Forecasting river discharge using autoregressive integrated moving-average model
In water resources management, forecasting is an activity that very beneficial for future extension. Since there are many methodologies which can be used for time series forecasting but there are many discussion on which model produces the best result. The main objective of this study is to evaluate...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
2014
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In water resources management, forecasting is an activity that very beneficial for future extension. Since there are many methodologies which can be used for time series forecasting but there are many discussion on which model produces the best result. The main objective of this study is to evaluate the performance of autoregressive integrated moving average (ARIMA) by using ‘Statistical Packages for Social Science’ (SPSS) software. In order to investigate the performance of forecasting is analyzed by using mean absolute percentage error (MAPE), root mean squared error (RMSE) and coefficient of determination (R2). With assistance of Auto Regressive Integrated Moving Average (ARIMA) Models, flow records from two different gauging stations from two different rivers have been collected for this study. The data was obtained from Department of Irrigation and Drainage (DID), Malaysia. They are streamflow station 2235401 at the Kahang River, streamflow station 2237471 at Lenggor River and another rainfall station 2032071 at Ladang Kian Hoe for Batu Pahat river basin. ARIMA has been used to find out the ability in forecasting of monthly discharge for short term forecast with various pattern and rivers trend. From this study, the generated data for station 2235401 at Kahang Rivers shows that the ARIMA(1,1,1)(0,1,1)12 model produce better results with MAPE, RMSE and R2 are 216.738, 49.338 and 0.249 respectively. For station 2237471 at Lenggor River, the data obtained shows that ARIMA(0,1,1)(0,1,1)12 model produce better results with MAPE, RMSE and R2 are 399.921, 42.204 and 0.584. Therefore the result shows that ARIMA model are practical and feasible for streamflow forecasting |
|---|