Home Articles List Article Information
Soft Computing in Civil Engineering
Journal Archive
Volume Volume 2 (2018)
Volume Volume 1 (2017)
Londhe, S., Gavraskar, S. (2018). Stream Flow Forecasting using Least Square Support Vector Regression. Soft Computing in Civil Engineering, 2(2), 56-88. doi: 10.22115/scce.2017.96717.1024
Shreenivas Londhe; Seema Gavraskar. "Stream Flow Forecasting using Least Square Support Vector Regression". Soft Computing in Civil Engineering, 2, 2, 2018, 56-88. doi: 10.22115/scce.2017.96717.1024
Londhe, S., Gavraskar, S. (2018). 'Stream Flow Forecasting using Least Square Support Vector Regression', Soft Computing in Civil Engineering, 2(2), pp. 56-88. doi: 10.22115/scce.2017.96717.1024
Londhe, S., Gavraskar, S. Stream Flow Forecasting using Least Square Support Vector Regression. Soft Computing in Civil Engineering, 2018; 2(2): 56-88. doi: 10.22115/scce.2017.96717.1024

Stream Flow Forecasting using Least Square Support Vector Regression

Article 4, Volume 2, Issue 2 - Serial Number 4, Spring 2018, Page 56-88  XML PDF (2.05 MB)
Document Type: Regular Article
DOI: 10.22115/scce.2017.96717.1024
Authors
Shreenivas Londhe 1; Seema Gavraskar2
1Professor, Vishwakarma Institute of Information Technology, Pune, India
2PG Student, Vishwakarma Institute of Information Technology, Pune, India
Receive Date: 28 August 2017,  Revise Date: 11 December 2017,  Accept Date: 17 December 2017 
Abstract
Effective stream flow forecast for different lead-times is useful in almost all water resources related issues. The Support Vector Machines (SVMs) are learning systems that use a hypothetical space of linear functions in a kernel induced higher dimensional feature space, and are trained with a learning algorithm from optimization theory. The support vector regression attempts to fit a curve with respect to the kernel used in SVM on data points such that the points lie between two marginal hyper planes which helps in minimizing the regression error. The current paper presents least square support vector regression (LS-SVR) to predict one day ahead stream flow using past values of the rainfall and stream flow at three stations in India, namely Nighoje and Budhwad in Krishna river basin and Mandaleshwar in Narmada river basin. The relevant inputs are fixed on the basis of autocorrelation, Cross-correlation and trial and error. The model results are reasonable as can be seen from low value of Root Mean Square Error (RMSE), Coefficient of Efficiency (CE) and Mean Absolute Relative Error (MARE) accompanied by scatter plots and hydrographs.

Highlights
Keywords
Stream flow forecasting; Support Vector Machines; Support vector regression; Kernel function
Main Subjects
Evolutionary Computation (EC) - based on the origin of the species
References
[1]     Shalamua A. Monthly and Seasonal Streamflow Forecasting in the Rio Grande Basin, Ph.D. thesis, New Mixico State University, 2009, 321.

[2]     Bhatnagar A. Hydrologic Time Series Analysis using Support Vector Regression, M.Tech Thesis-2009, Indian Institute of Technology, Bombay

[3]     Solomatine D. P., Wagener T. Hydrological Modeling, Treatise on Water Science, 2011; 2: 435-457.

[4]     Shreshta R.R., Nestmann M. Physically Based and Data-Driven Models and Propagation of Input Uncertainties in River Flood Prediction.ASCE Hydrologic Engineering, 2009; 4(12): 1409-1419.

[5]     http://www.cwc.gov.in/main/HP

[6]     www.mahap.org

[7]     Mahjoobi E. J., Adeli M. Prediction of significant wave height using regressive support vector machines. Ocean Engineering, 2009; 36(5): 339-347.

[8]     Vapnik V.N. An overview of statistical learning theory. IEEE Transactions on Neural Networks, 1999; 10 (5): 988–999.

[9]     Dibike Y. B., Velickov S., Solomatine, Michael B., A. Model Induction with Support Vector Machines: Introduction and Applications. ASCE Journal of Computing in Civil Engineering, 2001; 15(3): 208-216.

[10]  Wu C. L., Chau K. W.,  Li Y. S. River stage prediction based on a distributed support vector regression. Journal of Hydrology,  2008; 358: 96– 111.

[11]  Suykens  J. A. K., Vandewalle Least Squares Support Vector Machine Classifiers. Neural Processing Letters, 1999; 9:293-300.

[12]  Rajsekaran S., Gayathri S. T., Lee T. L. Support Vector regression methodology for storm surge prediction. Ocean Engineering, 2008;35(16) :1578-1587.

[13]  Dibike Y. B., Velickov S., Solomatine D. Support Vector Machines: Review and Applications in Civil Engineering, Proc. of the joint workshop on Applications of AI in Civil Engineering,  Cottbus-2000, Germany.

[14]  Bray M., Han D. Identification of support vector machines for runoff modeling. Journal of Hydroinformatics, 2004;6(4): 265-280.

[15]  Asefa T., Kemblowski M., Mckee M, Khalil A. Multi-time scale stream flow predictions: The support vector machines approach. Journal of Hydrology, 2006; 318(1-4): 7-16.

[16]  Lin Jian-Yi, Cheng Chun-Tia, Chau, Kwok-Wing. Using support vector machines for long-term discharge prediction. Hydrological Sciences Journal, 2010; 51(4): 599-612.

[17]  Yu P., Chen S, Chang I. Support vector regression for real-time flood stage forecasting. Journal of Hydrology, 2006; 328: 704-716.

[18]  Behzad M., Asghari K., Eazi M., Palhang M. Generalization performance of support vector machines and neural networks in runoff modeling. Expert Systems with applications, 2009; 36(4): 7624-7629.

[19]  Noori R., Karbassi A. R., Moghaddamnia A., Han D., Zokaei-Ashtiani M. H., Farokhnia A.,  Gousheh, M. G. Assessment of input variables determination on the SVM model performance using PCA, Gamma test, and forward selection techniques for monthly stream flow prediction. Journal of  Hydrology. 2011;401(3): 177-189.

[20]  Kisi O. Modelling Discharge-Suspended Sediment Relationship using Least Square Support Vector Machine. Journal of Hydrology, 2012; 456–457:110–120.

[21]  Bhagwat P., Maity R. Hydroclimaticstreamflow prediction using Least Square-Support Vector Regression. ISH Journal of Hydraulic Engineering, 2013; 19(3): 320–328.

[22]  Sahraei S., Andalani S. Z., Zakermoshfegh M., Sisakht B. N., Talebbeydokhti N., Moradkhani, H. Daily discharge forecasting using least square support vector regression and regression tree. ScientiaIranica. Transaction A, Civil Engineering, 2015; 22(2): 410-422.

[23]  Kalteh A. M. Wavelet Genetic Algorithm-Support Vector Regression (wavelet GA-SVR) for Monthly Flow Forecasting. Water Resources Management, 2015; 29 (4): 1283–1293.

[24]  Kalteh A. M. Monthly river flow forecasting using Artificial Neural Network and Support Vector Regression models Coupled with Wavelet Transform. Computers and Geosciences,  2013; 54: 1–8.

[25]  Kalteh A. M., Improving Forecasting Accuracy of StreamflowTime Series using Least Squares Support Vector Machine Coupled with Data-Preprocessing techniques. Water Resources Management, 2016; 30 (2): 747–766.

[26]  Kisi O.Stream Flow Forecasting and Estimation using Least Square Support Vector Regression and Adaptive Neuro-Fuzzy Embedded Fuzzy C-means Clustering. Water Resources Management, 2015; 29(14): 5109–5127.

[27]  Zamini A., Solomatine D, Azimian A, Heemink A. Learning from data for wind -wave forecasting. Ocean engineering, 2008; 35: 953-962.

[28]  Londhe S., N., Dixit P.,R., Charhate S. B. Forecasting Ocean Waves using Support Vector Regression. Proc. of  18thIAHR-APD2012- 2012, Jeju, South Korea, 38-41.

[29]  Legates D., McCabe G., J. Evaluating the use of Goodness-of-Fit Measures in hydrologic and hydroclimatic model validation. Water Resources Research, 2010;35(1): 233-241.

[30]  Dawson C.W., Wilby R. L. Hydrological modeling using artificial neural networks. Progress in Physical Geography, 2001; 25(1): 80-108.

[31]  Londhe S., N., Panchang V. One-Day Wave Forecasts Based on Artificial Neural Networks. Journal of Atmospheric and Oceanic Technology, 2006; 23: 1593–1603.

Statistics
Article View: 373
PDF Download: 243