ارزیابی ترکیب مدل ANFIS با الگوریتم‌های فراکاوشی بهینه‌سازی در پیش‌بینی طوفان‌های گرد و غبار استان خوزستان

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری گروه مهندسی آبیاری و آبادانی، پردیس کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران.

2 دانشیار گروه مهندسی آبیاری و آبادانی، پردیس کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران.

3 دانشیار دانشکده مهندسی عمران، پردیس دانشکده‌های فنی، دانشگاه تهران، تهران، ایران.

4 دانشیار گروه مهندسی عمران، زمین‌شناسی و محیط‌زیست، دانشکده محیط‌زیست و پایداری، دانشگاه ساسکاچوان، ساسکاتون، کانادا.

5 استاد دانشکده منابع طبیعی، پردیس کشاورزی و منابع طبیعی، دانشگاه تهران، کرج، ایران.

چکیده

به منظور کنترل و مدیریت صحیح طوفان­های گرد و غبار، آگاهی از تغییرات زمانی- مکانی این پدیده و لزوم پیش­بینی و مدل­سازی آن با هدف شناخت دقیق­تر رفتار طوفان­های گرد و غبار نسبت به محرک­های طبیعی و انسانی، امری ضروری است. با توجه به توسعه روز افزون فرامدل­ها و ترکیب آن­ها با الگوریتم­های بهینه­سازی به منظور مدل­سازی و پیش­بینی متغیرهای هواشناسی، در این پژوهش چهار الگوریتم بهینه­سازی فراکاوشی ازدحام ذرات (PSO)، ژنتیک (GA)، کلونی مورچگان در محیط­های پیوسته (ACOR) و تکاملی تفاضلی (DE) با مدل سیستم استنتاج تطبیقی فازی عصبی (ANFIS) ترکیب شد. عملکرد چهار مدل ترکیبی توسعه داده­شده با مدل  ANFISبرای پیش­بینی متغیرهای فراوانی روزهای همراه با طوفان گرد و غبار (FDSD) در مقیاس فصلی در استان خوزستان در جنوب غربی ایران ارزیابی شد. بدین منظور از داده­های ساعتی گرد و غبار و کدهای سازمان جهانی هواشناسی در مقیاس فصلی با طول دوره آماری 40 ساله (2019-1980) در هفت ایستگاه سینوپتیک استان خوزستان استفاده شد. نتایج شاخص­های نیکویی برازش در مرحله آموزش و آزمایش نشان داد که اختلاف معنی­داری بین روش ANFIS و سایر مدل­های ترکیبی مورد استفاده وجود ندارد. مقادیر R و RMSE برترین مدل ترکیبی (ANFIS-PSO) به ترتیب از 88/0 تا 97/0 و 10/0 تا 19/0 و در مدل ANFIS به ترتیب از 83/0 تا 94/0 و 11/0 تا 21/0 متغیر بودند. همچنین نتایج نشان داد که ترکیب الگوریتم­های بهینه­سازی استفاده­شده با مدل ANFIS نتایج مدل را نسبت به مدل انفرادی ANFIS به صورت معنی­داری بهبود نمی­بخشد.

کلیدواژه‌ها


عنوان مقاله [English]

Evaluation of the Combination of ANFIS Model with Metaheuristic Optimization Algorithms in Predicting Dust Storms of Khuzestan Province

نویسندگان [English]

  • Mohammad Ansari Ghojghar 1
  • Masoud Pourgholam-Amiji 1
  • Shahab Araghinejad 2
  • Banafsheh Zahraie 3
  • Saman Razavi 4
  • Ali Salajegheh 5
1 Ph.D. Candidate, Department of Irrigation and Reclamation Engineering, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
2 Associate Professor, Department of Irrigation and Reclamation Engineering, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
3 Associate Professor, School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran.
4 Associate Professor, Department of Civil, Geological, and Environmental Engineering, School of Environment and Sustainability, University of Saskatchewan, Saskatoon, Canada.
5 Professor, Faculty of Natural Resources, College of Agriculture and Natural Resources, University of Tehran, Karaj, Iran.
چکیده [English]

Due to the growing development of meta-models and their combination with optimization algorithms for modeling and predicting meteorological variables, in this research four metaheuristic optimization algorithms of Particle Swarm Optimization (PSO), Genetics Algorithms (GA), Ant Colony Optimization for Continuous Domains (ACOR) and Differential Evolutionary (DE) were combined with the adaptive neural-fuzzy inference system (ANFIS) model. The performance of four combined models developed with ANFIS model to predict the Frequency variables of Dust Stormy Days (FDSD) on a seasonal scale in Khuzestan province in the southwest of Iran was evaluated. For this purpose, hourly dust data and codes of the Word Meteorological Organization were used on a seasonal scale with a statistical period of 40 years (1980-2019) in seven synoptic stations of Khuzestan province. The results of good fit indices in the training and testing phase showed that there is no significant difference between the ANFIS method and other combined models used. R and RMSE values of the best combined model (ANFIS-PSO) from 0.88 to 0.97 and 0.10 to 0.19, respectively, and in the ANFIS model from 0.83 to 0.94 and 0.11 to 21, respectively, were variable. The results also showed that the combination of optimization algorithms used with the ANFIS model does not significantly improve the results of the model compared to the individual ANFIS model.

کلیدواژه‌ها [English]

  • ANFIS
  • Artificial intelligence
  • Evolutionary Algorithms
  • Genetic Algorithm
  • Modeling
[1]          Abdolshahnejad, M., Khosravi, H., Nazari Samani, A. A., Zehtabian, G. R., & Alambaigi, M. (2020). Determining the Conceptual Framework of Dust Risk Based on Evaluating Resilience (Case Study: Southwest of Iran). Strategic Research Journal of Agricultural Sciences and Natural Resources, 5(1), 33-44. (In Persian)
[2]          Annaty, M., Eghbalzadeh, A., & Hosseini, S. (2015). Hybrid ANFIS model for predicting scour depth using particle swarm optimization. Indian journal of science and technology, 8(22), 642-649.
[3]          Ansari Ghojghar, M., Pourgholam-Amiji, M., Bazrafshan, J., Hosseini-Moghari, S. M., Liaghat, A., & Araghinejad, Sh. (2020). Performance Evaluation of Genetic Algorithm and GA-SA Hybrid Method in Forecasting Dust Storms (Case Study: Khuzestan Province). Iranian Journal of Soil and Water Research (Articles in Press). (In Persian)
[4]          Araghinejad, S. (2013). Data-driven modeling: using MATLAB® in water resources and environmental engineering (Vol. 67). Springer Science & Business Media.
[5]          Araghinejad, Sh., Ansari Ghojghar, M., Pourgholam-Amiji, M., Liaghat, A., & Bazrafshan, J. (2019). The Effect of Climate Fluctuation on Frequency of Dust Storms in Iran. Desert Ecosystem Engineering Journal, 7(21), 13-32. (In Persian)
[6]          Azad, A., Karami, H., Farzin, S., Saeedian, A., Kashi, H., & Sayyahi, F. (2018). Prediction of water quality parameters using ANFIS optimized by intelligence algorithms (case study: Gorganrood River). KSCE Journal of Civil Engineering, 22(7), 2206-2213.
[7]          Cao, R., Jiang, W., Yuan, L., Wang, W., Lv, Z., & Chen, Z. (2014). Inter-annual variations in vegetation and their response to climatic factors in the upper catchments of the Yellow River from 2000 to 2010. Journal of Geographical Sciences, 24(6), 963-979.
[8]          Davis, L. (1991). Handbook of genetic algorithms.
[9]          Dorigo, M. (1992). Optimization, learning and natural algorithms. PhD Thesis, Politecnico di Milano.
[10]      Farajzadeh Asl, M., & Alizadeh, Kh. (2011). Spatial Analysis of Dust storm in Iran. The Journal of Spatial Planning, 15(1), 65-84. (In Persian)
[11]      Goudie, A. S., & Middleton, N. J. (2006). Desert dust in the global system. Springer Science & Business Media.
[12]      Hassanzadeh, Y., Abdi Kordani, A., & Fakheri Fard, A. (2012). Drought Forecasting Using Genetic Algorithm and Conjoined Model of Neural Network-Wavelet. Journal of Water and Wastewater, 23(3), 48-59. (In Persian)
[13]      Jalalkamali, A. (2015). Using of hybrid fuzzy models to predict spatiotemporal groundwater quality parameters. Earth Science Informatics, 8(4), 885-894.
[14]      Jang, J. S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3), 665-685.
[15]      Mahmoodimahpash, N., & Souri, B. (2020). Detecting origin of dust-fall using ions ratio and morphology of the particles in western Iran. Journal of Natural Environment, 73(2), 355-367. (In Persian)
[16]      Mehrabi, Sh., Soltani, S., & Jafari, R. (2015). Investigating the Relationship between Climatic Parameters and the Exposure of Greenhouses (Case Study: Khuzestan Province). Journal of Water and Soil Science, 19(71), 69-80. (In Persian)
[17]      Mehri, Y., Mehri, M., & Soltani, J. (2020). Evaluation of combined Models with Optimization Approach of PSO and GA in ANFIS for Predicting of Dispersion Coefficient in Rivers. Water and Irrigation Management, 10(1), 45-59. (In Persian)
[18]      Mohammadi Ghaleni, M., & Ebrahimi, K. (2013). Evaluation of direct search and genetic algorithms in optimization of muskingum nonlinear model parameters - a flooding of Karoun river, Iran. Water and Irrigation Management, 2(2), 1-12. (In Persian)
[19]      Mozafari, Gh. A., Shafie, Sh., & Hemati, H. R.(2016). Predicting monthly precipitation of Kermanshah synoptic station using the hybrid model of neural network and wavelet. Journal of Water and Soil Conservation, 22(6), 135-152. (In Persian)
[20]      Nabizadeh, M., Mosaedi, A., & Dehghani, A. (2012). Intelligent estimation of stream flow by Adaptive Neuro-Fuzzy Inference System. Water and Irrigation Management, 2(1), 69-80. (In Persian)
[21]      Nadiri, A. A., Taherkhani, Z., & Sadeghi Aghdam, F. (2017). Prediction of ground water level of Bostan Abad using combining artificial intelligence models. Iran Water Resources Research, 13(3), 43-55. (In Persian)
[22]      O’Loingsigh, T., McTainsh, G. H., Tews, E. K., Strong, C. L., Leys, J. F., Shinkfield, P., & Tapper, N. J. (2014). The Dust Storm Index (DSI): a method for monitoring broadscale wind erosion using meteorological records. Aeolian Research, 12, 29-40.
[23]      Prudêncio, R. B., & Ludermir, T. B. (2003). Neural network hybrid learning: genetic algorithms & Levenberg-Marquardt. In Between Data Science and Applied Data Analysis (pp. 464-472). Springer, Berlin, Heidelberg.
[24]      Rashki, A., Kaskaoutis, D. G., Goudie, A. S., & Kahn, R. A. (2013). Dryness of ephemeral lakes and consequences for dust activity: the case of the Hamoun drainage basin, southeastern Iran. Science of the total environment, 463, 552-564.
[25]      Sepehri, M, Ildoromi, A. R., Hosseini, S. Z., Nori, H., Mohammadzade, F., & Artimani, M. M. (2018). The combination of neural networks and genetic algorithms is a way to estimate the Peak flood. Iranian Journal of Watershed Management Science and Engineering, 11(39), 23-28. (In Persian)
[26]      Shafaei, M., Fakheri Fard, A., Darbandi, S., Ghorbani, M. (2014). Prediction Daily Flow of Vanyar Station Using ANN and Wavelet Hybrid Procedure. Irrigation and Water Engineering, 4(2), 113-128. (In Persian)
[27]      Shi, Y. (2001). Particle swarm optimization: developments, applications and resources. In Proceedings of the 2001 congress on evolutionary computation (IEEE Cat. No. 01TH8546), 1, 81-86.
[28]      Sobhani, B., Safarian Zengir, V., & faizollahzadeh, S. (2020). Modeling and prediction of dust in western Iran. Physical Geography Research Quarterly, 52(1), 17-35. (In Persian) 
[29]      Socha, K., & Dorigo, M. (2008). Ant colony optimization for continuous domains. European journal of operational research, 185(3), 1155-1173.
[30]      Sreedhara, B. M., Rao, M., & Mandal, S. (2019). Application of an evolutionary technique (PSO–SVM) and ANFIS in clear-water scour depth prediction around bridge piers. Neural Computing and Applications, 31(11), 7335-7349.
[31]      Storn, R., & Price, K. (1997). Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. Journal of global optimization, 11(4), 341-359.
[32]      Yarmoradi, Z., Nasiri, B., Mohammadi, Gh. H., & Karampour, M. (2018). Trend analysis of dusty day’s frequency in Eastern arts o Iran associated with Climate Fluctuations. Desert Ecosystem Engineering Journal, 7(18), 1-14. (In Persian)
Zeinali, B. (2016). Investigation of frequency changes trend of days with dust storms in western half of Iran. Journal of Natural Environment hazards, 5(7), 100-87. (In Persian)