Gaussian Naïve Bayes Classification Algorithm for Drought and Flood Risk Reduction

Abstract

Natural disasters such as flood and drought have been declared as sources of setback to sustainable development efforts in countries where their risk is high (Mochizuki and Naqvi 2019). Rainfall patterns usually have spatial and temporal variability which affect the agricultural production, water supply, transportation, the entire economy of a region, and the existence of its people (Oduro-Afriyie and Adukpo 2006). In regions where the year-to-year variability is high, people often suffer great calamities due to floods or droughts. Whereas damage due to extremes of rainfall cannot be avoided completely, a forewarning could certainly be useful (Oduro-Afriyie and Adukpo 2006). Vargas and Paneque (2019) distinguished the difference between drought as a natural phenomenon and as a risk. As a natural phenomenon, drought is perceived as the availability of rainfall too less than normal at a place for a given period (Pita 2007; Aiyelokun et al. 2017); whereas, drought risk is the impact of decreased rainfall on the available water resources, while trying to maintain availability and demand (Vargas and Paneque 2017). Flood is risk is the probability of flood occurrence and its potential effects. Flood risk has been projected to amplify in many regions of the world as a result of climate change, urbanization, and population growth (Bradford et al. 2012; Liu et al. 2018). Flooding is globally perceived as a huge problem that impacts millions of people annually (Henstra et al. 2019) and has grown over the years in frequency and magnitude (Berghuijs et al.