A comparative analysis of classification techniques on predicting flood risk

Abstract

Flood is a temporary overflow of a dry area due to overflow of excess water, runoff surface waters or undermining of shoreline. In Malaysia itself in 2014, the country grieved with the catastrophic flood event in Kuala Krai, Kelantan, which caused of human lives, public assets and money lost. Due to uncertainties in flooding event, it is vital for Malaysia to have pre-warning system that assist related agencies in to categorize land areas that face high risk of flood so preventive actions can be planned in place. This paper conducts a comparative analysis of three classifications in classifying the risk of flood, whether high or low. The classification experiment conducts using three variants of Bayesian approaches, which are Bayesian Networks (BN), Naive Bayes (NB), and Tree Augmented Naive Bayes (TAN). The outcome of this research shows that Tree Augmented Naive Bayes (TAN) has the best algorithms as compared to others algorithms in classifying the risk of flood.