نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکترا، گروه مهندسی عمران، دانشکده فنی‌مهندسی، واحد اراک، دانشگاه آزاد اسلامی، اراک، ایران

2 دانشیار، گروه مهندسی آب، دانشکده کشاورزی، واحد اراک، دانشگاه آزاد اسلامی، اراک، ایران

3 استادیار، گروه مهندسی آب، دانشکده کشاورزی، واحد مهاباد، دانشگاه آزاد اسلامی، مهاباد، ایران

4 استادیار، گروه مهندسی عمران، دانشکده فنی‌مهندسی، واحد اراک، دانشگاه آزاد اسلامی، اراک، ایران.

چکیده

امروزه مدل‌های یادگیری ماشین با تکیه بر استخراج الگوی بین داده‌ها قادر به ‌پیش‌بینی مناسب سری‌های زمانی هستند. در این پژوهش از شبکه عصبی- فازی (ANFIS) برای پیش‌بینی جریان ورودی به مخزن سد مهاباد در شمال غرب ایران استفاده گردید. همچنین از الگوریتم بهینه‌سازی جدید شکار شاهین هریس (HHO) برای بهبود ساختار ANFIS بهره برده شد. از داده‌های هواشناسی مانند بارش ماهانه، دمای ماهانه و جریان ورودی به مخزن یک تا سه ماه قبل به‌عنوان پارامترهای ورودی و در 6 الگوی مختلف ورودی استفاده شد. حدود 70% داده‌ها برای آموزش مدل‌ها و 30% برای آزمون آن‌ها در نظر گرفته شد. نتایج نشان داد که مدل ANFIS از دقت خوبی در داده‌های آموزش برخوردار است اما برای داده‌های آزمون از دقت آن بسیار کاسته می‌شود. توسعه مدل HHO-ANFIS موجب بهبود دقت پیش‌بینی شد. در بین الگوهای ورودی، الگویی که شامل تمام پارامترهای ورودی بود (P6) دارای بیش­ترین دقت پیش‌بینی بود. در این الگو مقادیر جذر میانگین مربعات خطا (RMSE)، میانگین خطای مطلق (MAE) به همراه ضریب ناش ساتکلیف (NSE) برای داده‌های آزمون به ترتیب برابر MCM 9/3، MCM 41/2 و 86/0 بود. با توجه به عملکرد خوب مدل مورداستفاده، می‌توان آن را برای پیش‌بینی سری‌های زمانی توصیه کرد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Development of Hybrid Adaptive Neuro Fuzzy Inference System - Harris Hawks Optimizer (ANFIS-HHO) for Inlet Flow to Dam Reservoir Prediction

نویسندگان [English]

  • Seyed Mohammad Enayati 1
  • Mohsen Najarchi 2
  • Osman Mohammadpour 3
  • Seyed Mohammad Mirhosseini 4

1 PhD Scholar, Department of Civil Engineering, Faculty of Engineering, Arak Branch, Islamic Azad University, Arak, Iran

2 Assoc. Professor, Department of Water Engineering, Faculty of Agriculture, Arak Branch, Islamic Azad University, Arak, Iran

3 Assist. Professor, Department of Water Engineering, Faculty of Agriculture, Mahabad Branch, Islamic Azad University, Mahabad, Iran

4 Assist. Professor, Department of Civil Engineering, Faculty of Engineering, Arak Branch, Islamic Azad University, Arak, Iran

چکیده [English]

Nowadays, machine learning models are able to make good predictions based on pattern extraction between data. In this study, a neural-fuzzy network (ANFIS) was used to predict the inflow to the reservoirs of a dam namely, the Mahabad dam located in the northwestern part of Iran. A new Harris Hawk (HHO) optimization algorithm was also used to improve the ANFIS (HHO-ANFIS) structure. Monthly precipitation and temperature and inlet flow data to the reservoir one to three months ago were used as input parameters as 6 different input patterns. About 70% of the data was used for training and 30% to test the models. The results showed that the ANFIS model has good accuracy in training data although, for test data, its accuracy was greatly reduced. The development of the HHO-ANFIS model improved the accuracy of the prediction. The patterns with all input parameters had the highest prediction accuracy. In this pattern, values ​​of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Nash Sutcliffe Efficiency coefficient (NSE) for test data were 3.9 MCM, 2.41 MCM, and 0.86, respectively. Due to the good performance of the model used, it can be recommended for time series predictions.

کلیدواژه‌ها [English]

  • Evolutionary Algorithms
  • Rainfall-Runoff
  • Predicting Time Series
  • Mahabad Dam
  • Machine learning
Abbasi, M., Araghinejad, S. and Ebrahimi, K. (2019). Evaluation of Moving Average Pre-processing Approach to Improve the Efficiency of Support Vector Regression Model for Inflow Prediction. Iran. J. Soil Water Res., 50(1), 247-258. [In Persian] DOI: 10.22059/ijswr.2018.250803.667838
Arya Azar, N., Ghordoyee Milan, S., and Kayhomayoon, Z. (2021a). Predicting monthly evaporation from dam reservoirs using LS-SVR and ANFIS optimized by Harris hawks optimization algorithm. Environ. Monit. Assess., 193(11), 1-14. DOI: 10.1007/s10661-021-09495-z
Arya Azar, N., Kardan, N., and Ghordoyee Milan, S. (2021b). Developing the artificial neural network–evolutionary algorithms hybrid models (ANN–EA) to predict the daily evaporation from dam reservoirs. Eng. Comput., 1-19. DOI: 10.1007/s00366-021-01523-3
Awchi, T. A. (2014). River discharges forecasting in Northern Iraq using different ANN techniques. Water Resour. Manag., 28 (3), 801–814. DOI: 10.1007/s11269-014-0516-3
Azar, N. A., Milan, S. G. and Kayhomayoon, Z. (2021). The prediction of longitudinal dispersion coefficient in natural streams using LS-SVM and ANFIS optimized by Harris hawk optimization algorithm.­ J. Contam. Hydrol., 240, 103781. DOI: 10.1016/j.jconhyd.2021.103781
Chu, H. J. and  Chang, L. C. (2009). Application of optimal control and fuzzy theory for dynamic groundwater remediation design. Water Resour. Manag., 23(4), 647– 660. DOI: 10.1007/s11269-008-9293-1
Di, C., Yang, X., and Wang, X. (2014). A four-stage hybrid model for hydrological time series forecasting. PLoS ONE 9 (8), e104663. DOI: 10.1371/journal.pone.0104663
Ghordoyee Milan, S., Bahmani, S., Salimi, H., and Gorbani, M. A. (2021). Development of a hybrid adaptive neuro fuzzy inference system-harris hawks optimizer (ANFIS-HHO) model to predict soil cation exchange capacity. Environ. Water Eng., 7(2), 304-317. [In Persian] DOI: 10.22034/jewe.2021.254271.1447
Ghordoyee Milan, S., Roozbahani, A., Banihabib, M. E., and Javadi, S. (2018). Developing fuzzy optimization model for conjunctive use of surface and ground water, case study: Astaneh-Koch Esfahan Plain. Iran. J. Ecohydrol., 5(3), 891-905. [In Persian] DOI: 10.22059/ije.2018.250098.807
He, Z., Wen, X., Liu, H. and Du, J. (2014). A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semi arid mountain region. J. Hydrol., 509, 379-386. DOI: 10.1016/j.jhydrol.2013.11.054
Heidari, A. A., Mirjalili, S., Faris, H., Aljarah, I., Mafarja, M. and Chen, H. (2019). Harris hawks optimization: Algorithm and applications. Fut. Generat. Comput. Syst., 97, 849-872. DOI: 10.1016/j.future.2019.02.028
Jang, J. S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans. Syst. Man. Cybernet., 23(3), 665-685. DOI: 10.1109/21.256541
Kayhomayoon, Z., Azar, N. A., Milan, S. G., Moghaddam, H. K. and Berndtsson, R. (2021a). Novel approach for predicting groundwater storage loss using machine learning. J. Environ. Manag., 296, 113237. DOI: 10.1016/j.jenvman.2021.113237
Kayhomayoon, Z., Ghordoyee Milan, S., Arya Azar, N. and Kardan Moghaddam, H. (2021b). A new approach for regional groundwater level simulation: clustering, simulation, and optimization. Nat. Resour. Res., 30(6), 4165-4185. DOI: 10.1007/s11053-021-09913-6
Mahmoudi, N., Majidi, A., Jamei, M., Jalali, M., Maroufpoor, S., Shiri, J. and Yaseen, Z. M. (2022). Mutating fuzzy logic model with various rigorous meta-heuristic algorithms for soil moisture content estimation. Agri. Water Manag., 261, 107342. DOI: 10.1016/j.agwat.2021.107342
Milan, S. G., Roozbahani, A. and Banihabib, M. E. (2018). Fuzzy optimization model and fuzzy inference system for conjunctive use of surface and groundwater resources. J. Hydrol., 566, 421-434 DOI: 10.1016/j.jhydrol.2018.08.078
Milan, S. G., Roozbahani, A., Azar, N. A. and Javadi, S. (2021). Development of adaptive neuro fuzzy inference system–Evolutionary algorithms hybrid models (ANFIS-EA) for prediction of optimal groundwater exploitation. J. Hydrol., 598, 126258. DOI: 10.1016/j.jhydrol.2021.126258
Misaghi, F. (2016). Forecasting of the alavian dam inflow water using optimized adaptive neuro-fuzzy inference system (Oanfis). Iran. J. Soil Water Res., 47(3), 439–448 [In Persian]. DOI: 10.22059/IJSWR.2016.59314
Moazami, S., Noori, R., Vesali Naseh, M. and Akbarzadeh, A. (2020). Proper orthogonal decomposition performance to determine the inputs to the artificial neural network for prediction of inflow into Alavian Dam. J. Environ. Sci. Technol., 22(7), 375-387. DOI: 10.22034/jest.2019.21920.3101
Moghaddam, H. K., Milan, S. G., Kayhomayoon, Z. and Azar, N. A. (2021). The prediction of aquifer groundwater level based on spatial clustering approach using machine learning. Environ. Monit. Assess., 193(4), 1-20. DOI: 10.1007/s10661-021-08961-y
Nikolos, I. K., M. Stergiadi, M. P. Papadopoulou, and G. P. Karatzas (2008), Artificial neural networks as an alternative approach to groundwater numerical modelling and environmental design. Hydrol. Proces., 22(17), 3337– 3348. DOI: 10.1002/hyp.6916
Noorbeh, P., Roozbahani, A., Kardan Moghaddam, H. (2018). Prediction of Zayandeh Rood Dam inflow and hydrological wet and dry periods using Bayesian networks. Water Soil, 32(3), 633-646. [In Persian] DOI: 10.22067/jsw.v32i3.72084
Panahi, M., Khosravi, K., Ahmad, S., Panahi, S., Heddam, S., Melesse, A. M., and Lee, C. W. (2021). Cumulative infiltration and infiltration rate prediction using optimized deep learning algorithms: A study in Western Iran. J. Hydrol: Region. Stud., 35, 100825. DOI: 10.1016/j.ejrh.2021.100825
Peueot, C., Cappelaere, B., Vieux, B.E., Seguis, L. and Maia, A., (2003). Hydrologic process simulation of a semiarid, endorheic catchment in Sahelian West Niger. 1. Modelaided data analysis and screening. J. Hydrol., 279, 224–243. DOI: 10.1016/S0022-1694(03)00181-1
Riahi-Madvar, H., Dehghani, M., Memarzadeh, R., & Gharabaghi, B. (2021). Short to long-term forecasting of river flows by heuristic optimization algorithms hybridized with ANFIS. Water Resour. Manag., 35(4), 1149-1166. DOI: 10.1007/s11269-020-02756-5
Shafaei, M. and Kisi, O. (2017). Predicting river daily flow using wavelet-artificial neural networks based on regression analyses in comparison with artificial neural networks and support vector machine models. Neur. Comput. Appl., 28(1), 15-28. DOI: 10.1007/s00521-016-2293-9
Shahkarami, N., Sanikhani, H.and Moradi, M. (2016). Forecasting of Inflow to Kamal Saleh Reservoir using Soft Computing. Irrig. Water Eng., 6(2), 48-61 [In Persian]. DOI: 10.22059/IWE.2016.47322
Zhang, H., Singh, V.P., Wang, B., and Yu, Y., (2016). CEREF: A hybrid data-driven model for forecasting annual streamflow from a socio-hydrological system. J. Hydrol., 540, 246-256. DOI: 10.1016/j.jhydrol.2016.06.029