Daily streamflow prediction using support vector machine-artificial flora (SVM-AF) hybrid model

Abstract

Precise estimation of river flow in catchment areas has a significant role in managing water resources and, particularly, making firm decisions during flood and drought crises. In recent years, different procedures have been proposed for estimating river flow, among which hybrid artificial intelligence models have garnered notable attention. This study proposes a hybrid method, so-called support vector machine–artificial flora (SVM-AF), and compares the obtained results with outcomes of wavelet support vector machine models and Bayesian support vector machine. To estimate discharge value of the Dez river basin in the southwest of Iran, the statistical daily watering data recorded by hydrometric stations located at upstream of the dam over the years 2008–2018 were investigated. Four performance criteria of coefficient of determination (R2), root-mean-square error, mean absolute error, and Nash–Sutcliffe efficiency were employed to evaluate and compare performances of the models. Comparison of the models based on the evaluation criteria and Taylor’s diagram showed that the proposed hybrid SVM-AF with the correlation coefficient R2 = 0.933–0.985, root-mean-square error RMSE = 0.008–0.088 m3/s, mean absolute error MAE = 0.004–0.040 m3/s, and Nash-Sutcliffe coefficient NS = 0.951–0.995 had the best performance in estimating daily flow of the river. The estimation results showed that the proposed hybrid SVM-AF model outperformed other models in efficiently predicting flow and daily discharge.

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

References

  1. Adnan R, Liang Z, Heddam S, Kermani M, Kisi O, Li B (2019) Least square support vector machine and multivariate adaptive regression splines for streamflow prediction in mountainous basin using hydro-meteorological data as inputs. J Hydrol 19(4):432–448

    Google Scholar 

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

    Google Scholar 

  3. Alizadeh F, Gharamaleki A, Jalilzadeh M, Akhoundzadeh A (2020) Prediction of river stage-streamflow process based on a conceptual model using EEMD-WT-LSSVM Approach. Water Resour 47:41–53

    Google Scholar 

  4. ASCE (1993) Criteria for evaluation of watershed models. J Irrig Drain Eng 119(3):429–442

    Google Scholar 

  5. Asefa T, Kemblowski MW, Urroz G, McKee M, Khalil A (2004) Support vector based groundwater head observation networks design. Water Resour Res. https://doi.org/10.1029/2004WR003304

    Article  Google Scholar 

  6. Basak D, Pal S, Patranabis DC (2007) Support vector regression. Neural Inf Process 11:203–225

    Google Scholar 

  7. Beven KJ, Kirkby MJ (1979) A physically based variable contributing area model of basin hydrology Hydrological. Sci Bull 43:43–69

    Google Scholar 

  8. Bhagwat PP, Maity R (2012) Multistep-ahead River Flow Prediction using LS-SVR at Daily Scale J. Water Resour 4:528–539

    Google Scholar 

  9. Boser JA (1992) Microcomputer needs assessment of american evaluation association members. Am J Eval 13:92–93

    Google Scholar 

  10. Cameron M, Donland H, Slobodan P (1999) Short term streamflow forecasting using artificial neural networks. J Hydrol 214(4):32–48

    Google Scholar 

  11. Cartlidge JP, Bulloc SG (2004) Combating coevolutionary disengagement by reducing parasite virulence. Evol Comput 12(2):193–222

    Google Scholar 

  12. Cheng L, Wu X, Wang Y (2018) Artificial flora (AF) optimization algorithm. Appl Sci 329(8):2–22

    Google Scholar 

  13. Coken U, Forman A, Fensoy A (2016) Streamflow forecasting using different neural network models with satellite data for a snow dominated region in Turkey. Procedia Eng 154:1185–1192

    Google Scholar 

  14. Dibike YB, Velickov S, Solomatine D, Abbott MB (2001) Model induction with support vector machines: introduction and applications. J Comput Civ Eng 15:208–216

    Google Scholar 

  15. Dolling O, Eduardo A (2002) Artificial Neural Networks for Streamflow Prediction. J Hydraul Res 40(5):547–554

    Google Scholar 

  16. Duan Q, Sorooshian S, Gupta VK (1992) Effective and efficient global optimization for conceptual rainfall–runoff models. Water Resour Res 28(4):1015–1031

    Google Scholar 

  17. Duan Q, Sorooshian S, Gupta VK (1994) Optimal use of SCEUA global optimization method for calibrating watershed models. J Hydrol 158:265–284

    Google Scholar 

  18. Duie Tien B, Khosravi K, Tiefenbacher J, Nguyen H, Kazakis N (2020) Improving prediction of water quality indices using novel hybrid machine-learning algorithms. J Sci Total Environ 721:136612

    Google Scholar 

  19. Ghorbani MA, Khatibi R, Geol A, Fazelifard MH, Azani A (2016) Modeling river streamflow time series using support vector machine and artificial neural networks. Environ Earth Sci 75(4):675–685

    Google Scholar 

  20. Ghorbani MA, Deo R, Karimi V, Yassen ZM, Terzi O (2018a) Implementation of a hybrid MLP-FFA model for water level prediction of Lake Egirdir Turkey. Stoch Environ Res Risk Assess 32(6):1683–1697

    Google Scholar 

  21. Ghorbani MA, Khatibi R, Karimi V, Yaseen ZM, Zounemat-Kermani M (2018b) Learning from multiple models using artificial intelligence to improve model prediction accuracies: application to river flows. Water Resour Manag 32(13):4201–4215

    Google Scholar 

  22. Gizaw MS, Gan TY (2016) Regional flood frequency analysis using support vector regression under historical and future climate. J Hydrol 538:387–398

    Google Scholar 

  23. Guven A, Kisi O (2011a) Daily pan evaporation modeling using linear genetic programming technique. Irrig Sci 136(10):715–723

    Google Scholar 

  24. Guven A, Kisi O (2011b) Daily pan evaporation modeling using linear genetic programming technique. Irrig Sci 29(2):135–145

    Google Scholar 

  25. Hamel L (2009) Knowledge discovery with support vector machines. Wiley, Hoboken

    Google Scholar 

  26. Haykin A (1998) Neural networks: a comprehensive foundation. Prentice Hall, Upper Saddle River

    Google Scholar 

  27. Heckerman D (1997) Bayesian networks for data mining, data mining and knowledge. Discovery 1(1):79–119

    Google Scholar 

  28. Hillis WD (1990) Co-evolving parasites improve simulated evolution as an optimization procedure. Phys D Nonlinear Phenom 42:228–234

    Google Scholar 

  29. Hsu K, Gupta HV, Sorooshian S (1995) Artificial neural network modeling of the rainfall–runoff process. Water Resour 31(10):2517–2530

    Google Scholar 

  30. Huang S, Chang J, Huang Q, Chen Y (2014) Monthly streamflow prediction using modified emd-based support vector machine. J Hydrol 511(4):764–775

    Google Scholar 

  31. Jakeman AJ, Hornberger GM (1993) How much complexity is warranted in a rainfall-runoff model. Water Resour Res 29:2637–2649

    Google Scholar 

  32. Kalteh AM (2013) Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform. Comput Geosci 54:1–8

    Google Scholar 

  33. Kesgin E, Agaccioglu H, Dogan A (2020) Experimental and numerical investigation of drainage mechanisms at sports fields under simulated rainfall. J Hydrol 580:124251

    Google Scholar 

  34. Kevin B, Nicholson E (2010) Bayesian artificial intelligence. Comput Sci Data Anal 14(8):1328–1344

    Google Scholar 

  35. Kisi O, Cobaner M (2009) Modeling river stage–discharge relationships using different neural network computing techniques. CLEAN Soil Air Water 37:160–169

    Google Scholar 

  36. Kisi O, Karahan M, Sen Z (2006a) River suspended sediment modeling using fuzzy logic approach. Hydrol Process 20(2):4351–4362

    Google Scholar 

  37. Kisi O, Karahan M, Sen Z (2006b) River suspended sediment modeling using fuzzy logic approach. Hydrol Process 20:4351–4362

    Google Scholar 

  38. Kumar RA, Jothiprakash V (2013) Reservoir evaporation prediction using data-driven techniques. J Hydrol Eng 18(1):40–49

    Google Scholar 

  39. Lima AR, Cannon AJ, Hsieh WW (2016) Forecasting daily streamflow using online sequential extreme learning machines. J Hydrol 537:431–443

    Google Scholar 

  40. Lo Conti F, Hsu KL, Noto LV, Sorooshian S (2014) Evaluation and comparison of satellite precipitation estimates with reference to a local area in the Mediterranean Sea. Atmos Res 138:189–204

    Google Scholar 

  41. Macfarlane C, Ogden GN (2012) An improved evaporation dome for forest environments Comput. Electron Agric 89:126–129

    Google Scholar 

  42. Misra D, Oommen T, Agarwa A, Mishra SK, Thompson AM (2009) Application and analysis of support vector machine based simulation for runoff and sediment yield. Biosyst Eng 103(3):527–535

    Google Scholar 

  43. Moriasi DN, Arnold JG, Van Liew MW, Bingner RL, Harmel RD, Veith TL (2007) Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Am Soc Agric Biol Eng 50(3):885–900

    Google Scholar 

  44. Nagelkerke NJD (1991) A note on a general definition of the coefficient of determination. Biometrika. https://doi.org/10.1093/biomet/78.3.691

    Article  Google Scholar 

  45. Nagy H, Watanabe K, Hirano M (2002a) Prediction of sediment load concentration in rivers using artificial neural network model. J Hydraul Eng 128(3):558–559

    Google Scholar 

  46. Nagy H, Watanabe K, Hirano M (2002b) Prediction of sediment load concentration in rivers using artificial neural network model. J Hydraul Eng 128:558–559

    Google Scholar 

  47. Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models: part 1. A discussion of principles. J Hydrol 10(3):282–290

    Google Scholar 

  48. Nguyen D, Widrow B (1990) Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights. Proc IJCNN 3:21–26

    Google Scholar 

  49. Pagie L, Mitchell MA (2002) Comparison of evolutionary and coevolutionary search. Int J Comput Intell Appl 2:53–69

    Google Scholar 

  50. Pulido-Calvo I, Portela M (2007) Application of neural approaches to one-step daily flow forecasting in Portuguese watersheds. J Hydrol 332(4):1–15

    Google Scholar 

  51. Robert JA, Linda S (2000) Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments. Hydrol Process 14:2157–2172

    Google Scholar 

  52. Rosin CD, Belew RK (1995) Methods for competitive co-evolution: finding opponents worth beating. In: Proceedings of the international conference on genetic algorithms, Pittsburgh, pp 373–381

  53. Safavi AA, Romagnoli JA (1997) Application of wavelet-based neural networks to modelling and optimisation of an experimental distillation column. IFAC J Eng Appl Artif Intell 10(3):301–313

    Google Scholar 

  54. Salas G, Markuus M, Tokar AS (2000) Streamflow forecasting based on artificial neural networks. Artif Neural Netw Hydrol 154(2):918–925

    Google Scholar 

  55. Sedighi F, Vafakhah M, Javadi MR (2016) Rainfall-runoff modeling using support vector machine in snow-affected watershed. Arab J Sci Eng 41(10):4065–4076

    Google Scholar 

  56. Sevat E, Dezetter A (1991) Selection of calibration objective functions in the context of rainfall-runoff modeling in a Sudanese savannah area. Hydrol Sci J 36(4):307–330

    Google Scholar 

  57. Shin S, Kyung D, Lee S, Taik K, Kim J, Hyun J (2005) An application of support vector machines in bankruptcy prediction model. Expert Syst Appl 28(4):127–135

    Google Scholar 

  58. Sivapragasam C, Muttil N (2005) Discharge rating curve extension—a new approach. Water Resour Manag 19:505–520

    Google Scholar 

  59. Solomatine DP (2005) Data-driven modeling and computational intelligence methods in hydrology. In: Encyclopedia of hydrological sciences. Wiley

  60. Srivastava P, McVair JN, Johnson TE (2006) Comparison of process-based and artificial neural network approaches for streamflow modeling in an agricultural watershed. J Am Water Resour Assoc 2(3):545–563

    Google Scholar 

  61. Suliman A, Nazri N, Othman M, Abdul M, Ku-mahamud KR (2013) Artificial neural network and support vector machine in flood forecasting: a review. J Hydroinform 15:327–332

    Google Scholar 

  62. Taylor E (2001a) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res 106(7):7183–7192

    Google Scholar 

  63. Taylor KE (2001b) Summarizing multiple aspects of model performance in a single diagram. J Geophys Res Atmos 106:7183–7192

    Google Scholar 

  64. Tokar AS, Markus M (2000) Precipitation-runoff modeling using artificial neural networks and conceptual models. J Hydrol Eng 5:156–161

    Google Scholar 

  65. Tukey JW (1969) Analyzing data: sanctification or detective work. Am Psychol 24

  66. Vapnik VN (1998) Statistical learning theory. Wiley, New York

    Google Scholar 

  67. Vapnik V, Chervonenkis A (1991) The necessary and sufficient conditions for consistency in the empirical risk minimization method. Pattern Recognit Image Anal 1(3):283–305

    Google Scholar 

  68. Wang D, Safavi AA, Romagnoli JA (2000) Wavelet-based adaptive robust M-estimator for non-linear system identification. AIChE J 46(4):1607–1615

    Google Scholar 

  69. Wang W, Men C, Lu W (2008) Online prediction model based on support vector machine. Neurocomputing 71:550–558

    Google Scholar 

  70. Wehner MF (2013) Very extreme seasonal precipitation in the NARCCAP ensemble: model performance and projections. Clim Dyn 40(1–2):59–80

    Google Scholar 

  71. Wiegand RP, Sarma J (2004) Spatial embedding and loss of gradient in cooperative coevolutionary algorithms. In: Proceedings of the international conference on parallel problem solving from nature, Berlin, Germany, vol 43, pp 912–921

  72. Williams N, Mitchell M (2005) Investigating the success of spatial coevolution. In: Proceedings of the 7th annual conference on genetic and evolutionary computation Washington, vol 46, pp 523–530

  73. Yoon H, Jun SC, Hyun Y, Bae GO, Lee KK (2011) A comparative study of artificial neural networks and support vector machines for predicting groundwater levels in a coastal aquifer. J Hydrol 396(4):128–138

    Google Scholar 

  74. Yu PS, Chen ST, Chang IF (2005) Flood stage forecasting using support vector machines. Geophys Res 7:41–76

    Google Scholar 

  75. Yu PS, Chen ST, Chang IF (2006) Support vector regression for realtime flood stage forecasting. J Hydrol 328:704–716

    Google Scholar 

  76. Zhu YM, Lu XX, Zhou Y (2007) Suspended sediment flux modeling with artificial neural network: an example of the longchuanjiang river in the upper yangtze catchment. Geomorphology 84(4):111–125

    Google Scholar 

  77. 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):531–544

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Hassan Torabi Poudeh.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Dehghani, R., Torabi Poudeh, H., Younesi, H. et al. Daily streamflow prediction using support vector machine-artificial flora (SVM-AF) hybrid model. Acta Geophys. 68, 1763–1778 (2020). https://doi.org/10.1007/s11600-020-00472-7

Download citation

Keywords

  • Artificial flora
  • Prediction
  • Streamflow
  • Support vector machine