Advertisement

Evaluation of Wavelet-Based De-noising Approach in Hydrological Models Linked to Artificial Neural Networks

  • Vahid NouraniEmail author
  • Aida Hosseini Baghanam
  • Aida Yahyavi Rahimi
  • Farzad Hassan Nejad
Chapter

Abstract

The inherent complexities in hydrologic phenomena have been turned into a barrier to get accurate prediction by conventional linear methods. Therefore, there is an increasing interest toward data-driven black box models. In recent decades artificial neural network (ANN) as a branch of artificial intelligence method has proved its efficiency in providing accurate results to model hydrologic processes, which subsequently leads to provide important information for the urban and environmental planning, land use, flood, and water resources management. The efficiency of any data-driven model (e.g., ANN) largely depends on quantity and quality of available data; furthermore, the occult noises in data may impact the performance of the model. Although ANN can capture the underlying complexity and nonlinear relationship between input and output parameters, there might be a need to preprocess data. In this way, noise reduction of data using an appropriate de-noising scheme may lead to a better performance in the application of the data-driven ANN model. Thereupon, in this chapter, the ANN-based hydrological models (i.e., stream-flow and sediment) were developed by focusing on wavelet-based global soft thresholding method to de-noise hydrological time series on the daily scale. The appropriate selection of decomposition level and mother wavelet type is effective in thresholding results, so that sensitivity analysis was performed over levels and several Daubechies group mother wavelets (Haar, db2, db3, db4, and db5) to choose the proper variables. In this way, de-noised time series were imposed into an ANN model to forecast flow discharge and sediment values. The comparison of obtained results for both single ANN-based and de-noised-based (i.e., preprocessed) approaches revealed that the outcomes have been improved for the later model. Furthermore, the consequences indicated that the wavelet de-noising was significantly dependent on the chosen mother wavelet whereas forecasting results varied obviously with the alteration of mother wavelets. Eventually, it was resulted that after a specific threshold, no eminent progress in results was obtained unlike the reduction occurred. Overall, the wavelet-based de-noising approach, as a preprocessing method, can be a promising idea to improve the ANN-based hydrological models.

Keywords

Artificial neural network De-noising Stream-flow Sediment Wavelet 

References

  1. Abrahart R, Anctil F, Coulibaly P et al (2012) Two decades of anarchy? Emerging themes and outstanding challenges for neural network river forecasting. Prog Phys Geogr 36(4):480–513. doi: 10.1177/0309133312444943 CrossRefGoogle Scholar
  2. Agarwal A, Mishra SK, Ram S et al (2006) Simulation of runoff and sediment yield using artificial neural networks. Biosyst Eng 94(4):597–613. http://dx.doi.org/10.1016/j.biosystemseng.2006.02.014 CrossRefGoogle Scholar
  3. Alp M, Cigizoglu HK (2007) Suspended sediment load simulation by two artificial neural network methods using hydrometeorological data. Environ Model Softw 22(1):2–13. doi: 10.1016/j.envsoft.2005.09.009#doilink. http://dx.doi.org/10.1016/j.envsoft.2005.09.009 CrossRefGoogle Scholar
  4. Cannas B, Fanni A, See L et al (2006) Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Phys Chem Earth 31(18):1164–1171. doi: 10.1016/j.pce.2006.03.020 CrossRefGoogle Scholar
  5. Dawson C, Wilby R (2001) Hydrological modeling using artificial neural networks. Prog Phys Geogr 25(1):80–108. doi: 10.1177/030913330102500104 CrossRefGoogle Scholar
  6. Dawson CH, See L, Abrahart R et al (2005) A comparative study of artificial neural network techniques for river stage forecasting. Paper presented at the international joint conference on neural networks, Montreal, vol 4, pp 2666–2670Google Scholar
  7. Donoho DH (1995) De-noising by soft-thresholding. IEEE Trans Inf Theory 41(3):613–617. doi: 10.1109/18.382009,  10.1109/18.382009#blank CrossRefGoogle Scholar
  8. Elshorbagy A, Simonovic SP, Panu US (2002) Noise reduction in chaotic hydrologic time series: facts and doubts. J Hydrol 256(3):147–165. doi: 10.1016/S0022-1694%2801%2900534-0#doilink. http://dx.doi.org/10.1016/S0022-1694(01)00534-0 CrossRefGoogle Scholar
  9. Foufoula-Georgiou E, Kumar P (1995) Wavelets in geophysics. Academic, San DiegoGoogle Scholar
  10. Grossmann A, Morlet J (1984) Decomposition of Hardy functions into square integrable wavelets of constant shape. SIAM J Math Anal 15(4):723–736. doi: 10.1137/0515056 CrossRefGoogle Scholar
  11. Guo J, Zhou J, Qin H et al (2011) Monthly streamflow forecasting based on improved support vector machine model. Expert Syst Appl 38(10):13073–13081. doi: 10.1016/j.eswa.2011.04.114#doilink. http://dx.doi.org/10.1016/j.eswa.2011.04.114 CrossRefGoogle Scholar
  12. Hornik K (1988) Multilayer feed-forward networks are universal approximators. Neural Netw 2(5):359–366. doi: 10.1016/0893-6080(89)90020-8,  10.1016/0893-6080%2889%2990020-8#_self CrossRefGoogle Scholar
  13. Hsu KL, Gupta HV, Sorooshian S (1995) Artificial neural network modeling of the rainfall-runoff process. Water Resour Res 31(10):2517–2530. doi: 10.1029/95WR01955 CrossRefGoogle Scholar
  14. Jain SK (2001) Development of integrated sediment rating curves using ANNs. J Hydraul Eng 127(1):30–37. doi: 10.1061/%28ASCE%290733-9429%282001%29127:1%2830%29. http://dx.doi.org/10.1061/(ASCE)0733-9429(2001)127:1(30)CrossRefGoogle Scholar
  15. Jain A, Ormsbee LE (2002) Short-term water demand forecast modeling techniques: conventional methods versus AI. J Am Water Works Assoc 94(7):64–72Google Scholar
  16. Jansen M (2006) Minimum risk thresholds for data with heavy noise. IEEE Signal Process Lett 13:296–299. doi: 10.1109/LSP.2006.870355,  10.1109/LSP.2006.870355#blank CrossRefGoogle Scholar
  17. Kalman RE (1960) A new approach to linear filtering and prediction problems. J Fluids Eng 82(1):35–45Google Scholar
  18. Kisi O (2009) Daily suspended sediment estimation using neuro-wavelet models. Int J Earth Sci 99:1471–1482. doi: 10.1007/s00531-009-0460-2 CrossRefGoogle Scholar
  19. Labat D (2005) Recent advances in wavelet analyses. Part 1: a review of concepts. J Hydrol 314:275–288. doi: 10.1016/j.jhydrol.2005.04.003#doilink. http://dx.doi.org/10.1016/j.jhydrol.2005.04.003 CrossRefGoogle Scholar
  20. Labat D, Ababou R, Mangin A (2000) Rainfall-runoff relation for Karstic Spring. Part 2: continuous wavelet and discrete orthogonal multi resolution analyses. J Hydrol 238:149–178. doi: 10.1016/S0022-1694%2800%2900322-X#doilink. http://dx.doi.org/10.1016/S0022-1694(00)00322-X CrossRefGoogle Scholar
  21. Maier HR, Jain A, Dandy GC et al (2010) Methods used for the development of neural networks for the prediction of water resources variables: current status and future directions. Environ Model Softw 25:891–909. doi: 10.1016/j.envsoft.2010.02.003#doilink. http://dx.doi.org/10.1016/j.envsoft.2010.02.003 CrossRefGoogle Scholar
  22. Mallat SG (ed) (1998) A wavelet tour of signal processing. Academic, San DiegoGoogle Scholar
  23. Martyn PC, David ER, Ross AW et al (2008) Hydrological data assimilation with the ensemble Kalman filter: use of streamflow observations to update states in a distributed hydrological model. Adv Water Resour 31:1309–1324. doi: 10.1016/j.advwatres.2008.06.005#doilink. http://dx.doi.org/10.1016/j.advwatres.2008.06.005 CrossRefGoogle Scholar
  24. Melesse AM, Ahmad S, McClain ME et al (2011) Suspended sediment load prediction of river systems: an artificial neural network approach. Agric Water Manag 98:855–866. doi: 10.1016/j.agwat.2010.12.012#doilink. http://dx.doi.org/10.1016/j.agwat.2010.12.012 CrossRefGoogle Scholar
  25. Nejad FH, Nourani V (2012) Elevation of wavelet de-noising performance via an ANN-based streamflow forecasting model. Int J Comput Sci Manag Res 1(4):764–770Google Scholar
  26. Nourani V (2009) Using artificial neural networks (ANNs) for sediment load forecasting of Talkherood River mouth. J Urban Environ Eng 3(1):1–6. doi: 10.4090/juee.2009.v3n1.001006 CrossRefGoogle Scholar
  27. Nourani V, Fard MS (2012) Sensitivity analysis of the artificial neural network outputs in simulation of the evaporation process at different climatologicr. Adv Eng Softw 47(1):127–146. doi: 10.1016/j.advengsoft.2011.12.014#doilink. http://dx.doi.org/10.1016/j.advengsoft.2011.12.014 CrossRefGoogle Scholar
  28. Nourani V, Mogaddam AA, Nadiri AO (2008) An ANN based model for spatiotemporal groundwater level forecasting. Hydrol Process 22:5054–5066. doi: 10.1002/hyp.7129 CrossRefGoogle Scholar
  29. Nourani V, Komasi M, Mano A (2009a) A multivariate ANN-wavelet approach for rainfall–runoff modeling. Water Resour Manag 23:2877–2894. doi: 10.1007/s11269-009-9414-5 CrossRefGoogle Scholar
  30. Nourani V, Alami MT, Aminfar MH (2009b) A combined neural-wavelet model for prediction of Ligvanchai watershed precipitation. Eng Appl Artif Intell 22:466–472. doi: 10.1016/j.engappai.2008.09.003#doilink. http://dx.doi.org/10.1016/j.engappai.2008.09.003 CrossRefGoogle Scholar
  31. Nourani V, Komasi M, Alami MT (2012a) A hybrid wavelet-genetic programming approach to optimize ANN modeling of rainfall-runoff process. J Hydrol Eng 17(6):724–741. doi: 10.1061/%28ASCE%29HE.1943-5584.0000506#_blank#Opens new window. http://dx.doi.org/10.1061/(ASCE)HE.1943-5584.0000506 CrossRefGoogle Scholar
  32. Nourani V, Kalantari O, Hosseini Baghanam A (2012b) Two semi-distributed ANN-based models for estimation of suspended sediment load. J Hydrol Eng 17(12):1368–1380. doi: 10.1061/%28ASCE%29HE.1943-5584.0000587#_blank#Opensnew window. http://dx.doi.org/10.1061/(ASCE)HE.1943-5584.0000587 CrossRefGoogle Scholar
  33. Nourani V, Hosseini Baghanam A, Adamowski JF et al (2013) Using self-organizing maps and wavelet transforms for space–time pre-processing of satellite precipitation and runoff data in neural network based rainfall–runoff modeling. J Hydrol 476:228–243. doi: 10.1016/j.jhydrol.2012.10.054#doilink. http://dx.doi.org/10.1016/j.jhydrol.2012.10.054 CrossRefGoogle Scholar
  34. Porporato A, Ridolfi L (1997) Nonlinear analysis of river flow time sequences. Water Resour Res 33(6):1353–1367. doi: 10.1029/96WR03535 CrossRefGoogle Scholar
  35. Rai RK, Mathur BS (2008) Event-based sediment yield modeling using artificial neural network. Water Resour Manag 22:423–441. doi: 10.1007/s11269-007-9170-3; 10.3390/e11041123 CrossRefGoogle Scholar
  36. Rajaee T, Mirbagheri SA, Nourani V et al (2010) Prediction of daily suspended sediment load using wavelet and neuro-fuzzy combined model. Int J Environ Sci Technol 7(1):93–110CrossRefGoogle Scholar
  37. Reichel RH, Walker JP, Koster RD et al (2002) Extended versus ensemble Kalman filtering for land data assimilation. J Hydrometeorol 3:728–740CrossRefGoogle Scholar
  38. Rogers R (1996) Neural networks: a systematic introduction. Springer, BerlinGoogle Scholar
  39. Salas JD, Delleur JW, Yevjevich V et al (eds) (1980) Applied modeling of hydrologic time series. Water Resources Publications, Highlands Ranch, COGoogle Scholar
  40. Sang YF (2013) A review on the applications of wavelet transform in hydrology time series analysis. Atmos Res 122:8–15. doi: 10.1016/j.atmosres.2012.11.003#doilink. http://dx.doi.org/10.1016/j.atmosres.2012.11.003 CrossRefGoogle Scholar
  41. Sang YF, Wang D, Wu JC et al (2009a) Entropy-based wavelet de-noising method for time series analysis. Entropy 11(4):1123–1147. doi: 10.3390/e11041123 CrossRefGoogle Scholar
  42. Sang YF, Wang D, Wu JC et al (2009b) The relationship between period’s identification and noises in hydrological series data. J Hydrol 368:165–177. doi: 10.1016/j.jhydrol.2009.01.042#doilink. http://dx.doi.org/10.1016/j.jhydrol.2009.01.042 CrossRefGoogle Scholar
  43. Schouten JC, Takens F, Van den Bleek CM (1994) Estimation of the dimension of a noisy attractor. Phys Rev E 50(3):1851–1861. http://link.aps.org/doi/10.1103/PhysRevE.50.1851 Google Scholar
  44. Sivakumar B, Phoon KK, Liong SY et al (1999) A systematic approach to noise reduction in chaotic hydrological time series. J Hydrol 219:103–135. doi: 10.1016/S0022-1694%2899%2900051-7#doilink. http://dx.doi.org/10.1016/S0022-1694(99)00051-7 CrossRefGoogle Scholar
  45. Solomatine DP, Price RK (2004) Innovative approaches to flood forecasting using data driven and hybrid modeling. In: Liong S.Y. et al., (ed)Proceedings of the 6th International Conference on Hydroinformatics, Singapore, 2004Google Scholar
  46. Tayfur G (2002) Artificial neural networks for sheet sediment transport. Hydrol Sci J 47(6):879–892CrossRefGoogle Scholar
  47. Tokar AS, Johnson PA (1999) Rainfall-runoff modeling using artificial neural network. J Hydrol Eng 4(3):232–239CrossRefGoogle Scholar
  48. Wiener N (1964) Extrapolation, interpolation, and smoothing of stationary time series: with engineering applications. Technology Press of the Massachusetts Institute of Technology, Cambridge, MAGoogle Scholar
  49. Zhang G, Patuwo E, Hu M (1998) Forecasting with artificial neural networks: the state of the art. Int J Forecast 14:35–62. doi: 10.1016/S0169-2070%2897%2900044-7#doilink. http://dx.doi.org/10.1016/S0169-2070(97)00044-7 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2014

Authors and Affiliations

  • Vahid Nourani
    • 1
    Email author
  • Aida Hosseini Baghanam
    • 1
  • Aida Yahyavi Rahimi
    • 1
  • Farzad Hassan Nejad
    • 1
  1. 1.Faculty of Civil Engineering, Department of Water Resources EngineeringUniversity of TabrizTabrizIran

Personalised recommendations