Forecasting of Evaporation from Hemren Reservoir by using Artificial Neural Network

SAAD SH. SAMMEN

doi:10.24237/djes.2013.06403

Authors

SAAD SH. SAMMEN Diyala University – College of Engineering

Keywords:

Artificial neural networks, Daily Evaporation, Hemren Reservoir

Abstract

The evaporation is one of the basic components of the hydrologic cycle and is essential for studies such as water balance, irrigation system design, and water resource management and it is requires knowledge of the values of many climatic variables. In order to estimate the evaporation, direct measurement methods or physical and empirical models can be used. Using direct methods require installing meteorological stations and instruments for measuring evaporation. Installing such instruments in various areas requires specific facilities and cost which is hard to be employed. Accordingly, this paper is an attempt to assess the potential and usefulness of ANN based modeling for evaporation prediction from Hemren reservoir by using daily temperature, relative humidity, wind velocity, sunshine hours, and evaporation data in Hemren meteorological station. Also, this study outlines a procedure to evaluate the effects of input variables on the output variable using the weight connections of ANN models.
The Lev. Marqn. Back Prog. (LMBP) has been utilized to construct the ANN models. For the development ANN model, different networks with different numbers of neurons and layers were evaluated. Mean Squared Error (MSE) and the Correlation Coefficient (R2) were employed to evaluate the accuracy of the proposed model. The study shows that the best model for estimation of evaporation is ANN (4-10-1), it have MSE equal to 0.112711 and the correlation coefficient (R2) equal to 0.999540.

Downloads

Download data is not yet available.

References

- Altendorf, C.T., Elliott, R. C., Stevens, E. W. and Stone,V M. L., (1999), “Development and validation of a neural network model for soil water content prediction with comparison to regression techniques”,Trans., ASAE, vol. 42, no.3, pp691-699,. DOI: https://doi.org/10.13031/2013.13230

- Box GEP, Jenkins G.M., (1976), “Time Series Analysis: Forecasting and Control”, Holden Day Inc.: San Francisco, USA.

- Cybenko G., (1989) “Approximation by superpositions of a sigmoidal function”, Math. Ctrl. Signals Syst. (MCSS), 2: 303–314. DOI: https://doi.org/10.1007/BF02551274

- Coulibaly P, Anctil F. Bobée B. (1999). “Prévision hydrologique parréseaux de neurones artificiels: état de l'art”, Can. J. Civ. Eng., 26(3): 293-304. DOI: https://doi.org/10.1139/l98-069

- Coulibaly, P., Anctil, F., Aravena, R., Bobee, B., (2001), “Artiﬁcial neural network modeling of water table depth ﬂuctuations”, Water Resources Research 37: 885–896. DOI: https://doi.org/10.1029/2000WR900368

- Cobaner, M., Information, C., Haktanir, T., Kisi, O., (2008), “Prediction of Hydropower Energy Using ANN for the Feasibility of Hydropower Plant Installation to an Existing Irrigation Dam”, Water Resour. Manage., 22: 757-774. DOI: https://doi.org/10.1007/s11269-007-9190-z

- Hornik, K., Stinchcombe, M., White, H., (1989), “Multilayer feed forward networks are universal approximators. Neural Netw”, 2: 359-366. DOI: https://doi.org/10.1016/0893-6080(89)90020-8

- Gallant, S.T., (1993), “Neural Network learning and Expert systems”, Cambridge, Mass : MIT press. DOI: https://doi.org/10.7551/mitpress/4931.001.0001

- Jain, S. K., Nayak, P.C., and Sudheer, K.P., (2008), “Models for estimating evapotranspiration using artiﬁcial neural networks, and their physical interpretation”, Hydological Processes, 22 : 2225 – 2234. DOI: https://doi.org/10.1002/hyp.6819

- Legates, D.R. and McCabe, G.J., (1999), “Evaluating the use of goodness-of-fit measures in hydrologic and hydro-climatic model validation”, Water Resources Research, 35 (1): 233-241. DOI: https://doi.org/10.1029/1998WR900018

- Mcculloch, W. S., and Pitts, W., (1943), “A Logical Calculus of the Ideas Immanent in Nervous Activity”, Bulletin of Mathematical Biophysics 5: pp.115-133. DOI: https://doi.org/10.1007/BF02478259

- Ministry of Water Resources, General Directorate of Dams and Reservoirs, Hemren Dam Project Management.

- Nash, J.E, and Sutcliffe, J.V., (1970), “River ﬂow forecasting through conceptual models: 1. A discussion of principles”, Journal of Hydrology 10: pp.282–290. DOI: https://doi.org/10.1016/0022-1694(70)90255-6

- Schaap, M.G. and Leij, F.J., (1998), “Database related accuracy and uncertainty of pedotransfer functions”, Soil Science, 163: 765-779. DOI: https://doi.org/10.1097/00010694-199810000-00001

- Singh, V. P. and Xu, C. Y., (1997), “Evaluation and generalization of 13 mass transfer equations for determining free water evaporation,” Hydrological Processes, vol. 11, pp. 311-323. DOI: https://doi.org/10.1002/(SICI)1099-1085(19970315)11:3<311::AID-HYP446>3.0.CO;2-Y

- Vongkunghae, A., Chumthong, A., (2007), “The performance comparisons of backpropagation algorithm's family on a set of logical functions”, Trans. Electrical Eng., Electron. Commun., 5: 114-118.