Short-term water level forecast using ANN hybrid Gaussian-nonlinear autoregressive neural network

Wei, Ming Wong and Subramaniam, Siva Kumar and Feroz, Farah Shahnaz and Lew, Rose Ai Fen (2022) Short-term water level forecast using ANN hybrid Gaussian-nonlinear autoregressive neural network. International Journal of Integrated Engineering, 14 (4). pp. 425-437. ISSN 2229-838X

[img] Text
425-437-033 (1).PDF

Download (515kB)

Abstract

The aim of this study is to develop the best forecast model using hybrid Gaussian-Nonlinear Autoregressive Neural Network to forecast the water level with multiple hour ahead for Melaka River. The development of flood forecast models is crucial and has led to risk control, policy recommendations, a reduction in human life loss, and a reduction in flood-related property destruction. In this research, Artificial Neural Network (ANN) approach was used to forecast flood by modeling and forecasting water level time series . ANN approach was selected due to its high reputation abilities to learn from the time-series data pattern. A total of 2782 data for the period of one month was used in ANN training, validation, and testing to forecast the flash flood. In this study , Hybrid Gaussian Nonlinear Autoregressive Neural Network (Gaussian-NAR) was used as the ANN approach to forecasting the water level time series. This study's primary focus is to find the most appropriate forecast model to forecast the water level in multiple time steps ahead, which are 1 hour, 3 hours, 5 hours, and 7 hours. The forecast accuracy measures are measured using the Pearson R and R-squared to find the most accurate model for this multiple time-step ahead. The result indicates that with 7 hours forecast ahead, the R squared is 86.7%. The best model in the Gaussian-NAR forecast is a 3-hour water level forecast with the R squared of 99.8 percent and had the best model performance result.

Item Type: Article
Uncontrolled Keywords: Flood, Forecast, ANN, NAR, Gaussian
Divisions: Faculty of Electronics and Computer Engineering
Depositing User: mr eiisaa ahyead
Date Deposited: 28 Mar 2023 10:46
Last Modified: 28 Mar 2023 10:46
URI: http://eprints.utem.edu.my/id/eprint/26759
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item