Evaluation of Six Neural Networks and Two Geostatistical Methods for Generating the Missing Precipitation Data

Document Type : Research Paper

Authors

Abstract

Improving the accuracy of the missing precipitation data, particularly in large watershed with low-density precipitation network, is one of the challenges of the hydrologists. This study investigated six different types of artificial neural networks, namely: the MLP, the TLFN, the RBF, the RNN, the TDRNN, the CFNN along with different optimization methods, and geostatistical methods namely the Kriging and the Cokriging models for infilling the missing daily precipitation. Daily precipitation records from 15 rain gaging stations located within the Karkheh Watershed in the southwest Iran, were used to evaluate the accuracy of different models for infilling data gaps of daily precipitation. The results suggest that the MLP, the TLFN the CFNN and the Cokriging can provide more accurate estimates of the missing precipitation values than the other ones. However, the MLP overall appears to be the most effective method for infilling the missing daily precipitation values. Moreover, the results show that the dynamically driven networks (RNN and TDRNN) are less suitable for infilling the daily precipitation records whereas the RBF are appeared to be fairly suitable. Also, the kriging model is less effective than the MLP, the Cokriging, the TLFN and the CFNN models, but shows better results than the RNN, TDRNN and RBF networks.

Keywords

References

  1. حسنی پاک، ع. 1377. زمین آمار (ژئواستاتیستیک). انتشارات دانشگاه تهران، چاپ اول.
  2. ثقفیان، ب، س، رحیمی بندر آبادی. 1384. مقایسه روشهای درون یابی و برون یابی براورد توزیع مکانی مقدار بارندگی سالانه. تحقیقات منابع آب ایران. 1(2): 74-84
  3. ثقفیان، ب، ه،  رزمخواه، ب، قرمز چشمه. 1390. بررسی تغییرات منطقه ای بارش سالانه با کاربرد روشهای زمین آمار (مطالعه موردی استان فارس). مجله مهندسی منابع آب. سال چهارم.
  4. رحیمی بندر آبادی، س. ب، ثقفیان. 1386. برآورد توزیع مکانی بارندگی با کمک نظری مجموعه­های فازی. تحقیقات منابع آب ایران. 3(2): 26-38
  5. شقاقی، م. م، نظری فر. ر، مومنی. ز، زواره ای مقدم. 1385. بررسی تغییرات منطقه ای بارش ماهانه و سالانه حوضه کارون با استفاده از روشهای زمین آمار. اولین همایش منطقه ای بهره برداری بهینه از منابع آب حوضه­های کارون و زاینده رود. شهرکرد.
  6. عساکره، ح. 1387. کاربرد روش کریجینگ در درون یابی بارش. مطالعه موردی درون یابی بارش در ایران. جغرافیا و توسعه. 12: 25-42
  7. طایفه نسکیلی، ن. 1389. بررسی روشهای مختلف تحلیل داده های مفقود جریان رودخانه (مطالعه موردی حوضه بالادست سد کرخه). پایان­نامه کارشناسی ارشد. دانشگاه آزاد اسلامی، واحد مهاباد.
  8. قهرودی تالی، م. 1381. ارزیابی درون یابی به روش کریجینگ. پژوهشهای جغرافیایی. 43 :95-108
  9. میثاقی، ف. ک، محمدی. 1385. پهنه بندی اطلاعات بارندگی با استفاده از روشهای آمار سنتی و زمین آمار و مقایسه با شبکه­های عصبی مصنوعی. مجله علمی کشاورزی. 29(4):1-14.
    1. Abebe, A.J., D.P, Solomatine and R.G.W. Venneker. 2000. Application of adaptive fuzzy rule-based models for reconstruction of missing precipitation events. Hydrol. Sci. J 45.425–436.
    2. Abghari, H., M, Mahdavi. A, Fakherifard, and A. Salajegheh, 2009. Cluster Analysis of Rainfall-Runoff training patterns to flow modeling using hybrid RBF networks. Asian J Appl. Sci. 2: 150-159.
    3. Abghari H, H. Ahmadi, S. Besharat, V. Verdinejad. 2012. Prediction of daily pan evaporation using wavelet neural networks. J Water Resour. Manage. 3639- 3652. DOI: 10.1007/s11269-012-0096-z.
    4. Anctil F, Perrin C, Andre´assian V. 2003. ANN output updating of lumped conceptual rainfall/runoff forecasting models. J Am. Water Resour. Assoc. 39:1269–1279.
    5. Chang, F.J., and Y.C. Chen. 2001. A counter propagation fuzzy-neural network modeling approach to real time stream flow prediction. J. Hydrol 245: 153–164.
    6. Chang, F.J., H.F. Hu, Y.C. Chen. 2001. Counter propagation fuzzy-neural network for stream flow reconstruction. Hydrol. Proc. 15. 219–232.
    7. Cheng, K, Sh. Lin, J.J. Liou. 2008. Rain-gauge network evaluation and augmentation using geostatistics. Hydrol. Proc. 22: 2554-2564.
    8. Cigizoglu, H.K. 2005. Application of the generalized regression neural networks to intermittent flow forecasting and estimation. J. Hydrol. Eng ASCE 10: 336–341.
    9. Cigizoglu, H. K., and O. Kisi. 2006. Methods to improve the neural network performance in suspended sediment estimation. J. Hydrol 317: 221–238.
    10. Clouse D.S., C.L, Giles., B.G, Horne, and G.W. Cottrell. 1997. Time delay neural networks: Representation and induction of finite state machines. IEEE Trans. Neural Net. 8:1065–1070.
    11. Coulibaly, P. and C.K. Baldwin. 2005. Non stationary hydrological time series forecasting using nonlinear dynamic methods. J. Hydrol. 307: 164–174.
    12. Coulibaly, P., F, Anctil. and B. Bobe´e. 1999. Hydrological forecasting using artificial neural network: the state of the art (in French). Canadian J Civ. Eng. 26:293–304.
    13. Coulibaly, P., F, Anctil, and B. Bobe´e. 2000. Daily reservoir in flow forecasting using artificial neural networks with stopped training approach. J. Hydrol. 230: 244–257.
    14. Coulibaly, P., F, Anctil. R, Aravena. and B. Bobee. 200.1a. Artificial neural network modeling of water table depth. Water Resour. Re. 37:885–896.
    15. Coulibaly, P., F, Anctil. And B. Bobee, 2001.b. Multivariate reservoir inflow forecasting using temporal neural networks. J. Hydrol. Eng. ASCE 6: 367–376.
    16. Coulibaly, P., Y.B, Dibike, and F. Anctil, 2005. Downscaling precipitation and temperature with temporal neural networks. J. Hydrometeor. 6:483–496.
    17. Coulibaly, P., and N.D. Evora, 2007. Comparison of neural network methods for infilling missing daily weather records. J. Hydrol. 341:27– 41
    18. Creutin, J.D., E, Andrieu.and D. Faure, 1997. Use of weather radar for the hydrology of a mountainous area. Part II: radar measurement validation. J. Hydrol. 193:26–44.
    19. Dibike, Y.B, and P. Coulibaly, 2006. Temporal neural networks for downscaling climate variability and extremes. Neural Net. 19:135–144.
    20. Diodato, N., and M. Ceccarelli, 2005. Interpolation processes using multivariate geostatistics for mapping of climatological precipitation mean in the Sannio Mountains (southern Italy). Earth Surface Proc. Landforms. 30: 259-268.
    21. Drogue,  G., J, Humbert, J, Deraisme. N, Mahr. and N. Freslon, 2002. A statistical topographic model using an omnidirectional parameterization of the relief for mapping orographic rainfall. Inter. J. Climate. 22: 599-613.
    22. Elman, J.L., 1990. Finding structure in time. Cogn, Sci. 14:179–211.
    23. Feldkamp L.A, and G.V., Puskorius, 1998. A signal processing framework based on dynamic neural networks with application to problems in adaptation. filtering and classification. Proc. IEEE 86: 2259–2277.
    24. Hecht-Nielsen, R. 1987. Counter propagation networks. Appl Opt. 26: 4979–4984.
    25. Hsu, K., H.V, Gupta, X, Gao, and S. Sorooshian, 1999. Estimation of physical variables from multichannel remotely sensed imagery using a neural network: application to rainfall estimation. Water Resour. Res. 35: 1605–1618.
    26. Igúzquiza, E. P. 1998. Comparison of geostatistical methods for estimating the areal average climatological rainfall mean using data on precipitation and topography. Int. J. Climate. 8: 1031– 1047.
    27. Khalil, M., U.S, Panu, and W.C. Lennox, 2001. Groups and neural networks based stream flow data infilling procedures. J. Hydrol. 241: 153–176.
    28. Luck, K.C., J.E, Ball, and A. Sharma. 2000. A study of optimal model lag and spatial inputs to artificial neural network for rainfall forecasting. J. Hydrol. 227:56–65.
    29. Maier, H.R, and G.C. Dandy, 2000. Neural network for the prediction and forecasting of water resources variables: A review of modeling issues and applications. Environ. Model. Softw. 15:101–124.
    30. Nie, J. 1989. A class of new fuzzy control algorithms. In: Proc IEEE Int. Confe Control and Appl. p. 896–897.
    31. Nie, J., and D.A. Linkens, 1994. Fast self-learning multivariable fuzzy controllers constructed from a CPN network. Int. J. Control 60: 369–393.
    32. Park, J., and I.W. Sandberg. 1991. Universal approximation using radial basis function networks. Neural Comput. 3:246–257.
    33. Pearlmutter, B.A. 1995. Gradient calculations for dynamic recurrent neural networks: a survey. IEEE Trans Neural Net. 6:1212–1228.
    34. Poggio, T., and F. Girosi, 1990. Networks for approximation and learning. Proc the IEEE 78:1481–1497.
    35. Principe, J.C., N.R, Euliano, and  W.C. Lefebvre, 2000. Neural and adaptive systems: fundamentals through simulations. John Wiley, New York.
    36. Prechelt, L. 1998. Automatic early stopping using cross-validation: Quantifying criteria. Neural Net. 6:1212–1228.
    37. Rumelhart, D.E., Zipser, D. 1985. Feature discovery by competitive learning. Cogn. Sci. 9:75–112.
    38. Rumelhart, D.E., G.E, Hinton, and R.J. Williams, 1986. Learning internal representation by error propagation. p. 318–362. In: Rumelhart D.E, and McClelland J.L. (Eds.), Parallel distributed Processing: explorations in the microstructure of cognition. vol. 1. MIT Press, Cambridge. MA.
    39. Sirca, G.F., and H. Adeli, 2004. Counter propagation neural network model for steel girder bridge structures. J. Bridge Engi. 9:55–65.
    40. Specht, D.F. 1991. A general regression neural network. IEEE Trans. Neural Net. 2:569–576.
    41. Toth, E., A, Brath, and A. Montanari, 2000. Comparison of short-term rainfall prediction models for real-time flood forecasting. J. Hydrol. 239:132–147.
    42. Wettschereck, D., T. Dietterich, 1992. Improving the performance of radial basis function networks by learning center locations. p. 1133–1140 In: Moody J.E, Hanson S.J, Lippmann R.P. (Eds.). Advances in neural information processing systems, Vol. 4. Morgan Kaufmann, San Mateo. CA.
    43. Williams, R.J, and J. Peng, 1990. An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural Comput. 2: 490–501.

Files

History

  • Receive Date: 29 February 2016
  • Accept Date: 29 February 2016

Share

How to cite

Statistics