Comparison performance of two models DRAINMOD and Artificial Neural Network (ANN) for the forecast of water table

Subject Areas : Water and Environment

Atefeh Sayadi Shahraki ¹ ( Ph.D of Irrigation and drainage Shahid, Shahid Chamran University of Ahvaz, Ahvaz, Iran. *(Corresponding Author) )
Abd Ali Naseri ² ( Professor of Irrigation and Drainage Shahid, Shahid Chamran University of Ahvaz, Ahvaz, Iran. )
Amir Soltani Mohammadi ³ ( Associated Professor of Irrigation and Drainage, Shahid Chamran University of Ahvaz, Ahvaz, Iran. )

Received: 2016-06-27 Accepted : 2016-11-23 Published : 2019-03-21

Keywords: Piezometer, Khuzestan, Drainage, Simulation, Matlab, Model,

Abstract :

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, Artificial Neural Networks (ANN) and model DRAINMOD are used to predict water table. For this purpose, field R9-11 of the Debal Khazaei sugarcane plantation is selectedand Input parameters of the models, including fluctuations in water table, the volume of irrigation water, drainage flow, Climatic data, Soil physical properties and Drainage system parameters were measured from November 2013 to October 2014. The results have showed that the artificial neural network method has a highest accuracy in predicting water table. So that the average RMSE between measured and simulation with Artificial Neural Networks and DRAINMOD obtained 0.02 and 16.8 respectively.

References:

1. Skaggs, R.W. 1978. A water management model for shallow water table soils. Technical Report No. 134 of the Water Resources Research Institute of the University of North Carolina, North Carolina State University, Raleigh, NC.


2. Wahba, M., Christen, E., 2006. Modeling subsurface drainage for salt load management in southeastern Australia. Irrig Drain Syst, vol. 20, pp. 267-282.


3. Workman, S.R., Skaggs, R.W., 1989. Comparison of two drainage simulation models using field data. Trans. ASAE, vol. 32, pp. 1933-1938.


4. Ghadampour, Z., Rakhshandehroo Gh., 2010. Using artificial neural network to forecast groundwater depth in union country Well. World Academy of Science, Engineering and Technology.


5. Alipour, Z., Akhund Ali, A., Radmanesh, F., 2014. Comparison of three methods of ANN, ANFIS and Time Series Models to predict ground water level: (Case study: North Mahyar plain), Academy for Environment and Life Sciences, India, vol. 3, pp.128-134.


6. Ioannis N, D., Paulin, C., Ioannis K, T. 2005. Groundwater level and forecasting using artificial neural networks. Hydrology, vol. 309, pp. 229–240.


7. عمارتی م ر. 1393. بررسی روش‌های پیش بینی بار و قیمت در بازارهای تجدید ساختار شده برق و ارائه روش هوشمند ترکیبی جدید. دانشگاه تحصیلات تکمیلی و فناوری پیشرفته. کرمان. پایان نامه کارشناسی ارشد.
   
   
   1. Lallahem S, Mania J, Hani A., Najjar Y., 2005. On the use of neural networks to evaluate. groundwater levels in fracturedmedia. Hydrology, vol. 307, pp. 92–111.
   
   
   2. Coppola, E, Rana, AJ, Poulton, M., Szidarovszky, F., Uhi, VWو. 2005. Aneural networks model for predicting aquifer water level elevation. Ground Water, vol. 43, pp. 231-241.
   
   
   3. رحیمی قباق تپه م. 1379. ارزیابی مدل DRAINMOD و بررسی تاثیر منطقه غیر اشباع خاک بر نوسانات سطح ایستابی در شرایط نیمه خشک خوزستان. دانشگاه شهید چمران . اهواز. پایان نامه کارشناسی ارشد آبیاری و زهکشی.
   
   
   4. آذرنوش، م. 1383. مدلسازی تغییرات سطح ایستابی در خاک با استفاده از مدل DRAINMOD و شبکه عصبی مصنوعی مطالعه موردی: خوزستان. دانشگاه تربیت مدرس. تهران. پایان نامه کارشناسی ارشد آبیاری و زهکشی.