Advertisement

Development of streamflow prediction models for a weir using ANN and step-wise regression

  • Muhammad Hassan
  • Haseeb Zaffar
  • Imran Mehmood
  • Anwar Khitab
Original Article
  • 5 Downloads

Abstract

The study was aimed to develop an accurate prediction model for streamflow at Patrind Hydropower Station located on Kunhar river right on the border line of district Abbottabad, KPK and district Muzaffarabad, AJK. Antecedent meteorological data condition of upstream site was considered as inputs. A variety of input combinations were made to select the suitable ones for smooth model development. The model training was carried out using two artificial neural networking techniques; two layer back propagation and Broyden Fletcher GoldfrabShano. The results were also compared with a step-wise regression based model. The best model was evaluated on the basis of distributive statistics analysis such as root mean square error, bias, variance and correlation coefficient R2. All the developed models showed extraordinary results with very high values of model efficiency (more than 95%) but model based upon step-wise regression technique outperformed all the other models with low values of variance and BIAS.

Keywords

ANN Meteorological conditions Model development Statistics analysis streamflow Training 

Notes

Acknowledgements

The authors would like to acknowledge the guidance and support of Late Sir Muhammad Ali Shamim to carry out this research work. The authors are also thankful to the students of civil engineering department, MUST for their effort and contribution in this project.

References

  1. Adıgüzel F, Tutu SA (2002) Small hydroelectric power plants in turkey. In: Proceedings of hydro 2002, development, management, performance, 4–7 November, pp 283–293Google Scholar
  2. Agalbjorn S, Koncar N, Jones AJ (1997) A note on gamma test. Neural Comput Appl 5(3):131–133CrossRefGoogle Scholar
  3. Alqudah A, Chandrasekar V, Le M (2013) Investigating rainfall estimation from radar measurements using neural networks. Nat Hazards Earth Syst Sci 13:535–544CrossRefGoogle Scholar
  4. Bloschl G, Sivapalan M (1995) Scale issues in hydrological modeling a review. Hydrol Process 9:251–290CrossRefGoogle Scholar
  5. Bray M, Han D (2004) Identification of support vector machines for runoff modeling. J Hydroinform 6(4):265–280CrossRefGoogle Scholar
  6. Burges SJ, Hoshi K (1978) Approximation of a normal distribution by a three parameter log normal distribution. Water Resour Res 14:620–622CrossRefGoogle Scholar
  7. Chuzhanova NA, Jones AJ, Margetts S (1998) Feature selection for genetic sequence classification. Bioinformatics 14:139–143CrossRefGoogle Scholar
  8. Cluckie ID, Han D (2000) Fluvial flood forecasting. Water Environ 14:270–276CrossRefGoogle Scholar
  9. de Oliveira MC (1999) Linear systems control design based on linear matrix inequalities (Ph.D. thesis), Campinas, SP, Brazil: University of Campinas (in Portuguese)Google Scholar
  10. Dong X, Dohmen-Janssen CM, Booij M, Hulscher S (2006) Effect of flow forecasting quality on benefits of reservoir operation—a case study for the Geheyan reservoir (China). Hydrol Earth Syst Sci Discuss 3:3771–3814CrossRefGoogle Scholar
  11. Faraway JJ (2002) Practical regression and ANOVA in R. http://cran.r-project.org/doc/contrib/Faraway-PRA.pdf
  12. Fine TL (1999) Feedforward neural network methodology. Statistics for engineering and information science. Springer, New York, p 340Google Scholar
  13. Fletcher R (1987) Practical methods of optimization. Wiley, New YorkGoogle Scholar
  14. Hamlet AF, Huppert D, Lettenmaier DP (2002) Economic value of long lead stream flow forecasts for Columbia river hydropower. J Water Res Plan Manag 128(2):91–101CrossRefGoogle Scholar
  15. Han D, Cluckie ID, Karbassioun D, Lawry J, Krauskopf B (2002) River flow modelling using fuzzy decision trees. Water Resour Manag 16:431–445CrossRefGoogle Scholar
  16. Han D, Chan L, Zhu N (2007) Flood forecasting using support vectormachines. J Hydroinform 9(4), 267–276CrossRefGoogle Scholar
  17. Hassan M, Shamim MA, Hashmi HN, Ashiq SZ, Ahmed I, Pasha GA, Naeem UA, Ghumman AR, Han D (2014) Predicting streamflows to a multipurpose reservoir using artificial neural networks and regression techniques. Earth Sci Inform 8(2), 337–352CrossRefGoogle Scholar
  18. Hassan M, Shamim MA, Sikandar A, Mehmood I, Ahmed I, Ashiq SZ, Khitab A (2015) Development of sediment load estimation models by using artificial neural networking techniques. Environ Monit Assess 187:686.  https://doi.org/10.1007/s10661-015-4866-y CrossRefGoogle Scholar
  19. Haykin S (1999) Neural networks: a comprehensive foundation, 2nd edn. Pearson Education (Singapore) Pte.Ltd., DehliGoogle Scholar
  20. Hegyi G, Garamszegi LZ (2010) Using information theory as a substitute for stepwise regression in ecology and behavior. Behav Ecol Socbiol 65:69–76CrossRefGoogle Scholar
  21. Ishak AM, Remesan R, Srivastava PK, Islam T, Han D (2013) Error correction modelling of wind speed through hydro-meteorological parameters and mesoscale model: a hybrid approach. Water Resour Manag 27:1–23CrossRefGoogle Scholar
  22. Jones AJ (2004) New tools in non-linear modelling and prediction. CMS 1:109–149CrossRefGoogle Scholar
  23. Kim YO, Palmer RN (1997) Value of seasonal flow forecasts in bayesian stochastic programming. J Water Resour Plan Manag 123:327–335CrossRefGoogle Scholar
  24. Kisi O, Cimen M (2012) Precipitation forecasting by using wavelet-support vector machine conjunction model. Eng Appl Artif Intell 25:783–792CrossRefGoogle Scholar
  25. Koncar N (1997) Optimization methodologies for direct inverse neuro-control. Ph.D. thesis, Department of Computing, Imperial College of Science Technology & Medicine, University of LondonGoogle Scholar
  26. Lekkas DF, Imrie CE, Lees MJ (2001) Improved nonlinear transfer function and neural network methods of flowrouting for real-time forecasting. J Hydroinform 3:153–164CrossRefGoogle Scholar
  27. Maier HR, Dandy GC (1998) The effect of internal parameters and geometry on the performance of back-propagation neural networks: an empirical study. Environ Model Softw 13(20):193–209CrossRefGoogle Scholar
  28. McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4), 115–133CrossRefGoogle Scholar
  29. Miller A (2002) Subset selection in regression. Chapman & Hall, London, p 256CrossRefGoogle Scholar
  30. Minsky M, Papert S (1969) Perceptrons. MIT Press, CambridgeGoogle Scholar
  31. Moghaddamnia A, Gousheh MG, Piri J, Amin S, Han D (2009a) Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques. Adv Water Resour 32(1):88–97CrossRefGoogle Scholar
  32. Moghaddamnia A, Remesan R, Kashani MH, Mohammadi M, Han D, Piri J (2009b) Comparison of LLR, MLP, Elman, NNARX and ANFIS Models—with a case study in solar radiation estimation. J Atmos Solar Terr Phys 71(8–9):975–982CrossRefGoogle Scholar
  33. Nathan RJ, McMahon TA (1990) Identification of homogenous regions for the purposes of regionalization. J Hydrol 121:217–238CrossRefGoogle Scholar
  34. Parker D, Tunstall S, Wilson T (2005) Socio-economic benefits of flood forecasting and warning. In: Proceedings of the international conference on innovation, advances and implementation of flood forecasting technology, Norway, Tromso, 17–19 October 2005Google Scholar
  35. Pilgrim DH (1983) Some problems in transferring hydrological relationships between small and large drainage basins and between regions. J Hydrol 65:49–72CrossRefGoogle Scholar
  36. Piri J, Amin S, Moghaddamnia A, Keshavarz A, Han D, Remesan R (2009) Daily pan evaporation modeling in a hot and dry climate. J Hydrol Eng 14(8):803–811CrossRefGoogle Scholar
  37. Post DA, Jakeman AJ (1996) Relationships between catchment attributes and hydrological response characteristics in small Australian mountain ash catchments. Hydrol Process 10:877–892CrossRefGoogle Scholar
  38. Post DA, Jakeman AJ (1999) Predicting the daily streamflow of un-gauged catchments in SE Australia by regionalizing the parameters of a lumped conceptual rainfall-runoff model. Ecol Model 123:91–104CrossRefGoogle Scholar
  39. Private Power & Infrastructure Board (2002) Hydel Potential in Pakistan, Report Private Power and Infrastructure Board, Ministry of Water & Power Government of Pakistan. http://www.nepra.org.pk/Policies/Hydel%20Potential%20in%20Pakistan.pdf
  40. Remesan R, Shamim MA, Han D (2008) Model data selection using gamma test for daily solar radiation estimation. Hydrol Process 22:4301–4309CrossRefGoogle Scholar
  41. Remesan R, Shamim MA, Han D, Mathew J (2009) Runoff prediction using an integrated hybrid modelling scheme. J Hydrol 372:48–60CrossRefGoogle Scholar
  42. Remesan R, Shamim MA, Ahmadi A, Han D (2010) Effect of data time interval on real-time flood forecasting. J Hydroinform 12:396–407CrossRefGoogle Scholar
  43. Rosenblatt F (1961) Principles of neurodynamics: perceptions and the theory of brain mechanism. Spartan Books, Washington, DCCrossRefGoogle Scholar
  44. Sattari MT, Yurekli K, Pal M (2012a) Performance evaluation of artificial neural network approaches in forecasting reservoir inflow. Appl Math Model 36:2649–2657CrossRefGoogle Scholar
  45. Sattari MT, Apaydin H, Ozturk F (2012b) Flow estimations for sohy stream using artificial neural networks. Environ Earth Sci 66:2031–2045CrossRefGoogle Scholar
  46. Sattari MT, Apaydin H, Ozturk F (2013a) Stochastic operation analysis of irrigation reservoir in low flow conditions: a case study from Eleviyan reservoir Iran. Turk J Agric For 37:613–622CrossRefGoogle Scholar
  47. Sattari MT, Pal M, Ozturk AH, Ozturk F (2013b) M5 model tree application in daily river flow forecasting in Sohu Stream Turkey. Water Resour 40:233–242CrossRefGoogle Scholar
  48. Sefton CEM, Howarth SM (1998) Relationships between dynamic response characteristics and physical descriptors of catchments in England and Wales. J Hydrol 211:1–16CrossRefGoogle Scholar
  49. Shamim MA, Remesan R, Han D, Ghumman AR (2010) Solar radiation estimation in un-gauged catchments. Proc ICE Water Manag 163:349–359Google Scholar
  50. Shamim MA, Remesan R, Bray M, Han D (2015) An improved technique for global solar radiation estimation using numerical weather prediction. J Atmos Solar Terr Phys 129:13–22CrossRefGoogle Scholar
  51. Srivastava PK, Han D, Rico-Ramiraz MA, Bray M, Islam T (2012) Selection of classification techniques for land use/land cover change investigation. Adv Space Res 50:1250–1265CrossRefGoogle Scholar
  52. Stefansson A, Koncar N, Jones AJ (1997) A note on the gamma test. Neural Comput Appl 5:131–133CrossRefGoogle Scholar
  53. Vandewiele GL, Elias A (1995) Monthly water balance of ungauged catchments obtained by geographical regionalisation. J Hydrol 170:277–291CrossRefGoogle Scholar
  54. Wang W (2006) Stochasticity, nonlinearity and forecasting of streamflow processes. IOS Press, AmsterdamGoogle Scholar
  55. Yeh WWG, Becker L, Zettlemoyer R (1982) Worth of inflow forecast for reservoir operation. J Water Resour Plan Manag 108:257–269Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Civil EngineeringMUSTMirpurPakistan

Personalised recommendations