Operation of irrigation canals using intelligent methods

Document Type : Original Article


1 Department of Water Engineering, Faculty of Agriculure, University of Zanjan, Zanjan, Iran

2 Department of Water Engineering, Faculty of Agriculure, Bu-Ali Sina University, Hamadan, Iran


Introduction: The rapid growth of population, agriculture, urban and industries has led to increasing water demand and competition for its consumptions. The promotion of agricultural water productivity has the main effect on improving water consumption. Water delivery and scheduling methods are important to increase the flexibility of irrigation systems. Among different available methods, the on-request water delivery has higher flexibility than the rotational one and doesn’t need the high cost of automatic systems. The appropriate adjustment of the structures and their operational instructions between successive requests is a function of discharge variation, time interval between operations, coincidence of different request, physical condition of canal and structures and hydrodynamic behavior of the flow, which is a complex task. To obtain the performance of the recently utilized method, i.e., FSL (Fuzzy SARSA Learning), it is necessary to compare it to a traditional method like Artificial Neural Network (ANN). In this research, data  from the east Aghili canal was trained for programming water delivery and distribution using MLP (Multi-Layer Perceptron) and RBF (Radial Basis Function) networks of  ANN with the on-request method. Finally, the results of the FSL and ANN models were compared.
Material and methods: In this research, the MLP (Multi-Layer Perceptron) and RBF (Radial Basis Function) networks of  ANN were used to determine the procedure for exploiting the operational instructions of the on-request method in the east Aghili canal, in Khuzestan Province, using its flow and gate opening data. In this research, 70%, 15%, and 15% of data were used to train, test, and validate the model, respectively. The correlation coefficient and root mean square error were used for determining the better method. Modeling of the canal was  done using the Irrigation Canal Conveyance System (ICSS) hydrodynamic model. To evaluate the MLP, RBF, and FSL outputs, maximum and average errors of water depth, adequacy, efficiency, equity, and dependability were used.
Results and discussion: The operational instructions were determined using the MLP  in March 2017 in the east Aghili canal, and were compared to the corresponding determined operational instructions using FSL. According to the obtained results, it  was observed that the MPA index in the  ANN method in the first and second block of this channel, respectively  were 0.952 and 0.919 and in the case of using the FSL method, these values  were equal to 0.996 and 1. Also, the MPF index in the simulation using the  ANN in both blocks  were equal to 1 and in the case of FSL, these values  were equal to 0.999 and 0.971. The maximum error of MAE of water level in the first and second block of the study, respectively  were equal to 9.2 and 3.8 % and in the case of using the FSL method, these  were equal to 5.5 and 7.4 %. The results showed that the MLP  was better than the RBF to determine the operational instructions. The MAE and IAE indicators were minimum, and the water delivery indicators were close to their desired values according to the Molden and Gates (1990) criteria. Aldo, it was revealed that the FSL  was better than the MLP, however, the MLP results  were valid and can be used in practice.
Conclusion: In this research, the ANN model was used for determining operational instructions using MATLAB. The training was done using the MLP and RBF using the east Aghili canal data. The ICSS was used for simulating the canal. The results showed that the MLP was better than RBF, and the FSL model was better than the MLP as well. However, both of them can be used in practice.


Arauz, T., Maestre, J.M., Tian, X. and Guan, G., 2020. Design of PI controllers for irrigation canals based on linear matrix inequalities. Water. 12(3), 855-860.
Arekhi, S. and Fathizadehh, H., 2014. Efficiency evaluation of four methods of artificial neural network to provide land use cover using images of ETM satellite. Geography and Development Iranian Journal. 37, 133-146. (In Persian with English abstract).
Clemmens, A.J., Kacerek, T.F., Grawitz, B. and Schuurmans, W., 1998. Test cases for canal control algorithms. Journal of Irrigation and Drainage Engineering. 124(1), 23-30.
Glorennec, P.Y. and Jouffe, L., 1997. Fuzzy Q-learning fuzzy systems. In proceedings 4th IEEE International Conference, 17th-18th June, Londen, England. P.20.
Haq, Z.U. and Anwar, A.A., 2010. Irrigation scheduling with genetic algorithms. Journal of Irrigation and Drainage Engineering. 136(10), 704-714.
Hassani, Y. and Hashemy, S.M., 2019. Agricultural water distribution under drought conditions based on economic priorities: Case study of Qazvin Irrigation District. Irrigation and Drainage. 68(3), 443-451.
Hykin, S., 1999. Neural networks: A comprehensive foundation. Printice-Hall, New Jersey.
Karbasi, M., 2017. Reconstruction of missing data of monthly total sunshine hours using artificial neural networks. Iranian Journal of Irrigation and Drainage. 10(5), 570–580. (In Persian with English abstract).
Karimizad, F. and Shahsavand, A., 2013. Comparing the results of MLP and RBF methods in predicting simultaneous phenomena of mass transfer and heat convection. Journal of Modeling in Engineering. 11(33), 27-43. (In Persian with English abstract).
Manz, D.H. and Schaalje, M., 1992. Development and application of the irrigation conveyance system simulation model. In CEMAGREF-IIMI Int. Workshop on the application of mathematical modeling for improvement of irrigation canal operation, CEMAGREF, Montpelier, France. P.210.
Molden, D.J. and Gates, T.K., 1990. Performance measures for evaluation of irrigation-water-delivery systems. Journal of irrigation and drainage engineering. 116(6), 804-823.
Savari, H., Monem, M.J. and Shahverdi, K., 2016. Comparing the performance of FSL and traditional operation methods for on-request water delivery in the Aghili network, Iran. Journal of Irrigation and Drainage Engineering. 142(11), 1-8.
Shahdany, S.H., Taghvaeian, S., Maestre, J. and Firoozfar, A., 2019. Developing a centralized automatic control system to increase flexibility of water delivery within predictable and unpredictable irrigation water demands. Computers and Electronics in Agriculture, 163, 1-13.
Shahrokhnia, M.A. and Ghiasi, A.O., 2018. Evaluation of water delivery performance in doroodzan irrigation network under Two different water requirements. Irrigation and Drainage Structures Engineering Research. 19(70), 127-142. (In Persian with English abstract).
Shahverdi, k., 2015. Development of on-request operation system for irrigation networks using reinforcement learning algorithm (Case Study: East Aghili Canal). Ph.D. Thesis, Tarbiat Modares University, Tehran. (In Persian with English abstract).
Shahverdi, K. and Monem, M.J., 2015. Application of reinforcement  learning algorithm for automation of canal structures, Irrigation and Drainage. 64, 77–84.
Shahverdi, K., Monem, M.J. and Nili, M., 2016a. Application of reinforcement learning algorithm for determining the operational instructions of the on-request method for optimal water distribution and delivery. Journal of Water and Soil. 46(2), 283-291. (In Persian with English abstract).
Shahverdi, K., Monem, M.J., and Nili, M., 2016b. Fuzzy SARSA learning of operational instructions to schedule water distribution and delivery. Journal of Irrigation and Drainage. 65, 276–284.
Valipoor, M., Heidarpoor, M. and Afrasiabykia, P., 2016. Determination of optimal water distribution policy in an irrigation network (Case Study: Droodzan Network). Applied Research of Water Sciences. 2 (2), 11-24. (In Persian with English abstract).