Exploiting Two Intelligent Models to Predict Water Level: A Field Study of Urmia Lake, Iran

Authors: Shahab Kavehkar, Mohammad Ali Ghorbani, Valeriy Khokhlov, Afshin Ashrafzadeh, Sabereh Darbandi

Abstract:

Water level forecasting using records of past time series is of importance in water resources engineering and management. For example, water level affects groundwater tables in low-lying coastal areas, as well as hydrological regimes of some coastal rivers. Then, a reliable prediction of sea-level variations is required in coastal engineering and hydrologic studies. During the past two decades, the approaches based on the Genetic Programming (GP) and Artificial Neural Networks (ANN) were developed. In the present study, the GP is used to forecast daily water level variations for a set of time intervals using observed water levels. The measurements from a single tide gauge at Urmia Lake, Northwest Iran, were used to train and validate the GP approach for the period from January 1997 to July 2008. Statistics, the root mean square error and correlation coefficient, are used to verify model by comparing with a corresponding outputs from Artificial Neural Network model. The results show that both these artificial intelligence methodologies are satisfactory and can be considered as alternatives to the conventional harmonic analysis.

Keywords: Water-Level variation, forecasting, artificial neural networks, genetic programming, comparative analysis.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1084754

References:

[1] Alvisi, S., Mascellani,G., Franchini, M., Bardossy,A. Water level forecasting through fuzzy logic and artificial neural network approaches. Hydrology and Earth System Science (2006), 10(1), 1-17.
[2] Aytek, A., Alp, M. An application of artificial intelligence for rainfall runoff modeling. Journal of Earth System Science (2008), 117(2),145- 155.
[3] Aytek, A., Kisi, O. A genetic programming approach to suspended sediment modeling. Journal of Hydrology (2008), 351, 288-298.
[4] Babovic, V., Keijzer, M. Rainfall runoff modeling based on genetic programming . Nordic Hydrology (2002), 33, 331-343.
[5] Banzhaf W, Nordin P, Keller PE, Francone FD. Genetic Programming, Morgan Kaufmann, San Francisco, CA (1998).
[6] Bhattacharya, B., Solomatine, D.P. Neural networks and M5 model trees in modeling water level-discharge relationship. Neurocomputing (2005), 63, 381-396.
[7] Borelli A, De Falco I, Della CA, Nicodemi M, Trautteur G. Performance of genetic programming to extract the trend in noisy data series. Physica A (2006), 370: 104-108.
[8] Chang H-K and Lin L-C. Multi-point tidal prediction using artificial neural network with tide-generating forces, Coastal Engineering (2006), 53, P.P. 857864.
[9] Coulibaly, P., Anctil, F., Aravena, R., Bobee, B. Artificial neural network modeling of water table depth fluctuation. Water Resources Researches (2001), 37(4), 885-896.
[10] Gaur S, Deo MC. Real-time wave forecasting using genetic programming. Ocean Engineering (2008), 35(11-12):1166-1172.
[11] Ghorbani MA, Khatibi R, Aytek A, Makarynskyy O, Shiri J. Sea Water Level Forecasting Using Genetic Programming and Comparing the Performance with Artificial Neural Networks. Computers & Geosciences (2010), 36:620627.
[12] Giustolisi, O. Using GP to determine Chezzy resistance coefficient in corrugated channels. Journal of Hydroinformatics (2004), 157-173.
[13] Goldberg DE. Genetic algorithms in search, optimization, and machine learning. Addison Wesley, Reading, Mass (1989).
[14] Hornik, K. Some new results on neural network approximation. Neural Networks (1993), 6, 1069-1072.
[15] Haykin, S. Neural networks: a comprehensive foundation, Prentic-Hall, Upper saddle river, New Jersey (1999), 842 PP.
[16] Khatibi, R. Barriers inherent in Flood Forecasting and their Treatments, Chapter 29 of the book: River Basin Management for Flood Risk Mitigation, Ed. D.W. Knight and A.Y. Shamseldin (2006).
[17] Khu, S.T., Liong, S.Y., Babovic, V., Madsen, H., Muttil, N. Genetic programming and its application in real- time runoff forming. Journal of American Water Resources Association (2001), 37(2), 439-451.
[18] Koza JR. Genetic Programming: On the programming of computers by means of Natural Selection. Cambridge, MA: The MIT Press (1992).
[19] Liong, S.Y., Gautam, T.R., Khu, S.T., Babovic, V., Keijzer,M., Muttil, N. Genetic programming: A new paradigm in rainfall runoff modeling. Journal of AmericanWater Resources Association (2002), 38(3), 705-718.
[20] Livinia V, Ashkenazy Y, kinzer Z, Stryging V, Bunde A, HAvlin S. A stochastic model of river discharge fluctuation. Physica A (2003), 330:283-290.
[21] Makarynskyy O, Makarynska D, Kuhn M, Featherstone WE. Predicting sea level variations with artificial neural networks at Hillary Harbour, Western Australia. Estuarine, Coastal and Shelf Science (2004), 61: 351- 360.
[22] Muttil, N., Liong, S.Y. Improving runoff forecasting by input variable selection in GP. In: Proceedings of world water congres, ASCE (2001).
[23] Rahmstorf, S. A semi empirical approach to projecting future sea level rise. Science (2007), 315 (5810), 368-370.
[24] Sheta, A.F., Mahmoud, A. Forecasting using genetic programming. Proceedings the 33-rd southeastern symposium on system theory (2001), 343-347.
[25] Ustoorikar K, Deo MC. Filling up gaps in wave data with genetic programming. Marine Structures (2008), 21: 177-195.
[26] Zaldivar, J.M., Strozzi, F., Gutierrez, E., Shepherd, I.M. Early detection of high water at Venice Lagoon using chaos theory techniques. European report 17317. ISPRA: E.C (1998).