Flood Prediction Using ARIMA Model In Sungai Melaka, Malaysia

Wong, Wei Ming and Subramaniam, Siva Kumar and Feroz, Farah Shahnaz and M. Subramaniam, Indra Devi and Lew, Rose Ai Fen (2020) Flood Prediction Using ARIMA Model In Sungai Melaka, Malaysia. International Journal of Advanced Trends in Computer Science and Engineering, 9 (4). pp. 5287-5295. ISSN 2278-3091

[img] Text

Download (767kB)


The aim of this study is to develop a flood prediction model by analyzing the real-time flood parameters for Pengkalan Rama, Melaka river hereafter known as Sungai Melaka using the Box-Jenkins method. Hourly water levels are predicted to alleviate flood related problems caused by the overflow of Sungai Melaka.. The time series from 7 January 2020 12.00 am until 15 January 2020 8.00 am was used to check the stationarity by using the Augmented Dickey-Fuller (ADF) and differencing method to make a non-stationary time series stationary. The main methods used for model identification with autocorrelation (ACF) function and partial autocorrelation function (PACF) are visual observation of the series. The best ARIMA model was identified by the parameter Akaike Information Information Criterion (AIC) and the Bayesian Information Criterion (BIC). The best ARIMA model for the Pengkalan Rama was ARIMA (2, 1, 2) with the AIC value 1297.5 and BIC value 1304.6. The time series had lead forecast up to 8 hours generated by using the ARIMA (2, 1, 2) model. The accuracy of the model was checked by comparing the original series and forecast series. The result of this research indicated that the ARIMA model is adequate for Sungai Melaka. In conclusion, ARIMA model is an adequate short term forecast of water level with the lead forecast of up to 8 hours. Hence, it is indubitable that the ARIMA model is suitable for river flood.

Item Type: Article
Uncontrolled Keywords: ARIMA, Flood, Forecast, Melaka, Prediction
Divisions: Faculty of Electronics and Computer Engineering
Depositing User: Sabariah Ismail
Date Deposited: 19 Aug 2021 09:03
Last Modified: 19 Aug 2021 09:03
URI: http://eprints.utem.edu.my/id/eprint/25229
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item