Time series modelling of Klang River flow

Abstract

Klang River is one of the main urban rivers in Malaysia, which passes through the capital of the country. Prediction of river flow constitutes one of the most important applications in hydrology and water resources management. One of the most well-known techniques among several methods for this purpose is the Autoregressive Moving Average (ARMA) model. This study aims to model the river flow and predict the future water-level at Klang River. The data used to construct the model consist of 2713 daily water-level (m) measurements obtained from the Sulaiman telemetric station. Results indicate that a minimum corrected Akaike’s Information Criteria (AICC) based ARMA(11,7) model is appropriate for this set of data.