Simulation of hydraulic head using Particle Swarm Optimization Algorithm and Genetic Algorithm. (Case study: Debal khazaie sugarcane plantation)

Document Type : Research Paper

Author

• atefeh sayadi shahraki

phd student

Abstract

Farm experiments are useful in knowing the drainage systems but they have considerable limitations including the inability to use them as prediction tools. Application of simulation models can cover these deficiencies but it is necessary to use the field data to evaluate the accuracy of the model. In this study, Particle Swarm Optimization Algorithm and Genetic Algorithm is used to predict hydraulic head. For this purpose, field R9-11 of the Debal Khazaei sugarcane plantation is selected and number piezometers were installed in different depth (2/2,3,4 and 5 meters from the ground) and distance from collector.Piezometers. hydraulic load changes, the volume of irrigation water and drainage flow were measured from September 2013 to November 2014 on a daily basis. The results showed that the Particle Swarm Optimization Algorithm has a highest accuracy in predicting hydraulic head. So that the average RMSE in different depths between measured and predicted with Particle Swarm Optimization Algorithm and Genetic Algorithm obtained 0.098 and 0.114 , respectively and the average coefficient R^2 in different depths for Particle Swarm Optimization Algorithm and Genetic Algorithm models obtained 0.991 and 0.94 respectively. The test results of the comparison between measured and simulated data show that, between any of the values predicted by the models, measured data were not significantly different.

Keywords

• Forecast
• Artificial neural network
• Drainage flow
• Particle Swarm Optimization
• hydraulic head

20.1001.1.20086377.1398.12.43.2.4

---

References

1)       Ahmadi, Z., Zekri,M., beyjami, A. 2015. Predict the depth of the groundwater table using particle swarm optimization. In: Proceedings of 10th International Congress of Civil Engineering,  5-7 May, Tabriz, Abstract. (in Persian).

2)       Emarati, M. R. 2014. Study of load and price forecasting methods in restructured electricity markets and offering new intelligence methods with more capabilities. MSc. Dissertation, University of Advanced Technology Faculty of Energy Department of Energy Management, Kerman. (in Persian).

3)       Goldberg, D.E. 1989. Genetic Algorithms in Search Optimization and Machine Learning. Addison-Wesley.

4)       Hamed,Y., Elkili,M. 2015.  Prediction of future groundwater level using artificial Neural Network, southernriyadh, ksa(CASE STUDY). International Water Technology Journal,. 5:149-162.

5)       Hsu, Sh., Hsieh, JJ.P.A., Chih, T.Ch. & Hsu, K.Ch. 2009. A two-stage architecture for stock price forecasting by integrating self-organizing map and support vector regression. Expert Systems with Applications, 36(4): 7947-7951.

6)       Mokhtaran, R. 2015. Dynamic study of freshwater and saltwater interface in irrigated lands of  sugarcane. Ph. D. dissertation, University of Chamran, Ahvaz. (in Persian).       

7)       Rahmani, Gh. R. 2012. Simulation of groundwater resources in Aghili’s plain using artificial neural networks method and comparison with finite differences mathematical model results. MSc. dissertation, University of Chamran, Ahvaz. (in Persian).

8)       Shiri, J., and Kisi, O. 2011. Comparison of genetic programming with neurofuzzy systems for predicting short-term water table depth fluctuations. Comput. Geosci. 37: 1692-1701.

9)       Traore, S., and Guven, A. 2012. Regional-specific numerical models of evapotranspiration using gene-expression programming interface in Sahel. Water Resour. Manag. 26: 4367-4380.

10)   Zamaniahmadmahmoodi, R., Akhondali, A. M. and Radmanesh, F. 2014. Estimation of the groundwate level by using a combined optimized method with Genetic Algorithms in Ramhormoz plain. Journal of Irrigation and Water Engineering, 4 (15):38-26. (in Persian).