Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River)
Forecasting river flow using current models like time series, Physical-theoretical and regression models are very important in water resources management. In this study monthly and daily discharge of Barandouz-Chai River for period of 37 years have been used in order to linear ARMA and Nonlinear Bil...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Shahid Chamran University of Ahvaz
2014-09-01
|
| Series: | علوم و مهندسی آبیاری |
| Subjects: | |
| Online Access: | http://jise.scu.ac.ir/article_10849_840c0cd04f26f79042d09332a5acb7c5.pdf |
| _version_ | 1831758455866654720 |
|---|---|
| author | Farshad Ahmadi Yaaghob Dinpazhooh Ahmad Fakherifard Keyvan Khalili |
| author_facet | Farshad Ahmadi Yaaghob Dinpazhooh Ahmad Fakherifard Keyvan Khalili |
| author_sort | Farshad Ahmadi |
| collection | DOAJ |
| description | Forecasting river flow using current models like time series, Physical-theoretical and regression models are very important in water resources management. In this study monthly and daily discharge of Barandouz-Chai River for period of 37 years have been used in order to linear ARMA and Nonlinear Bilinear models. ADF test has been used for stationarity test. Result showed removing nonstasionarity components cause to river series became stationary. For nonlinearity rate of monthly and daily streamflow series BDS test has been employed. As results showed monthly series detect low nonlinearity but daily series has high nonlinearity dependence. For monthly series AR(8) and BL(8,0,1,1) selected as the best models. Regression coefficient and root mean square error of these models are 0.906 and 2.892 (m<sup>3</sup>/s) for linear model and 0.930 and 2.436 (m<sup>3</sup>/s) for nonlinear model respectively. For daily streamflow series, AR(25) and BL(25,0,1,1) were best models with regression coefficient and root mean square error equal to 0.873 and 4.116 (m<sup>3</sup>/s) for linear model and 0.923 and 3.085 (m<sup>3</sup>/s) for nonlinear model respectively. According to results using bilinear nonlinear model cause to reduction error of daily model up to 33 percent and increased regression coefficient to 5.7 percent. Because of high nonlinearity rate of daily streamflow series the bilinear model accuracy increased. |
| first_indexed | 2024-12-22T00:48:53Z |
| format | Article |
| id | doaj.art-89b598b724f940369110b15d9192ec14 |
| institution | Directory Open Access Journal |
| issn | 2588-5952 2588-5960 |
| language | fas |
| last_indexed | 2024-12-22T00:48:53Z |
| publishDate | 2014-09-01 |
| publisher | Shahid Chamran University of Ahvaz |
| record_format | Article |
| series | علوم و مهندسی آبیاری |
| spelling | doaj.art-89b598b724f940369110b15d9192ec142022-12-21T18:44:29ZfasShahid Chamran University of Ahvazعلوم و مهندسی آبیاری2588-59522588-59602014-09-013719310510849Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River)Farshad Ahmadi0Yaaghob Dinpazhooh1Ahmad Fakherifard2Keyvan Khalili3Msc student, Tabriz University, Tabriz, Iran.Assosicate Professor, Tabriz University, Tabriz, Iran.Professor, Tabriz University, Tabriz, Iran.Assistant Professor, Urmia University, Urmia, Iran.Forecasting river flow using current models like time series, Physical-theoretical and regression models are very important in water resources management. In this study monthly and daily discharge of Barandouz-Chai River for period of 37 years have been used in order to linear ARMA and Nonlinear Bilinear models. ADF test has been used for stationarity test. Result showed removing nonstasionarity components cause to river series became stationary. For nonlinearity rate of monthly and daily streamflow series BDS test has been employed. As results showed monthly series detect low nonlinearity but daily series has high nonlinearity dependence. For monthly series AR(8) and BL(8,0,1,1) selected as the best models. Regression coefficient and root mean square error of these models are 0.906 and 2.892 (m<sup>3</sup>/s) for linear model and 0.930 and 2.436 (m<sup>3</sup>/s) for nonlinear model respectively. For daily streamflow series, AR(25) and BL(25,0,1,1) were best models with regression coefficient and root mean square error equal to 0.873 and 4.116 (m<sup>3</sup>/s) for linear model and 0.923 and 3.085 (m<sup>3</sup>/s) for nonlinear model respectively. According to results using bilinear nonlinear model cause to reduction error of daily model up to 33 percent and increased regression coefficient to 5.7 percent. Because of high nonlinearity rate of daily streamflow series the bilinear model accuracy increased.http://jise.scu.ac.ir/article_10849_840c0cd04f26f79042d09332a5acb7c5.pdfadf testbds teststationaritytime seriesbilinear model |
| spellingShingle | Farshad Ahmadi Yaaghob Dinpazhooh Ahmad Fakherifard Keyvan Khalili Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River) علوم و مهندسی آبیاری adf test bds test stationarity time series bilinear model |
| title | Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River) |
| title_full | Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River) |
| title_fullStr | Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River) |
| title_full_unstemmed | Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River) |
| title_short | Comparing Linear and Nonlinear Time Series Models in River Flow Forecasting (Case Study: Baranduz-chai River) |
| title_sort | comparing linear and nonlinear time series models in river flow forecasting case study baranduz chai river |
| topic | adf test bds test stationarity time series bilinear model |
| url | http://jise.scu.ac.ir/article_10849_840c0cd04f26f79042d09332a5acb7c5.pdf |
| work_keys_str_mv | AT farshadahmadi comparinglinearandnonlineartimeseriesmodelsinriverflowforecastingcasestudybaranduzchairiver AT yaaghobdinpazhooh comparinglinearandnonlineartimeseriesmodelsinriverflowforecastingcasestudybaranduzchairiver AT ahmadfakherifard comparinglinearandnonlineartimeseriesmodelsinriverflowforecastingcasestudybaranduzchairiver AT keyvankhalili comparinglinearandnonlineartimeseriesmodelsinriverflowforecastingcasestudybaranduzchairiver |