Advertisement

Water Resources Management

, Volume 31, Issue 12, pp 4023–4043 | Cite as

An Integration of Stationary Wavelet Transform and Nonlinear Autoregressive Neural Network with Exogenous Input for Baseline and Future Forecasting of Reservoir Inflow

  • Siriporn Supratid
  • Thannob Aribarg
  • Seree Supharatid
Article
  • 223 Downloads

Abstract

For effective water resources management and planning, an accurate reservoir inflow forecast is essential not only in training and testing phases but also in particular future periods. The objective of this study is to develop a reservoir inflow integrated forecasting model, relying on nonlinear autoregressive neural network with exogenous input (NARX) and stationary wavelet transform (SWT), namely SWT-NARX. Due to the elimination of down-sampling operation, SWT provides influential reinforcement of efficiently extracting the hidden significant, temporal features contained in the nonstationary inflow time series without information loss. The decomposed SWT sub-time series are determined as input-output for NARX forecaster; where a multi-model ensemble global mean (MMEGM) of downscaled precipitation based on nine global climate models (GCMs) represents as a climate-change exogenous input. Two major reservoirs in Thailand, Bhumibol and Sirikit ones are focused. Pearson’s correlation coefficient (r) and root mean square error (RMSE) are employed for performance evaluation. The achieved results indicate that the SWT-NARX explicitly outperforms the comparable forecasting approaches regarding a historical baseline period (1980–1999). Therefore, such SWT-NARX is further employed for future projection of the reservoir inflow over near (2010–2039) -, mid (2040–2069) - and far (2070–2099) - future periods against the inflow of the baseline one.

Keywords

Inflow forecast Nonlinear autoregressive neural network with exogenous input Stationary wavelet transform Bhumibol reservoir Sirikit reservoir 

Notes

Acknowledgements

We gratefully thank to the National Research Council of Thailand (NRCT) for funding this work. We also thank to the electricity generating authority of Thailand (EGAT) and Thai Meteorological Department for providing the observed reservoir inflow and rainfall data respectively.

References

  1. Bai Y, Wang P, Li C, Xie J, Wang Y (2014) A multi-scale relevance vector regression approach for daily urban water demand forecasting. J Hydrol 517:236–245CrossRefGoogle Scholar
  2. Box GEP, Jenkins GM, Reinsel GC (1994) Time Series Analysis: Forecasting and Control, 3rd edn. Prentice hall, Englewood cliffs pp 197–199Google Scholar
  3. Brands S, Herrera S, Ferna’ndez J, Gutie’rrez JM (2013) How well do CMIP5 earth system models simulate present climate conditions in Europe and Africa? Clim Dyn 41(3):803–817CrossRefGoogle Scholar
  4. Campos JNB, Souza Filho FA, Lima HVC (2014) Risks and uncertainties in reservoir yield in highly variable intermittent rivers: case of the Castanhão reservoir in semi-arid Brazil. Hydrol Sci J 59(6):1184–1195CrossRefGoogle Scholar
  5. Chang FJ, Chen PA, Lu YR, Huang E, Chang KY (2014) Real-time multi-step-ahead water level forecasting by recurrent neural networks for urban flood control. J Hydrol 517:836–846CrossRefGoogle Scholar
  6. Chen S, Billings SA, Grant PM (1990) Non-linear system identification using neural networks. Int J Control 51(6):1191–1214CrossRefGoogle Scholar
  7. Cook BI, Seager R (2013) The response of the North American monsoon to increased greenhouse gas forcing. J Geophys Res Atmos 118(4):1690–1699CrossRefGoogle Scholar
  8. Elman JL (1990) Finding structure time. Cogn Sci 14(2):179–221CrossRefGoogle Scholar
  9. El-Shafie A, Noureldin A, Taha M, Hussain A, Mukhlisin M (2012) Dynamic versus static neural network model for rainfall forecasting at Klang River basin, Malaysia. Hydrol Earth Syst Sci 16(4):1151–1169CrossRefGoogle Scholar
  10. Fowler JE (2005) The redundant discrete wavelet transform and additive noise. IEEE Signal Process Lett 12(9):629–632CrossRefGoogle Scholar
  11. Horne BG, Giles CL (1995) An experimental comparison of recurrent neural networks. MIT Press, In Advanc in Neural Info Process Syst, pp 697–704Google Scholar
  12. Hsu P-C et al (2012) Increase of global monsoon area and precipitation under global warming: a robust signal? Geophys Res Lett 39(6):L06701Google Scholar
  13. Hsu P-C, Li T, Murakami H, Kitoh A (2013) Future change of the global monsoon revealed from 19 CMIP5 models. J Geophys Res Atmos 118(3):1247–1260CrossRefGoogle Scholar
  14. Jang JSR, Sun CT, Mizutani E (1997) Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence. Prentice-Hall, Englewood Cliffs pp 665–685Google Scholar
  15. Joetzjer E, Douville H, Delire C, Ciais P (2013) Present-day and future Amazonian precipitation in global climate models: CMIP5 versus CMIP3. Clim Dyn 41(11):2921–2936CrossRefGoogle Scholar
  16. Jothiprakash V, Magar RB (2012) Multi-time-step ahead daily and hourly intermittent reservoir inflow prediction by artificial intelligent techniques using lumped and distributed data. J Hydrol 450–451:293–307CrossRefGoogle Scholar
  17. Karl TR, Melillo JM, Peterson TC (eds) (2009) Global climate change impacts in the United States. Cambridge University Press, New YorkGoogle Scholar
  18. Knutti R, Abramowitz G, Collins M, Eyring V, Gleckler PJ, Hewitson BM, Mearns L (2010) Good practice guidance paper on Assessing and combining multi model climate projections. Meeting report of the intergovernmental panel on climate change expert meeting on Assessing and combining multi model climate projections. University of Bern, Bern, IPCC Working Group I Technical Support UnitGoogle Scholar
  19. Koza JR (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, CambridgeGoogle Scholar
  20. Krishna B (2014) Comparison of wavelet based ANN and regression models for reservoir inflow forecasting. J Hydrol Eng 19(7):1385–1400CrossRefGoogle Scholar
  21. Kucuk M, Oglu NA (2006) Wavelet regression technique for stream flow prediction. J Appl Stat 33(9):943–960CrossRefGoogle Scholar
  22. Kumar D, Kodra E, Ganguly AR (2014) Regional and seasonal intercomparison of CMIP3 and CMIP climate model ensembles for temperature and precipitation. Clim Dyn 43(9):2491–2518CrossRefGoogle Scholar
  23. Kumar S, Tiwari MK, Chatterjee C, Mishra A (2015) Reservoir inflow forecasting using ensemble models based on neural networks, wavelet analysis and bootstrap method. Water Resour Manag 29(13):4863–4883CrossRefGoogle Scholar
  24. Kummong R, Supratid S (2016) Thailand tourism forecasting based on a hybrid of discrete wavelet decomposition and NARX neural network. Ind Manag Data Syst 116(6):1242–1258CrossRefGoogle Scholar
  25. Latt ZZ (2015) Application of feedforward artificial neural network in Muskingum flood routing: a black-box forecasting approach for a Natural River system. Water Resour Manag 29(14):4995–5014CrossRefGoogle Scholar
  26. Leontaritis IJ, Billings SA (1985) Input-output parametric models for non-linear systems part I: deterministic non-linear systems. Int J Control 41(2):303–328CrossRefGoogle Scholar
  27. Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11(7):674–693CrossRefGoogle Scholar
  28. Mariotti A et al (2008) Mediterranean water cycle changes: transition to drier twenty-first century conditions in observations and CMIP3 simulations. Environ Res Lett 3(4):044001CrossRefGoogle Scholar
  29. Meehl GA, Covey C, Delworth T, Latif M, McAvaney B, Mitchell JFB, Stouffer RJ, Taylor KE (2007) The WCRP CMIP3 multimodel dataset: a new era in climate change research. Bull Am Meteorol Soc 88(9):1383–1394CrossRefGoogle Scholar
  30. Vu MT, Aribarg T, Supratid S, Raghavan SV, Liong S-Y (2016) Statistical downscaling rainfall using artificial neural network: significantly wetter Bangkok? Theor Appl Climatol 126(3):453–467Google Scholar
  31. Mohanty S, Jha MK, Raul SK, Panda RK, Sudheer KP (2015) Using artificial neural network approach for simultaneous forecasting of weekly groundwater levels at multiple sites. Water Resour Manag 29(15):5521–5532CrossRefGoogle Scholar
  32. Moss RH, Edmonds JA, Hibbard KA et al (2010) The next generation of scenarios for climate change research and assessment. Nature 463(7282):747–756CrossRefGoogle Scholar
  33. Nakicenovic N et al (2000) Special Report on Emissions Scenarios (SRES): A Special Report of Working Group III of the Intergovernmental Panel on Climate Change. Cambridge University Press. http://www.grida.no/climate/ipcc/emission/index.htm. Accesses 2 Oct 2016
  34. Narendra KS, Parthasarathy K (1990) Identification and control of dynamical systems using neural networks. IEEE Trans Neural Netw 1(1):4–27CrossRefGoogle Scholar
  35. Norgaard M, Ravn O, Poulsen NK, Hansen LK (2000) Neural networks for Modelling and control of dynamic systems. Springer, BerlinCrossRefGoogle Scholar
  36. Okkan U (2012) Wavelet neural network model for reservoir inflow prediction. Sci Iran 19(6):1445–1455CrossRefGoogle Scholar
  37. Rogelj J, Meinshausen M, Knutti R (2012) Global warming under old and new scenarios using IPCC climate sensitivity range estimates. Nat Clim Chang 2(4):248–253CrossRefGoogle Scholar
  38. Rumelhart DE, JL MC, Corporate PDP Research Group (1986) Parallel distributed processing: explorations in the microstructure of cognition, vol 1. MIT Press, CambridgeGoogle Scholar
  39. Sanderson BM, Knutti R (2012) On the interpretation of constrained climate model ensembles. Geophys Res Lett 39(16):1–6 (L16708)Google Scholar
  40. Santer BD, Taylor KE, Glecker PJ et al (2009) Incorporating model quality information in climate change detection and attribution studies. Proc Natl Acad Sci 106(35):14778–14783CrossRefGoogle Scholar
  41. Seager R et al (2007) Model projections of an imminent transition to a more arid climate in southwestern North America. Science 316(5828):1181–1184CrossRefGoogle Scholar
  42. Sehgal V, Sahay RR, Chatterjee C (2014a) Effect of utilization of discrete wavelet components on flood forecasting performance of wavelet based ANFIS models. Water Resour Manag 28(6):1733–1749CrossRefGoogle Scholar
  43. Sehgal V, Tiwari MK, Chatterjee C (2014b) Wavelet bootstrap multiple linear regression based hybrid modeling for daily river discharge forecasting. Water Resour Manag 28(10):2793–2811CrossRefGoogle Scholar
  44. Shafaei M, Kisi O (2016) Lake level forecasting using wavelet-SVR, wavelet-ANFIS and wavelet-ARMA conjunction models. Water Resour Manag 30(1):79–97CrossRefGoogle Scholar
  45. Shenify M, Danesh AS, Gocić M, Taher RS, Wahab AWA, Gani A, Shamshirband S, Dalibor P (2016) Precipitation estimation using support vector machine with discrete wavelet transform. Water Resour Manag 30(2):641–652CrossRefGoogle Scholar
  46. Shensa MJ (1992) The discrete wavelet transform: wedding the a Trous and Mallat algorithms. IEEE Trans Signal Process 40(10):2464–2482CrossRefGoogle Scholar
  47. Solomon S, Qin D, Manning M, Chen Z, Marquis M, Averyt KB, Tignor M, Miller HL (eds) (2007) Climate change 2007: the physical Science basis. Working Group I Contribution to the Fourth Assessment Report of the Intergovernmental Panel on Climate ChangeGoogle Scholar
  48. Stocker TF, Qin D, Plattner GK, Tignor M, Allen SK, Boschung J (2013) Climate change 2013. The Physical Science Basis. Working Group I Contribution to the Fifth Assessment Report of the Intergovernmental Panel on Climate ChangeGoogle Scholar
  49. Supharatid S, Aribarg T, Supratid S (2016) Assessing potential flood vulnerability to climate change by CMIP3 and CMIP5 models: case study of the 2011 Thailand great flood. J Water Clim Change 7(1):52–67Google Scholar
  50. Supharatid S (2016) Skill of precipitation projection in the Chao Phraya river basin by multi-model ensembleCMIP3-CMIP5. Weather Clim Extremes 12:1–14CrossRefGoogle Scholar
  51. Taylor KE, Stouffer RJ, Meehl GA (2012) An overview of CMIP5 and the experimental design. Bull Am Meteorol Soc 93(4):485–498CrossRefGoogle Scholar
  52. Teutschbein C, Seibert J (2012) Bias correction of regional climate model simulations for hydrological climate-change impact studies: review and evaluation of different methods. Hydrol 456-457:12–29CrossRefGoogle Scholar
  53. Tipping ME (2000) The relevance vector machine. Adv Neural Inf Proces Syst 12:652–658Google Scholar
  54. Tiwari MK, Song KY, Chatterjee C, Gupta MM (2013) Improving reliability of river flow forecasting using neural networks, wavelets and self-organizing maps. J Hydroinf 15(2):486–502CrossRefGoogle Scholar
  55. Valipour M, Banihabib ME, Behbahani SMR (2013) Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. J Hydrol 476(7):433–441CrossRefGoogle Scholar
  56. Valipour M (2016) Optimization of neural networks for precipitation analysis in a humid region to detect drought and wet year alarms. Meteorol Appl 23(1):91–100CrossRefGoogle Scholar
  57. Vapnik VN (1995) The nature of statistical learning theory. Springer, New YorkCrossRefGoogle Scholar
  58. Wehner M (2013) Methods of projecting future changes in Extremes. Extremes in a Changing Clim 65:223–237CrossRefGoogle Scholar
  59. Wilks D (1990) Maximum likelihood estimation for the gamma distribution using data containing zeros. J Clim 3(12):1495–1501CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2017

Authors and Affiliations

  • Siriporn Supratid
    • 1
  • Thannob Aribarg
    • 1
    • 2
  • Seree Supharatid
    • 3
  1. 1.College of Information Technology and CommunicationRangsit UniversityPathumthaniThailand
  2. 2.Climate Change and Disaster CenterRangsit UniversityPathumthaniThailand
  3. 3.Provincial Waterworks AuthorityBangkokThailand

Personalised recommendations