ارزیابی کارایی روش‌های مختلف ایستاسازی داده‌ها با استفاده از مدل‌های خانواده ARIMA

نوع مقاله: مقاله پژوهشی

چکیده

پیش­بینی عمق بارندگی در مدیریت منابع آب هر منطقه از اهمیت بالایی برخوردار است. مدل­های سری­های زمانی خانواده ARIMA کاربرد گسترده­ای در این زمینه دارند. هدف اصلی این مطالعه پیش­بینی بارندگی ماهانه با استفاده از بهترین روش ایستاسازی سری زمانی و مناسب­ترین مدل خانواده ARIMA است. در این مطالعه، از داده­های ایستگاه همدید اردبیل استفاده شد. در گام اول، بخش­های روند و تغییرات فصلی داده­های بارندگی ماهانه از سال 1990 تا 2016 با استفاده از روش­های مختلف حذف شد و در گام دوم، کارایی مدل­های مختلف خانواده ARIMA در پیش­بینی بارندگی ماهانه مورد بررسی قرار گرفت. نتایج نشان داد که روش ایستا­سازی با استفاده از میانگین متحرک مرکزی مرتبه 12 و میانگین فصلی به­ترتیب، برای حذف روند و تغییرات فصلی (به­دلیل ایجاد بالاترین مقدار ضریب همبستگی (8/0=r)) بهترین روش ایستاسازی بوده و مدل 12(0،0،1)(1،0،1)SARIMA با بیشترین ضریب همبستگی (8/0=r) و کمترین معیار آکائیک (74/191=AIC) مناسب­ترین مدل پیش­بینی بارندگی ماهانه در ایستگاه مورد مطالعه است. در نهایت، بارندگی ماهانه 3 سال آینده (2017 تا 2019) با استفاده از روش ایستاسازی و مدل منتخب پیش­بینی گردید. نتایج نشان داد که روند بارندگی ایستگاه همدید اردبیل در سه سال آینده به­صورت کاهشی خواهد بود.

کلیدواژه‌ها


عنوان مقاله [English]

Evaluation of Different Data Stationary Methods Efficiency Using ARIMA Family Models

چکیده [English]

     Forecasting rainfall depth is very important in water resources management. ARIMA family time series models have a widespread application in this context. The main objective of this study was to predict monthly rainfall using the best time series stationary method and the most suitable ARIMA family model. In this study, Ardabil synoptic station’s data was used. In the first step, the trend and seasonality terms of monthly rainfall data from 1990 to 2016 were removed using different methods and in the second step the efficiency of different ARIMA models for predicting monthly rainfall was investigated. Results showed that the stationary method using 12 period centered moving average and seasonal average in order to remove trend and seasonal variation, respectively, is the best stationary method with the highest correlation coefficient (r=0.8). Also, the SARIMA (1,0,1) (0,0,1)12 model with the highest correlation coefficient (r=0.8) and the lowest Akaike criterion (AIC=191.74) is the best prediction model for monthly rainfall at the studied station. Finally, the monthly rainfall of the next 3 years (2017-2019) forecasted using the optimized stationary method and the selected model. Results showed that the rainfall trends of Ardabil synoptic station will be decreased in the next three years.

کلیدواژه‌ها [English]

  • Akaike Information Criterion
  • Ardabil
  • Rainfall prediction
  • Time Series
Abbot J and Marohasy J, 2014. Input selection and optimization for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks. Atmospheric Research 138: 166-178.
Abbot J and Marohasy J, 2012. Application of artificial neural networks to rainfall forecasting in Queensland, Australia. Advances in Atmospheric Sciences 29(4): 717-730.
Abdollah Nejhad K, 2015. Stochastic time series models in monthly precipitation prediction. Geographical Planning of Space 5(17): 15- 25. (In Persian)
Bagirov AM, Mahmood A and Barton A, 2017. Prediction of monthly rainfall in Victoria, Australia: Clusterwise linear regression approach. Atmospheric Research 188: 20-29.
Bowerman BL and Connel RT, 1979. Time Series and Forecasting. PWS Publisher, Boston.
Box GPE, Jenkins GM and Reinsel GC, 1994. Time Series Analysis: Forecasting and Control. John Wiley & Sons, New Jersey.
Bozorg Niya SA and Niroomand H, 2011. Time Series, Payamnoor University press, Tehran. (In Persian)
Dastorani M, Mirzavand M, Dastorani MT and Sadatinejad SJ, 2016. Comparative study among different time series models applied to monthly rainfall forecasting in semi-arid climate condition. Natural Hazards 81(3): 1811-1827.
Hosseinalizadeh M, Hassanalizadeh N, Babanezhad M and Rezanezhad M, 2014. Monthly precipitation forecast by time series packages in R environment (Case study: Arazkooseh station of Golestan province). Conservation and Utilization of Natural Resources 2(2): 1-12. (In Persian)
Jafarzadeh J, Rostamzadeh H and Asadi E, 2017. Modeling temporal of groundwater level using basic techniques of time series analysis (Case Study: Ardabil Plain). Water and Soil Science- University of Tabriz 27(4): 185-196. (In Persian)
Karamooz M and Araghi Nejad Sh, 2014. Advanced Hydrology. Amirkabir University of Technology Press, Tehran. (In Persian)
Khalili K, Fakheri-Fard A, Dinpajooh Y and Ghorbani MA, 2011. Nonlinearity testing of stream-flow processes by BDS test (case study: Shaharchi River in Urmia). Water and Soil Science- University of Tabriz 21(2): 25-37. (In Persian)
Khalili K, Nazeri Tahrudi M and Abbaszadeh Afshar M, 2017. Performance evaluation of combined multivariate time series, MPAR and MPAR-ARCH models for modeling river flow eeries considering the effectivemeteorological components (Case study: Nazloochai river). Water and Soil Science- University of Tabriz 27(3): 121-133. (In Persian)
Khalili K and Nazeri Tahrudi M, 2016. Performance evaluation of ARMA and CARMA models in modeling annual precipitation of Urmia synoptic station. Water and Soil Science- University of Tabriz 26(2-1): 13-28. (In Persian)
Khalili K and Nazeri Tahrudi M, 2014. Modeling of annual water level changes of Urmia Lake with linear time series models. Water Management in Arid Lands 1(1): 25-35. (In Persian)
Mahdavi M, 2007. Applied Hydrology, Tehran University Press. Tehran. (In Persian)
Meher J and Jha R, 2013. Time-series analysis of monthly rainfall data for the Mahanadi river basin, India. Sciences in Cold and Arid Regions 5(1): 73-84.
Mirzavand M and Ghazavi R, 2015. A stochastic modelling technique for groundwater level forecasting in an arid environment using time series methods. Water Resource Management 29:1315-1328.
Narasimha Murthy KV, Saravanal R and Vijaya Kumar K, 2018. Modeling and forecasting rainfall patterns of southwest monsoons in North–East India as a SARIMA process. Meteorology and Atmospheric Physics 130(1): 99-106.
Nazeri Tahrudi M, Khalili K, Abbaszade Afshar M and Nazeri Tahrudi Z, 2014. Compared to the normal mechanism becomes the normal monthly rainfall data from different regions of Iran. Journal of Water and Soil 28(2): 365-372. (In Persian)
Papalaskaris T, Panagiotidis T and Pantrakis A, 2016. Stochastic monthly rainfall time series analysis, modeling and forecasting in Kavala sity, Greece, north-eastern mediterranean basin. Procedia Engineering 162: 254-263.
Rahman AM, Yunsheng Y and Sultana N, 2017. Analysis and prediction of rainfall trends over Bangladesh using Mann–Kendall, Spearman’s rho tests and ARIMA model. Meteorology and Atmospheric Physics 129(4): 409-424.
Somvanshi VK, Pandey OP, Agrawal PK, Kalanker NV, Prakash MR and Chand R, 2006. Modelling and prediction of rainfall using artificial neural network and ARIMA techniques. Journal of Indian Geophysical Union 10(2): 141-151.
Toranjian A and Marofi S, 2017. Evaluation of deterministic and geostatistical methods for regionalization of seasonal precipitation in Hamadan province. Water and Soil Science- University of Tabriz 27(3): 211-224. (In Persian)
Veysipoor H, Masumpoor Samakoosh J, Sahneh B and Yousefi Y, 2010. Analysis of prediction of rainfall and temperature trends using time series models (ARIMA) (Case study: Kermanshah township). Geography 4(12): 63 – 77. (In Persian)
Wang HR, Wang C, Lin X and Kang J, 2014. An improved ARIMA model for precipitation simulations. Nonlinear Processes in Geophysics 21: 1159-1168.