کاربرد مدل ترکیبی شبکه عصبی مصنوعی و الگوریتم‌های بهینه‌سازی فرا ابتکاری در پیش‌بینی شاخص خشکسالی SPEI12

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری، گروه علوم و مهندسی آب، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.

2 دانشیار، گروه مهندسی آب، دانشگاه زنجان، زنجان، ایران.

3 دانشیار، گروه مهندسی عمران، واحد شهر قدس، دانشگاه آزاد اسلامی، تهران، ایران.

4 استادیار، گروه علوم و مهندسی آب، واحد علوم و تحقیقات، دانشگاه آزاد اسلامی، تهران، ایران.

چکیده

خشکسالی یکی از مهم‌ترین بلایای طبیعی می‌باشد که در همه‌ی رژیم‌های آب و هوایی رخ می‌دهد. بنابراین، پیش‌بینی و مقابله با آن از اهمیت بالایی برخوردار است. در پژوهش حاضر از سه الگوریتم‌های بهینه‌سازی هوشمند (الگوریتم بهینه‌سازی مبتنی بر آموزش و یادگیری (TLBO)، الگوریتم بهینه‌سازی علف‌های هرز (IWO)، الگوریتم ازدحام ذرات (PSO)) و الگوریتم متداول لونبرگ- مارکوات به‌منظور آموزش شبکه عصبی مصنوعی چند لایه، برای پیش‌بینی شاخص خشکسالی SPEI12 یک الی سه ماه آینده در 79 ایستگاه سینوپتیک کشور استفاده گردید. با توجه به تعداد زیاد ایستگاه‌های سینوپتیک، ایستگاه‌ها با توجه به سری‌های زمانی خشکسالی و با استفاده از روش K-means به پنج خوشه C1 تا C5 تقسیم شدند. نتایج با توجه به قرارگیری ایستگاه‌ها در خوشه‌ها مورد مقایسه قرار گرفتند و دقت مدل‌ها بر اساس آماره‌های RMSE) و (R2 داده‌های آزمون، مورد ارزیابی قرار گرفتند. نتایج به‌دست ‌آمده از این پژوهش نشان داد که در هر سه مدل پیش‌بینی با افزایش مقیاس زمانی پیش‌بینی دقت مدل‌ها کاهش یافته است. مقایسه بین سه الگوریتم بهینه‌سازی ذکر شده و الگوریتم لونبرگ- مارکوات به‌عنوان یک الگوریتم پرکاربرد در بهینه‌سازی وزن‌های شبکه عصبی، نشان‌دهنده برتری قابل توجه الگوریتم‌های بهینه‌سازی فراابتکاری است. مقایسه بین سه الگوریتم TLBO،IWO و PSO نشان داد که الگوریتم TLBO اندکی بهتر از سایر الگوریتم‌ها عمل می‌کند و نتایج دقیق‌تری را ارائه می‌کند. بهترین پیش‌بینی مدل‌های ذکر شده و بیشترین مقادیر R2 در خوشه یک (شرق، نوار جنوب و جنوب شرقی ایران) و بیشترین مقادیر RMSE و کمترین دقت مدل‌ها در خوشه پنج (نوار شمالی کشور) مشاهده شد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Application of Combined Artificial Neural Network Model and meta-heuristic Optimization Algorithms in Predicting SPEI12 Drought Index

نویسندگان [English]

  • Porya Ghasemi 1
  • Masoud Karbasi 2
  • Alireza Zamani Nouri 3
  • Mahdi Sarai Tabrizi 4
1 Ph.D. Candidate, Department of Water Engineering and Sciences, Science and Research Branch, Islamic Azad University, Tehran, Iran
2 Associate Professor, Water Engineering Department, University of Zanjan. Zanjan, Iran
3 Associate Professor, Department of Civil Engineering, Shahr-e-Qods Branch, Islamic Azad University, Tehran, Iran.
4 Assistant Professor, Department of Water Engineering and Sciences, Science and Research Branch, Islamic Azad University, Tehran, Iran.
چکیده [English]

Drought is one of the most important and damaging natural disasters in the field of water resources that occurs in all climatic regimes of the country. Therefore, predicting and dealing with it is very important. In the present study, 79 synoptic stations in Iran were selected as the study. Three meta-heuristic optimization algorithms TLBO, IWO, PSO and the conventional Levenberg-Marquadt algorithm were used to train the multilayer artificial neural network to predict the SPEI12 drought index for the next one to three months. Due to the large number of synoptic stations, the stations were divided into five clusters C1 to C5 according to the time series of the drought using the K-means method. The results were compared with respect to the location of the stations in the clusters and the accuracy of the models was evaluated based on the RMSE and R2 indices of the test data. Showed that in all three prediction models, the accuracy of the models decreased with increasing prediction time. Comparison between the three optimization algorithms mentioned and Levenberg-Marquadt algorithm as a widely used algorithm in optimizing neural network weights, showed the better performance of meta-heuristic algorithms. The comparison between the three TLBO, IWO and PSO algorithms showed that the TLBO algorithm performed slightly better than the other algorithms and provided more accurate results. R2 was observed in cluster one (eastern regions, southern strip and southeastern regions of Iran) and the highest RMSE values and the lowest accuracy of the models were observed in cluster five (northern strip strip of the country).

کلیدواژه‌ها [English]

  • Drought
  • Intelligence Optimization Algorithms
  • Machine learning
  • Standardized Precipitation Evapotranspiration Index
  1. 1. Abramowitz, M., & Stegun, I. (1965). Handbook of mathematical functions: with formulas, graphs, and mathematical tables, (9th ed.). New York. NY: Dover Publications.

    1. Aghelpour, P., Bahrami-Pichaghchi, H., & Varshavian, V. (2021). Hydrological drought forecasting using multi-scalar streamflow drought index, stochastic models & machine learning approaches, in northern Iran. Stochastic Environmental Research and Risk Assessment,1-21.
    2. Aghelpour, P., Bahrami-Pichaghchi, H., & Kisi, O. (2020). Comparison of three different bio-inspired algorithms to improve ability of neuro fuzzy approach in prediction of agricultural drought, based on three different indexes. Computers and Electronics in Agriculture, 170(3), 1-12.
    3. Alizadeh, M. J., Shabani, A., & Kavianpour, M. R. (2017). Predicting longitudinal dispersion coefficient using ANN with metaheuristic training algorithms. International Journal of Environmental Science and Technology,14(11), 2399-2410.
    4. Beguería, S., Vicente‐Serrano, S. M., Reig, F., & Latorre, B. (2014). Standardized precipitation evapotranspiration index (SPEI) revisited. parameter fitting, evapotranspiration models, tools, datasets and drought monitoring. International Journal of Climatology. 34(10), 3001-3023.
    5. Caliński, T., & Harabasz, J. (1974) A dendrite method for cluster analysis. Communications in Statistics-theory and Methods. 3(1), 1-27.
    6. Chen, X., Chau, K. & Busari, A. (2015). A comparative study of population based optimization algorithms for downstream river flow forecasting by a hybrid neural network model. Engineering Applications of Artificial Intelligence, 46(2), 258-268.
    7. Cheng, C.T., Wang W.C., Xu D.M., & Chau, K. (2008). Optimizing hydropower reservoir operation using hybrid genetic algorithm and chaos. Water Resources Management, 22(7), 895-909.
    8. Cheraghalizadeh, M., Nazi-Ghameshloo, A., & Bazrafshan, J. (2018). Integrated monitoring of hydro–meteorological droughts in kasilian's basin (Mazandaran Province). Journal of the Earth and Space Physics. 44(2), 463-477. (In Persian)
    9. Dang, N. M., Anh, D. T., & Dang, T. D. (2019). ANN optimized by PSO and Firefly algorithms for predicting scour depths around bridge piers. Engineering with Computers, 37, 293-303.
    10. Davarpanah, G., (2002). The investigation of the most important economic and drought and government assistance methods in reducing these effects. Firist National Confrence on Water Crisis. 9 March, Zabol University, Zabol, Iran,1-23. (In Persian).
    11. Droogers, P., & Allen, R. G. (2002). Estimating reference evapotranspiration under inaccurate data conditions. Irrigation and Drainage Systems, 16(1), 33-45.
    12. Dugenci, M., Aydemir, A., Esen, I., & Aydın, M.E. (2015). Creep modelling of polypropylenes using artificial neural networks trained with Bee algorithms. Engineering Applications of Artificial Intelligence, 45, 71-79.
    13. Edwards, D. C., & McKee, T. B. (1997). Characteristics of 20th century drought in the United States at multiple time scales. Atmospheric Science Paper, 634, 1-30.
    14. Eroğluer, T. A., & Apaydin, H. (2020). Estimation of drought by streamflow drought index (sdi) and artificial neural networks (anns) in ankara-nallihan region. Turkish Journal of Agriculture-Food Science and Technology, 8(2), 348-357.
    15. Farris, J. S. (1969). On the cophenetic correlation coefficient. Systematic Zoology, 18(3), 279-285.
    16. Feng, P., Wang, B., Li Liu, D., & Yu, Q. (2019). Machine learning-based integration of remotely-sensed drought factors can improve the estimation of agricultural drought in South-Eastern Australia. Agricultural Systems, 173, 303-316.
    17. Gao, W., Karbasi, M., Derakhsh, A. M., & Jalili, A. (2019). Development of a novel soft-computing framework for the simulation aims. a case study. Engineering with Computers, 35(1), 315-322.
    18. Ghamghami, M., & Bazrafshan, J. (2012). Prediction of meteorological drought conditions in Iran using Markov chain model. Journal of Soil and Water Resources Conservation, 1(3), 1-12. (In Persian)
    19. Govindaraju, R. S. (2013). Special issue on data-driven approaches to droughts. Journal of Hydrologic Engineering. 18, 735-736.
    20. Hartigan, J. A. (1975). Clustering algorithms, New York: John Wiley & Sons, Inc.
    21. Hosseini-Moghari, S. M., & Araghinejad, S. (2015). Monthly and seasonal drought forecasting using statistical neural networks. Environmental Earth Sciences, 74(1), 397-412.
    22. Kayarvizhy, N., Kanmani, S., & Uthariaraj, R. (2013). Improving fault prediction using ANN-PSO in object oriented systems. International Journal of Computer Applications,73, 18-25.
    23. Kennedy, J., & Eberhart, R.C. (1995). Particle swarm optimization. In Proceedings of the 1995 IEEE International Conference on Neural Networks. Perth. Australia. IEEE Service Center. Piscataway, 4, 1942-1948.
    24. Keyantash, J. A., & Dracup, J. A. (2004). An aggregate drought index. Assessing drought severity based on fluctuations in the hydrologic cycle and surface water storage. Water Resources Research, 40(9), 1-13.
    25. Kisi, O., Gorgij, A. D., Zounemat-Kermani, M., Mahdavi-Meymand, A., & Kim, S. (2019). Drought forecasting using novel heuristic methods in a semi-arid environment. Journal of Hydrology, 578(11). 1-11.
    26. Komasi, M., Sharghi, S., & Safavi, H. R. (2018). Wavelet & cuckoo search-support vector machine conjugation for drought forecasting using Standardized Precipitation Index (case study: Urmia Lake, Iran). Journal of Hydroinformatics, 20(4), 975-988
    27. Kousari, M. R., Hosseini, M. E., Ahani, H., & Hakimelahi, H. (2017). Introducing an operational method to forecast long-term regional drought based on the application of artificial intelligence capabilities. Theoretical and applied climatology, 127(1-2), 361-380.
    28. Mehdizadeh, S., Ahmadi, F., Mehr, A. D., & Safari, M. J. S. (2020). Drought modeling using classic time series and hybrid wavelet-gene expression programming models. Journal of Hydrology, 587(8), 1-17.
    29. Mehrabian, A. R., & Lucas, C. (2006). A novel numerical optimization algorithm inspired from weed colonization. Ecological Informatics, 1(4), 355-366.
    30. Mirakbari, M., Mortezaie, F. G., & Mohseni, S. M. (2018). Investigation of the effect of meteorological drought on surface and ground water resources by Indices SPI, SPEI, SDI and GRI. Iranian Journal of Watershed Management Science and Engineering, 12(42 ), 70-80. (In Persian)
    31. Mucherino, A., Papajorgji, P. J., & Pardalos, P. M. (2009). K-nearest neighbor classification. In Data mining in agriculture. New York, USA, 83-106.
    32. Nabipour, N., Dehghani, M., Mosavi, A., & Shamshirband, S. (2020). Short-Term hydrological drought forecasting based on different nature-inspired optimization algorithms hybridized with artificial neural networks. IEEE Access, 8, 15210-15222.
    33. Park, S., Im, J., Jang, E., & Rhee, J. (2016). Drought assessment and monitoring through blending of multi-sensor indices using machine learning approaches for different climate regions. Agricultural and Forest Meteorology, 216, 157-169.
    34. Rao, R. V., Savsani, V. J., & Vakharia, D. P. (2012). Teaching–learning-based optimization an optimization method for continuous non-linear large scale problems. Information Sciences, 183(1), 1-15.
    35. Rao, R. V., Savsani, V. J., & Vakharia, D. P. (2011). Teaching–learning-based optimization. A novel method for constrained mechanical design optimi zation problems. Computer-Aided Design, 43(3), 303-315.
    36. Shafiei, M., Ghahraman, B., Ansari, H., & Sharifi, M. (2011). Stochastic simulation of drought severity based on palmer index. Water and Irrigation Management, 1(1), 1-13. (In Persian)
    37. Shamshirband, S., Hashemi, S., Salimi, H., Samadianfard, S., Asadi, E., Shadkani, S., & Chau, K.W. (2020). Predicting standardized streamflow index for hydrological drought using machine learning models. Engineering Applications of Computational Fluid Mechanics, 14(1), 339-350.
    38. Satapathy, S. C., Naik, A., & Parvathi, K. (2012, December). Teaching learning based optimization for neural networks learning enhancement. In: International Conference on Swarm, Evolutionary, and Memetic Computing. Berlin, Heidelberg, Germany, 761-769.
    39. Sheffield, J., & Wood, E. F. (2011). Drought. past problems and future scenarios. Routledge.
    40. Toğan, V. (2012). Design of planar steel frames using teaching–learning based optimization. Engineering Structures, 34, 225-232.
    41. Vicente-Serrano, S. M., Beguería, S., & López-Moreno, J. I. (2010). A multiscalar drought index sensitive to global warming. the standardized precipitation evapotranspiration index. Journal of Climate, 23(7), 1696-1718.