Early Warning System for Flood Disaster Prediction in Wetland Area in Greater Yola Using Adaptive Neuro Fuzzy Inference System

Abstract

Natural calamity disrupts our daily life activities; thereby bring many sufferings in our life. One of the natural disasters is the flood. Flood is one of the most catastrophic disasters. However, too much rainfall courses environmental hazard. These prompted to flood prediction in order to help communities and Government with the necessary tool to take precaution to safe human life and properties. This work was developed using an (ANFIS) Adaptive Neuro-Fuzzy Inference System to compare some weather parameter (temperature and relative humidity) with rainfall to forecast the amount of rainfall capable of coursing flood in the study area. From the above graph (Fig. 22) it can be seen that the actual and the forecasted rainfall followed the same pattern from 2008 to 2010 with slight decrease in 2011. A high amount of rainfall in 2012 was forecasted to be flooded during that year and tally with the forecasted rainfall on the above graph in 2012. Based on the results on the graph, it shows that from 2014 to 2017 gives a constant flow between the actual and forecasted rainfall. It is predicted that the maximum amount of rainfall forecasted was 124.0 mm which is far below the recommended flood level of 160.0 mm which reveals that, River Benue would not experience flood disaster in the year ahead. The model developed was validated using (MAPE) Mean Absolute Percentage Error as 4.0% with model efficiency of 96.0% which shows very high excellent prediction accuracy.