Flood Prediction Modeling Using Hybrid BPN-EKF And Hybrid ENN-EKF: A Comparative Study

Recently, artificial neural networks have been successfully applied to various hydrologic problems. This paper proposed flood water level modeling using the Hybrid of Back Propagation Neural Network with Extended Kalman Filter and the Hybrid of Elman Neural Network with Extended Kalman Filter that using the water level data from Sungai Kelang which is located at Jambatan Petaling, Kuala Lumpur. The models were developed by processing offline data over time using neural network architecture. The methodologies and techniques of the two models were presented in this paper and comparison of the long term runoff time prediction results between them were also conducted. The prediction results using both hybrid models showed satisfactory and reliable performances for flood water level prediction. Keywords—Back Propagation Neural Network (BPN); Extended Kalman Filter (EKF); Elman Neural Network (ENN);