Performance enhancement of SVM model using discrete wavelet transform for daily streamflow forecasting

Abstract

Streamflow modeling becomes a vital task in any hydrological study for an improved planning and management of water resources. Soft computing and machine learning techniques are becoming popular day by day for their predictive capability when limited input data are available. In the present study, Support Vector Machine (SVM) technique is applied to forecast 1-day, 3-day, and 5-day ahead streamflow using daily streamflow time-series of Khanapur, Cholachguda, and Navalgund gauging stations in Malaprabha sub-basin located in the Karnataka state of India. Furthermore, Discrete Wavelet Transform is used as a data pre-processing method to evaluate the performance enhancement of SVM model, for which four different mother wavelet functions are used and tested separately, namely, Haar, Daubechies, Coiflets, and Symlets. Models are evaluated using coefficient of determination (R2), root-mean-square error, and Nash–Sutcliffe efficiency. The study indicates that the performance of SVM model improves considerably when wavelet method is coupled. It is found that the R2 values for Khanapur station using SVM are 0.91, 0.66, and 0.46 for 1-day, 3-day, and 5-day lead-time forecasts, respectively. However, when wavelet method is coupled with SVM model, the R2 is improved to 0.99, 0.73, and 0.68 for 1-day, 3-day, and 5-day lead-time forecasts, respectively.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

References

  1. Abdollahi S, Raeisi J, Khalilianpour M, Ahmadi F, Kisi O (2017) Daily mean streamflow prediction in perennial and non-perennial rivers using four data driven techniques. Water ResourManag 31:4855–4874

    Google Scholar 

  2. Adamowski JF (2008) Development of a short-term river flood forecasting method for snowmelt driven floods based on wavelet and cross-wavelet analysis. J Hydrol 353(3):247–266

    Article  Google Scholar 

  3. Adamowski J, Sun K (2010) Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. J Hydrol 390(1):85–91. https://doi.org/10.1016/j.jhydrol.2010.06.033

    Article  Google Scholar 

  4. Aggarwal SK, Goel A, Singh VP (2012) Stage and discharge forecasting by SVM and ANN techniques. Water ResourManag 26:3705–3724

    Google Scholar 

  5. Akrami SA, Hakim SJS (2014) Development of nonlinear model based on wavelet-ANFIS for rainfall forecasting at Klang Gates Dam. Water Resour Manage 28:2999–3018. https://doi.org/10.1007/s11269-014-0651-x

    Article  Google Scholar 

  6. Augusto C, Santos G, Barbosa G (2014) Daily streamflow forecasting using a wavelet transform and artificial neural network hybrid models. Hydrol Sci J J Des Sci Hydrol 59(2):312–324

    Article  Google Scholar 

  7. Box GEP, Jenkins GM (1970) Time series analysis: forecasting and control. Holden-Day, Oakland

    Google Scholar 

  8. Daubechies I (1992) Ten lectures on wavelets. SIAM, Philadelphia

    Google Scholar 

  9. Deka PC, Haque L, Banhatti AG (2012) Discrete Wavelet-Ann approach in time series flow forecasting—a case study of Brahmaputra River. Int J Earth Sci Eng 05(04):673–685

    Google Scholar 

  10. Dixit P, Deo SLMC (2016) Review of applications of neuro-wavelet techniques in water flows. INAE Lett 1(3):99–104

    Article  Google Scholar 

  11. Fletcher R (1987) Practical methods of optimization, 2nd edn. Wiley, New York

    Google Scholar 

  12. Fung KF, Huang YF, Koo CH, Soh YW (2019) Drought forecasting: a review of modelling approaches 2007–2017. J Water Clim Change. https://doi.org/10.2166/wcc.2019.236 (In press)

    Article  Google Scholar 

  13. Gunn SR (1998) Support vector machines for classification and regression. ISIS Tech Rep 14:85–86

    Google Scholar 

  14. Hadi SJ, Tombul M (2018a) Forecasting daily streamflow for basins with different physical characteristics through data-driven methods. Water ResourManag 32(10):3405–3422

    Google Scholar 

  15. Hadi SJ, Tombul M (2018b) Forecasting daily streamflow for basins with different physical characteristics through data-driven methods. Water ResourManag 32(10):3405–3422. https://doi.org/10.1007/s11269-018-1998-1

    Article  Google Scholar 

  16. Jian YL, Chun TC, Kwok WCH (2006) Using support vector machines for long term discharge prediction. Hydrol Sci J 51(4):599–612. https://doi.org/10.1623/hysj.51.4.599

    Article  Google Scholar 

  17. Kisi O (2004) River flow modeling using artificial neural networks. J HydrolEng 9(1):60–63

    Google Scholar 

  18. Kisi O, Cimen M (2011) A wavelet-support vector machine conjunction model for monthly streamflow forecasting. J Hydrol 399(1–2):132–140

    Article  Google Scholar 

  19. Kişi Ö (2008) Stream flow forecasting using neuro-wavelet technique. Hydrol Process 22:4142–4152. https://doi.org/10.1002/hyp.7014

    Article  Google Scholar 

  20. Kişi Ö (2009) Neural networks and wavelet conjunction model for intermittent streamflow forecasting. J HydrolEng 14(8):773–782. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000053

    Article  Google Scholar 

  21. Li S, Jiang L, Zhu Y, Bo P (2012) A hybrid forecasting model of discharges based on support vector machine. ProcediaEng 28(2011):136–141

    Google Scholar 

  22. Lohani AK, Kumar R, Singh RD (2012) Hydrological time series modeling: a comparison between adaptive neuro-fuzzy, neural network and autoregressive techniques. J Hydrol 442–443:23–35

    Article  Google Scholar 

  23. Machiwal D, Jha MK (2012) Hydrologic time series analysis: theory and practice. Springer Science & Business Media, Berlin

    Google Scholar 

  24. Maheswaran R, Khosa R (2012) Computers & geosciences comparative study of different wavelets for hydrologic forecasting. Comput Geosci 46:284–295

    Article  Google Scholar 

  25. Maier HR, Dandy GC (2000) Neural networks for the production and forecasting of water resource variables: a review and modelling issues and application. Environ Modell Softw 15:101–124

    Article  Google Scholar 

  26. Mallat SG (1989) Multiresolution approximations and wavelet orthonormal bases of L2 (R). Trans Am Math Soc 315(1):69–87. https://doi.org/10.2307/2001373

    Article  Google Scholar 

  27. Mansoor CNM, Bilwa LM, Hutti B (2014) Flood hazard zonation mapping using geoinformatics technology; Bennihalla Basin, Gadag and Dharwad District, Karnataka, India. Int J Eng Res Technol (IJERT) 3(9):750–755. ISSN: 2278-0181

  28. Mudbhatkal A, Raikar RV, Venkatesh B, Mahesha A (2017) Impacts of climate change on varied river-flow regimes of southern India. J HydrolEng 22(9):05017017

    Google Scholar 

  29. Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I—a discussion of principles. J Hydrol 10(3):282–290

    Article  Google Scholar 

  30. Nourani V, Baghanam AH, Rahimi AY, Nejad FH (2014) Evaluation of wavelet-based de-noising approach in hydrological models linked to artificial neural networks. In: Islam T, Srivastava PK, Gupta M, Zhu X, Mukherjee S (eds) Computational intelligence techniques in earth and environmental sciences. Springer, Dordrecht, pp 209–241

    Google Scholar 

  31. Raghavendra NS, Deka PC (2014) Support vector machine applications in the field of hydrology: a review. Appl Soft Comput J 19:372–386

    Article  Google Scholar 

  32. Sang Y (2012) A practical guide to discrete wavelet decomposition of hydrologic time series. Water ResourManag 26:3345–3365

    Google Scholar 

  33. Sang Y, Wang D, Wu J, Zhu Q, Wang L, Reuse R (2011) Wavelet-based analysis on the complexity of hydrologic series data under multi-temporal scales. Entropy 13:195–210. https://doi.org/10.3390/e13010195

    Article  Google Scholar 

  34. Sang Y, Singh VP, Sun F, Chen Y, Liu Y, Yang M (2016) Wavelet-based hydrological time series forecasting. J HydrolEng @ ASCE 21(5):1–5

    Google Scholar 

  35. Santos CAG, da Silva GBL (2014) Daily streamflow forecasting using a wavelet transform and artificial neural network hybrid models. Hydrol Sci J 59(2):312–324. https://doi.org/10.1080/02626667.2013.800944

    Article  Google Scholar 

  36. Shabri A, Suhartono (2012) Streamflow forecasting using least-squares support vector machines. Hydrol Sci J 57(7):1275–1293. https://doi.org/10.1080/02626667.2012.714468

  37. Shumway RH, Stoffer DS (2010) Time series analysis and its applications: with R examples. Springer Science & Business Media, Berlin

    Google Scholar 

  38. Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Stat Comput 14(3):199–222

    Article  Google Scholar 

  39. Thornthwaite CW (1948) An approach toward a rational classification of climate. Geogr Rev 38(1):55–94

    Article  Google Scholar 

  40. Tiwari MK, Chatterjee C (2010) Development of an accurate and reliable hourly flood forecasting model using wavelet-bootstrap-ANN (WBANN) hybrid approach. J Hydrol 394(3–4):458–470

    Article  Google Scholar 

  41. Torrence C, Compo GP (1998) A practical guide to wavelet analysis. Bull Am MeteorolSoc 79(1):61–78

    Article  Google Scholar 

  42. Vapnik VN (1995) The nature of statistical learning theory. Springer, New York

    Google Scholar 

  43. Zhang L, Zhou W, Jiao L (2004) Wavelet support vector machine. IEEE Trans Syst Man Cybern Part B Cybern 34(1):34–39

    Article  Google Scholar 

  44. Zhang F, Da H, Tang D (2014) A conjunction method of wavelet transform-particle swarm optimization-support vector machine for streamflow forecasting. J Appl Math. https://doi.org/10.1155/2014/910196

    Article  Google Scholar 

  45. Zhu S, Zhou J, Ye L, Meng C (2016) Streamflow estimation by support vector machine coupled with different methods of time series decomposition in the upper reaches of Yangtze River. China Environ Earth Sci 75(6):1–12

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Shruti Kambalimath S.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kambalimath S, S., Deka, P.C. Performance enhancement of SVM model using discrete wavelet transform for daily streamflow forecasting. Environ Earth Sci 80, 101 (2021). https://doi.org/10.1007/s12665-021-09394-z

Download citation

Keywords

  • Soft computing
  • Streamflow forecasting
  • Data pre-processing
  • Support vector machine (SVM)
  • Discrete wavelet transform (DWT)