3 Hours ahead of time flood water level prediction using NNARX structure: Case study pahang

Flood is defined as an overflow of large amount of water beyond its normal limits. Therefore, it has become threat to people's life and can cause damages to properties. However, in Malaysia, the only existing flood warning system are the alarming system which only notify residents nearby flood location to evacuate only when flood occur. Thus, flood water level prediction is very much needed in order to prevent flood disaster to happen. One of the effective techniques which frequently used to solve nonlinear cases such as flood is Artificial Neural Network (ANN). Therefore, this paper proposed 3 hours flood water level prediction using Neural Network Autoregressive model with Exogenous Input (NNARX) technique. The area involved in this study was along Pahang river basin where the flood location is situated at Mentakab. Four input parameters were fed in to the NNARX model to predict flood 3 hours ahead of time. The inputs were carefully selected during flood events. The samples used for training, validation and testing stage are 1553, 1997 and 4000 samples respectively. The NNARX flood prediction model developed using Matlab Neural Network Toolbox. Result shows satisfactory performance with low error measures.

[1]  Ramli Adnan,et al.  Flood modelling using Artificial Neural Network , 2013, 2013 IEEE 4th Control and System Graduate Research Colloquium.

[2]  Christian W. Dawson,et al.  Evaluation of artificial neural network techniques for flow forecasting in the River Yangtze , China 619 , 2002 .

[3]  S. Ghosh.  Flood control and drainage engineering , 1997 .

[4]  Ramli Adnan,et al.  Flood water level modeling and prediction using NARX neural network: Case study at Kelang river , 2014, 2014 IEEE 10th International Colloquium on Signal Processing and its Applications.

[5]  F ROSENBLATT,et al.  The perceptron: a probabilistic model for information storage and organization in the brain. , 1958, Psychological review.

[6]  Hilmi Berk Celikoglu,et al.  Modelling public transport trips by radial basis function neural networks , 2007, Math. Comput. Model..

[7]  Paulin Coulibaly,et al.  Groundwater level forecasting using artificial neural networks , 2005 .

[8]  M. Vaziri.  Predicting Caspian Sea Surface Water Level by ANN and ARIMA Models , 1997 .

[9]  Ramli Adnan,et al.  7 hours flood prediction modelling using NNARX structure: Case study Terengganu , 2016, 2016 IEEE 12th International Colloquium on Signal Processing & Its Applications (CSPA).

[10]  Ramli Adnan,et al.  5 hours flood prediction modeling using NNARX structure: case study Kuala Lumpur , 2014, 2014 IEEE 4th International Conference on System Engineering and Technology (ICSET).

[11]  Vahid Nourani,et al.  An ANN‐based model for spatiotemporal groundwater level forecasting , 2008 .

[12]  A. Ghanbarzadeh,et al.  The potential of different artificial neural network (ANN) techniques in daily global solar radiation modeling based on meteorological data , 2010 .