMachine learningArtificial intelligenceGeographyDemographyEconomic growthEconomicsPsychotherapistPsychologyArchaeologySociologyFlood Risk Assessment and ManagementHydrological Forecasting Using AIAnomaly Detection Techniques and Applications