Support vector machine and neural network based model for monthly stream flow forecasting
Accurate forecasting of streamflow is desired in many water resources planning and management, flood prevention and design development. In this study, the accuracy of two hybrid model, support vector machine - particle swarm optimization (SVM-PSO) and bat algorithm - backpropagation neural network (...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Published: |
Science Publishing Corporation Inc
2023
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-24063 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-240632023-05-29T14:54:58Z Support vector machine and neural network based model for monthly stream flow forecasting Zaini N. Malek M.A. Yusoff M. Osmi S.F.C. Mardi N.H. Norhisham S. 56905328500 55636320055 23391662400 54963643200 57190171141 54581400300 Accurate forecasting of streamflow is desired in many water resources planning and management, flood prevention and design development. In this study, the accuracy of two hybrid model, support vector machine - particle swarm optimization (SVM-PSO) and bat algorithm - backpropagation neural network (BA-BPNN) for monthly streamflow forecasting at Kuantan River located in Peninsular Malaysia are investigated and compared to regular SVM and BPNN model. Heuristic optimization namely PSO and BA are introduced to find the optimum SVM and BPNN parameters. The input parameters to the forecasting models are antecedent streamflow, historical rainfall and meteorological parameters namely evaporation, temperature, relative humidity and mean wind speed. Two performance evaluation measure, root mean square error (RMSE) and coefficient of determination (R 2 ) were employed to evaluate the performance of developed forecasting model. It is found that, RMSE and R 2 for hybrid SVM-PSO are 24.8267 m 3 /s and 0.9651 respectively while general SVM model yields RMSE of 27.5086 m 3 /s and 0.9305 of R 2 for testing phase. Besides that, hybrid BA-BPNN produces RMSE, 17.7579 m 3 /s and R 2 , 0.7740 while BPNN model produces lower RMSE and R 2 of 28.1396 m 3 /s and 0.5015 respectively. Therefore, the results indicate that hybrid model, SVM-PSO and Bat-BPNN yield better performance as compared to general SVM and BPNN, respectively in streamflow forecasting. � 2018 Authors. Final 2023-05-29T06:54:58Z 2023-05-29T06:54:58Z 2018 Article 10.14419/ijet.v7i4.35.23089 2-s2.0-85059232933 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85059232933&doi=10.14419%2fijet.v7i4.35.23089&partnerID=40&md5=e203a6dcae5ca23ac9f92097b831125c https://irepository.uniten.edu.my/handle/123456789/24063 7 4 683 688 Science Publishing Corporation Inc Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
Accurate forecasting of streamflow is desired in many water resources planning and management, flood prevention and design development. In this study, the accuracy of two hybrid model, support vector machine - particle swarm optimization (SVM-PSO) and bat algorithm - backpropagation neural network (BA-BPNN) for monthly streamflow forecasting at Kuantan River located in Peninsular Malaysia are investigated and compared to regular SVM and BPNN model. Heuristic optimization namely PSO and BA are introduced to find the optimum SVM and BPNN parameters. The input parameters to the forecasting models are antecedent streamflow, historical rainfall and meteorological parameters namely evaporation, temperature, relative humidity and mean wind speed. Two performance evaluation measure, root mean square error (RMSE) and coefficient of determination (R 2 ) were employed to evaluate the performance of developed forecasting model. It is found that, RMSE and R 2 for hybrid SVM-PSO are 24.8267 m 3 /s and 0.9651 respectively while general SVM model yields RMSE of 27.5086 m 3 /s and 0.9305 of R 2 for testing phase. Besides that, hybrid BA-BPNN produces RMSE, 17.7579 m 3 /s and R 2 , 0.7740 while BPNN model produces lower RMSE and R 2 of 28.1396 m 3 /s and 0.5015 respectively. Therefore, the results indicate that hybrid model, SVM-PSO and Bat-BPNN yield better performance as compared to general SVM and BPNN, respectively in streamflow forecasting. � 2018 Authors. |
| author2 |
56905328500 |
| author_facet |
56905328500 Zaini N. Malek M.A. Yusoff M. Osmi S.F.C. Mardi N.H. Norhisham S. |
| format |
Article |
| author |
Zaini N. Malek M.A. Yusoff M. Osmi S.F.C. Mardi N.H. Norhisham S. |
| spellingShingle |
Zaini N. Malek M.A. Yusoff M. Osmi S.F.C. Mardi N.H. Norhisham S. Support vector machine and neural network based model for monthly stream flow forecasting |
| author_sort |
Zaini N. |
| title |
Support vector machine and neural network based model for monthly stream flow forecasting |
| title_short |
Support vector machine and neural network based model for monthly stream flow forecasting |
| title_full |
Support vector machine and neural network based model for monthly stream flow forecasting |
| title_fullStr |
Support vector machine and neural network based model for monthly stream flow forecasting |
| title_full_unstemmed |
Support vector machine and neural network based model for monthly stream flow forecasting |
| title_sort |
support vector machine and neural network based model for monthly stream flow forecasting |
| publisher |
Science Publishing Corporation Inc |
| publishDate |
2023 |
| _version_ |
1806427491417456640 |
| score |
13.226497 |