Abstract
Floods occurrences are the most hated environmental hazard around the world. This is due to floods threaten human life and furthermore affected the economy of the involved country. In Malaysia, floods are usually due to the season monsoon and heavy rains that causing flash floods usually in urban area. Therefore, it is a must for researchers around the world to find a solution in solving this problem. A reliable and practical flood prediction model is in needs to predict flood occurrence ahead of time. Thus, this paper proposed the modelling of flood prediction model using NNARX (Neural Network Autoregressive with Exogenous Input) and hybrid NNARX with EKF (Extended Kalman Filter). The area of study was Klang River. The model was developed using real-time SCADA data that were acquired from the Department of Irrigation and Drainage, Malaysia. The model development was based on flood water level data in meter from 6 Feb. to 21 Nov. 2010. Modelling made used of 120 samples data, model validation using 78 samples data and model testing using 170 samples. The model performance of the NNARX-EKF hybrid model showed much better result than the NNARX model.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
