Modeling of Annual Maximum Flows with Geographic Data Components and Artificial Neural Networks

Abstract

Disasters such as floods and floods are also encountered on the days when the highest flow is recorded, according to the Annual Maximum Flow (AMF) statistics. The Annual Maximum Flow is the highest flow rate ever recorded in a water year. Wherever this flow happens, it usually results in flooding. Snow melts and unexpected precipitation associated with temperature fluctuations are the two most important factors that create flooding. The deluge that follows kills people and destroys property in communities and agricultural lands. As a result, it's critical to predict the flow that causes flooding and take appropriate precautions to limit the damage. The prediction of the probability of the flood event in advance is very important for the safety of life and property of large masses and agricultural lands. Early warning systems, disaster management plans and minimizing these losses are among the important goals of the country's administration. In this study, It is used in five Current Observation Stations (COS) located in Yeşilırmak Basin in Turkey. By using 8 input data including geographical location, altitude and area information of these stations, AMF data were tried to be estimated for each COS. A total of 240 input data was used in the study. The data period covers the years 1964-2012. Unfortunately, AMF values cannot be monitored for all 5 stations used after 2012.Therefore, the data period was stopped in 2012. In this study, Multilayer Artificial Neural Networks (MANN), Generalized Artificial Neural Networks (GANN), Radial Based Artificial Neural Networks (RBANN) and Multiple Linear Regulation (MLR) methods were used. Input data sets were made into 4 packets and these packages were used respectively in both training and testing stages. Root mean square error (RMSE), mean absolute error (MAE) and correlation coefficient (R) were used as the comparison criteria. The results are as follow; MANN (8 Input) (RMSE = 119.118, MAE = 93.213, R = 0.808), and RBANN (2 Input) (RMSE = 111.559, MAE = 81.114, R = 0.900). These results show that AMF can be predicted with artificial intelligence techniques and can be used as an alternative method.