پیش‌بینی بارش ماهانه بر اساس سیگنال‌های بزرگ‌مقیاس اقلیمی با به‌کارگیری مدل‌های هوشمند و رگرسیون خطی چندگانه (مطالعه موردی: ایستگاه سینوپتیک سمنان)

نوع مقاله : پژوهشی

نویسندگان

1 دانشجوی دکتری، گروه مهندسی آب و سازه‏های هیدرولیکی، دانشکدۀ مهندسی عمران، دانشگاه سمنان

2 استادیار، گروه مهندسی آب و سازه‏های هیدرولیکی، دانشکدۀ مهندسی عمران، دانشگاه سمنان

چکیده

سیگنال‏های بزرگ‏مقیاس اقلیمی شامل کنش‏های جوّی‌ـ ‏اقیانوسی، از عوامل اصلی مؤثر بر نوسانات اقلیمی زمین هستند و شاخص‏های بسیار مهمی در پیش‏بینی متغیرهای اقلیمی محسوب می‏شوند. در این پژوهش، با به‏کارگیری مدل‏های شبکۀ عصبی مصنوعی، شبکۀ فازی‌ـ ‏عصبی و رگرسیون خطی چندگانه، بارش ماه آتی در ایستگاه سینوپتیک سمنان پیش‏بینی شد. بدین‌منظور، از سری زمانی ماهانۀ بارش ایستگاه سینوپتیک سمنان و سیگنال‏های بزرگ‏مقیاس اقلیمی طی یک دورۀ 45 ساله (1966‌ـ 2010 میلادی) استفاده شد. سیگنال‏های مؤثر بر بارش ماه آتی با استفاده از تحلیل رگرسیون خطی گام‏به‏گام تعیین شدند و به‏عنوان متغیرهای ورودی در مدل‏های استفاده‌شده، انتخاب شدند. از 540 سری دادۀ ماهانه، 80 درصد ابتدایی برای آموزش و 20 درصد ‌باقی برای آزمون صحت‏سنجی مدل‏ها استفاده شدند. عملکرد مدل‏ها با معیارهای ارزیابی ضریب همبستگی، میانگین قدر مطلق خطا و ریشۀ میانگین مربعات خطا مقایسه شد. نتایج صحت‏سنجی نشان داد ضرایب همبستگی به‏دست‏آمده (829/0، 793/0 و 767/0) به‌ترتیب مربوط به مدل‏های شبکۀ عصبی مصنوعی، شبکۀ فازی‌ـ ‏عصبی و رگرسیون خطی چندگانه‌اند. بر‌اساس نتایج این تحقیق، می‏توان برای پیش‏بینی بارش ماه آتی ایستگاه سینوپتیک سمنان، به‌ترتیب از مدل‏های شبکۀ عصبی مصنوعی، شبکۀ فازی‌ـ ‏عصبی و رگرسیون خطی چندگانه استفاده کرد.
 

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Prediction of Monthly Precipitation Based on Large-scale Climate Signals Using Intelligent Models and Multiple Linear Regression (Case Study: Semnan Synoptic Station)

نویسندگان [English]

  • Majid Mohammadi 1
  • Hojat Karami 2
  • Saeed Farzin 2
  • Alireza Farokhi 1
1 Ph.D. Student, Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, Iran.
2 Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University, Semnan, Iran
چکیده [English]

Large-scale climatic signals including ocean-atmosphere interactions, are the main factors influencing the earth’s climatic oscillations and are the most important indices in predicting of climate variables. In this research, precipitation in the next month was predicted by applying artificial neural network (ANN), neuro-fuzzy network (NFN), and multiple linear regression (MLR) in Semnan synoptic station. For this purpose, monthly series of precipitation of Semnan synoptic station and signals of large-scale climate signals were used during a period of 45 years (1966–2010). From 540 monthly time series, the first 80% was used for training and the other 20% for testing. Performance of the models was compared by using correlation coefficient (R), mean absolute error (MAE), and root mean square error (RMSE) criteria. Results of the validation step showed that the obtained correlation coefficients (0.829, 0.793 and 0.767) are related to ANN, ANFIS and MLR models. Based on the results of this study, the next month’s precipitation of Semnan synoptic station could be predicted by ANN, NFN and MLR models, respectively.
 
                      

کلیدواژه‌ها [English]

  • Monthly precipitation
  • artificial neural network (ANN)
  • Neuro-Fuzzy Network (NFN)
  • Multiple linear regression (MLR)

مراجع

 
[1]. Khalili N, Khodashenas S.R, Davari K, Mousavi Baygi M. Daily Precipitation Forecasting Using Artificial Neural Networks: A Case Study: Synoptic Station of Mashhad. Watershed Management Researches (Pajouhesh-Va-Sazandegi). 2011; 23(4):7-15. (In Persian).
[2]. Halabian A H. Forecasting Yazd Precipitation with Artificial Neural Networks. Journal of Geographical Sciences. 2009; 11(14): 7-28. (In Persian).
[3]. Faghih H. Evaluating Artificial Neural Network and Its Optimization Using Genetic Algorithm In Estimation of Monthly Precipitation Data (Case Study: Kurdistan Region). Water and Soil Science (Journal of Science and Technology of Agriculture and Natural Resources). 2010; 14(51): 27-42. (In Persian).
[4]. Mahdavi M. Practical Hydrology. 11. Tehran: University of Tehran; 1998. (In Persian).
[5]. Asghari Moghaddam A, Nourani V, Nadiri A. Modeling of Tabriz Plain Rainfall Using Artificial Neural Networks. Journal of Agricultural Science (University of Tabriz). 2008; 18(1): 1-15. (In Persian).
[6]. Anderson D, McNeill G. Artificial Neural Networks Technology. Utica, New York: Kaman Sciences Corporation; 1992.
[7]. Gholizadeh M H, Darand M. Forecasting Monthly Precipitation by Using Artificial Neural Networks a Case Study: Tehran. Physical Geography Research Quarterly. 2010; 42(71): 51-63. (In Persian).
[8]. Fattahi E, Sedaghat Kerdar A, Delavar M. Long- Range Precipitation Prediction Using Artificial Neural Networks. Pajouhesh-Va-Sazandegi. 2008; 3(80): 44-50. (In Persian).
[9]. Fatehi Marj A, Mahdian M.H. Autumn rainfall forecasting using ENSO indices by Neural Network method. Watershed Management Researches (Pajouhesh & Sazandegi). 2009; 22(3): 42-52. (In Persian).
[10].  Falah Ghalhari Gh.A, Khoushhal J. Spring Rainfall Prediction of Khorasan-E Razavi Province, Based upon Climatic Large Scale Signals by Using Artificial Neural Network. Physical Geography Research Quarterly. 2009; 41(69): 115-133. (In Persian).
[11].  Hejazizadeh Z, Fatahi E, Saligheh M, Arsalani F. Study on The Impact of Climate Signals on The Precipitation of The Central of Iran Using Artificial Neural Network. Journal of Geographical Sciences. 2013; 13(29): 75-89. (In Persian).
[12].  Belayneh A, Adamowski J, Khalil B, Ozga-Zielinski B. Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models. Journal of Hydrology. 2014; 508: 418-429.
[13].  Kişi Ö, Sanikhani H. Prediction of long‐term monthly precipitation using several soft computing methods without climatic data. International Journal of Climatology. 2015; 35(14): 4139-4150.
[14].  Omidvar K, Nabavizadeh M, Samarehghasem M. Assessment of Narx Neural Network in Prediction of Daily Precipitation in Kerman Province. Journal of Physical Geography. 2015; 8(27): 73-89. (In Persian).
[15].  Choubin B, Khalighi-Sigaroodi S, Malekian A, Kişi Ö. Multiple linear regression, multi-layer perceptron network and adaptive neuro-fuzzy inference system for forecasting precipitation based on large-scale climate signals. Hydrological Sciences Journal. 2016; 61(6): 1001-1009.
[16].  Altunkaynak A, Ozger M. Comparison of Discrete and Continuous Wavelet–Multilayer Perceptron Methods for Daily Precipitation Prediction. Journal of Hydrologic Engineering. 2016; 04016014: 1-11.
[17].  Rahimi D, Abdollahi Kh, Hasheminasab S. Identify Tele-connection Patterns affecting on Rainfall in Karoon Basin. Iranian journal of Ecohydrology. 2016; 3(1): 95-105. (In Persian).
[18].  Ruigar, H, Golian S. Prediction of precipitation in Golestan dam watershed using climate signals. Theoretical and Applied Climatology. (2016); 123(3-4): 671-682.
[19].  Zamaniyan M, Fatahi R., Fatahi A.R, Hosseinpour F. Input Parameters Preprocessing In Artificial Neural Networks and Adaptive Neuro- Fuzzy Inference System Using Stepwise Regression and Gamma Test Techniques For Estimation of Daily Evaporation. Iranian of Irrigation & Water Engineering. 2012; 3(9): 63-76. (In Persian).
[20].  Ghabaei Sough M, Mosaedi A, Hesam M, Hezarjaribi A. Evaluation Effect of Input Parameters Preprocessing In Artificial Neural Networks (Anns) By Using Stepwise Regression and Gamma Test Techniques For Fast Estimation osf Daily Evapotranspiration. Journal of Water and Soil (Agricultural Sciences and Technology). 2010; 4(23): 610-624. (In Persian).
[21].  Haghizadeh A, Mohammadlou M, Noori F. Simulation of Rainfall-Runoff Process using multilayer perceptron and Adaptive Neuro-Fuzzy Interface System and multiple regression (Case Study: Khorramabd Watershed). Iranian journal of Ecohydrology. 2015; 2(2): 233-243. (In Persian).
[22].  Forougi D, Foroughnejad H, Mirzaei M. Earnings per Share Forecast: The Combination of Artificial Neural Networks and Particle Swarm Optimization Algorithm. Investment Knowledge. 2013; 2(6): 63-82. (In Persian).
[23].  Haykin S. Neural Networks: a Comprehensive Foundation. Prentice Hall PTR, Upper Saddle River. 1998.
[24].  Shanker M, Hu M Y, Hung M S. Effect of data standardization on neural network training. Omega. 199; 24(4): 385-397.
[25].  Asadzadeh F, Byzedi M, Kaki M. Monitoring and Prediction of Drought in Western Urmia Lake Basin Rain Gage Stations by ANFIS Model. Iranian journal of Ecohydrology. 2016; 3(2): 205-2018. (In Persian).
[26].  Sedghi R, Abbaspour Gilandeh Y. Prediction of Soil Fragmentation during Tillage Operation Using Adaptive Neuro Fuzzy Inference System (ANFIS). Journal of Agricultural Machinery. 2015; 4(2): 387-398. (In Persian).
[27].  Jang J S. ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems man and cybernetics. 1993; 23(3): 665-685.
[28].  Jang, J S, Sun C T. Neuro-fuzzy modeling and control. Proceedings of the IEEE. 1995; 83(3): 378-406.
[29].  Tiryaki S, Özşahin Ş, Yıldırım İ. Comparison of artificial neural network and multiple linear regression models to predict optimum bonding strength of heat treated woods. International Journal of Adhesion and Adhesives. 2014; 55: 29–36.
[30].  Sousa S I V, Martins F G, Alvim-Ferraz M C M, Pereira M C. Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations. Environmental Modelling & Software. 2007; 22(1): 97–103.
 
 
اکوهیدرولوژی
دوره 4، شماره 1
فروردین 1396
صفحه 201-214

فایل ها

سابقه مقاله

  • تاریخ دریافت: 30 آذر 1395
  • تاریخ بازنگری: 27 دی 1395
  • تاریخ پذیرش: 01 بهمن 1395

هم رسانی

ارجاع به این مقاله

آمار