A wavelet-SARIMA-ANN hybrid model for precipitation forecasting
Given its importance in water resources management, particularly in terms of minimizing flood or drought hazards, precipitation forecasting has seen a wide variety of approaches tested. As monthly precipitation time series have nonlinear features and multiple time scales, wavelet, seasonal auto regr...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Polish Academy of Sciences
2016-03-01
|
| Series: | Journal of Water and Land Development |
| Subjects: | |
| Online Access: | http://www.degruyter.com/view/j/jwld.2016.28.issue-1/jwld-2016-0003/jwld-2016-0003.xml?format=INT |
| _version_ | 1797759517400760320 |
|---|---|
| author | Shafaei Maryam Adamowski Jan Fakheri-Fard Ahmad Dinpashoh Yagob Adamowski Kazimierz |
| author_facet | Shafaei Maryam Adamowski Jan Fakheri-Fard Ahmad Dinpashoh Yagob Adamowski Kazimierz |
| author_sort | Shafaei Maryam |
| collection | DOAJ |
| description | Given its importance in water resources management, particularly in terms of minimizing flood or drought hazards, precipitation forecasting has seen a wide variety of approaches tested. As monthly precipitation time series have nonlinear features and multiple time scales, wavelet, seasonal auto regressive integrated moving average (SARIMA) and hybrid artificial neural network (ANN) methods were tested for their ability to accurately predict monthly precipitation. A 40-year (1970–2009) precipitation time series from Iran’s Nahavand meteorological station (34°12’N lat., 48°22’E long.) was decomposed into one low frequency subseries and several high frequency sub-series by wavelet transform. The low frequency sub-series were predicted with a SARIMA model, while high frequency subseries were predicted with an ANN. Finally, the predicted subseries were reconstructed to predict the precipitation of future single months. Comparing model-generated values with observed data, the wavelet-SARIMA-ANN model was seen to outperform wavelet-ANN and wavelet-SARIMA models in terms of precipitation forecasting accuracy. |
| first_indexed | 2024-03-12T18:45:32Z |
| format | Article |
| id | doaj.art-4960521a50da4565b49428d60fc9d76e |
| institution | Directory Open Access Journal |
| issn | 2083-4535 |
| language | English |
| last_indexed | 2024-03-12T18:45:32Z |
| publishDate | 2016-03-01 |
| publisher | Polish Academy of Sciences |
| record_format | Article |
| series | Journal of Water and Land Development |
| spelling | doaj.art-4960521a50da4565b49428d60fc9d76e2023-08-02T07:40:11ZengPolish Academy of SciencesJournal of Water and Land Development2083-45352016-03-01281273610.1515/jwld-2016-0003jwld-2016-0003A wavelet-SARIMA-ANN hybrid model for precipitation forecastingShafaei MaryamAdamowski JanFakheri-Fard AhmadDinpashoh YagobAdamowski KazimierzGiven its importance in water resources management, particularly in terms of minimizing flood or drought hazards, precipitation forecasting has seen a wide variety of approaches tested. As monthly precipitation time series have nonlinear features and multiple time scales, wavelet, seasonal auto regressive integrated moving average (SARIMA) and hybrid artificial neural network (ANN) methods were tested for their ability to accurately predict monthly precipitation. A 40-year (1970–2009) precipitation time series from Iran’s Nahavand meteorological station (34°12’N lat., 48°22’E long.) was decomposed into one low frequency subseries and several high frequency sub-series by wavelet transform. The low frequency sub-series were predicted with a SARIMA model, while high frequency subseries were predicted with an ANN. Finally, the predicted subseries were reconstructed to predict the precipitation of future single months. Comparing model-generated values with observed data, the wavelet-SARIMA-ANN model was seen to outperform wavelet-ANN and wavelet-SARIMA models in terms of precipitation forecasting accuracy.http://www.degruyter.com/view/j/jwld.2016.28.issue-1/jwld-2016-0003/jwld-2016-0003.xml?format=INTartificial neural network (ANN)precipitation forecastingseasonal auto regressive integrated moving average (SARIMA)water resources managementwavelet |
| spellingShingle | Shafaei Maryam Adamowski Jan Fakheri-Fard Ahmad Dinpashoh Yagob Adamowski Kazimierz A wavelet-SARIMA-ANN hybrid model for precipitation forecasting Journal of Water and Land Development artificial neural network (ANN) precipitation forecasting seasonal auto regressive integrated moving average (SARIMA) water resources management wavelet |
| title | A wavelet-SARIMA-ANN hybrid model for precipitation forecasting |
| title_full | A wavelet-SARIMA-ANN hybrid model for precipitation forecasting |
| title_fullStr | A wavelet-SARIMA-ANN hybrid model for precipitation forecasting |
| title_full_unstemmed | A wavelet-SARIMA-ANN hybrid model for precipitation forecasting |
| title_short | A wavelet-SARIMA-ANN hybrid model for precipitation forecasting |
| title_sort | wavelet sarima ann hybrid model for precipitation forecasting |
| topic | artificial neural network (ANN) precipitation forecasting seasonal auto regressive integrated moving average (SARIMA) water resources management wavelet |
| url | http://www.degruyter.com/view/j/jwld.2016.28.issue-1/jwld-2016-0003/jwld-2016-0003.xml?format=INT |
| work_keys_str_mv | AT shafaeimaryam awaveletsarimaannhybridmodelforprecipitationforecasting AT adamowskijan awaveletsarimaannhybridmodelforprecipitationforecasting AT fakherifardahmad awaveletsarimaannhybridmodelforprecipitationforecasting AT dinpashohyagob awaveletsarimaannhybridmodelforprecipitationforecasting AT adamowskikazimierz awaveletsarimaannhybridmodelforprecipitationforecasting AT shafaeimaryam waveletsarimaannhybridmodelforprecipitationforecasting AT adamowskijan waveletsarimaannhybridmodelforprecipitationforecasting AT fakherifardahmad waveletsarimaannhybridmodelforprecipitationforecasting AT dinpashohyagob waveletsarimaannhybridmodelforprecipitationforecasting AT adamowskikazimierz waveletsarimaannhybridmodelforprecipitationforecasting |