توسعه یک مدل جدید ترکیبی احتمالاتی کلاس مبنا برای پیش‌بینی بارش ماهانه

نوع مقاله : مقاله پژوهشی

نویسنده

استادیار گروه علوم و مهندسی آب دانشگاه فردوسی مشهد، مشهد، ایران.

چکیده

پیش‌بینی بارش ماهانه با دقت زیاد یکی از چالش‌های مهم در علوم هیدرولوژی و هواشناسی می‌باشد و در برنامه‎ریزی منابع آب از اهمیت بالایی برخوردار است. در تحقیق حاضر، یک مدل ترکیبی احتمالاتی کلاس مبنا (CPHM) بر پایه ترکیب روش‌های کلاس‎بندی و توابع کرنل احتمالاتی توسعه داده شده است که با استفاده از آن می‌توان بر اساس بارش‌های فصلی (ورودی مدل)، بارش ماهانه (خروجی مدل) را با دقت بالایی برای تمامی ‌ماه‌های یک فصل پیش‌بینی نمود. برتری‌های این مدل نسبت به روش‌های مرسوم پیش‌بینی ماهانه بارش، از یک سو قابلیت آن برای پیش‌بینی بارش ماهانه برای فصلی نظیر پاییز در ایران می‌باشد که ماه‌های قبل از آن (در تابستان) بدون بارش است، و از سوی دیگر قابلیت آن برای پیش‌بینی هم‌زمان بارش برای تمامی ماه‌های یک فصل می‌باشد که از نظر مدیریت منابع آب بسیار ارزشمند است. از این‌رو، به منظور ارزیابی کارآیی این مدل، مدل مذکور برای پیش‌بینی بارش ماهانه پاییزه در حوضه آبریز کرخه که دربرگیرنده جلگه حاصلخیز خوزستان است، بکار گرفته شد و عملکرد آن با مدل شبکه عصبی مصنوعی (ANN) با ساختار بهینه شده نیز مورد مقایسه قرار گرفت. نتایج نشان‌دهنده عملکرد بالای مدل CPHM و برتری آن در مقایسه با مدل بهینه شده ANN برای پیش‌بینی بارش در هر سه ماه فصل پاییز می‌باشد؛ به‌طوری که متوسط دقت نتایج در مرحله صحت‎سنجی این مدل برای سه ماه پاییز بر اساس شاخص‌های نش- ساتکلیف (NSE)، جذر میانگین مربعات خطا (RMSE) و ضریب همبستگی پیرسون (PCC) به ترتیب برابر با  0/7، 12 و 0/86 می‌باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Developing a New Class-based Probabilistic Hybrid Model for Monthly Precipitation Forecasting

نویسنده [English]

  • Fereshteh Modaresi
Assistant Professor, Department of Water and Science Engineering, Ferdowsi University of Mashhad, Mashhad, Iran (FUM).
چکیده [English]

High accuracy forecasting of monthly precipitation is one of the major challenges in hydrology and meteorology and is of great importance in water resources planning. In the current research a Class-Based Probabilistic Hybrid Model (CPHM) has been developed on the basis of a hybrid of classification methods and probabilistic kernel functions. Using this method, monthly precipitation (model output) can be forecasted more accurately for all months of a season according to seasonal precipitation (model input). The superiorities of this model over conventional monthly rainfall forecasting methods are on the one hand, its capability for monthly precipitation forecasting for a season such as autumn in Iran the previous months of which in summer have no precipitation, and on the other hand, the simultaneous prediction of precipitation for all months of a season which is valuable in terms of water resources management. In order to evaluate this model, it was applied to forecast autumnal monthly precipitation for Karkheh basin which includes Khuzestan fertile plain and its efficiency was compared to an optimized structural ANN model. Results revealed a high performance for the developed CPHM model while it was also superior to ANN model for its precipitation forecasts for all three months of autumn. The average accuracy of the model resulted from validation phase for three autumn months based on Nash-Sutcliff (NSE), Root Mean Square Error (RMSE), and Pearson correlation coefficient (PCC) indices were 0.7, 12, and 0.86, respectively.

کلیدواژه‌ها [English]

  • Monthly Precipitation Forecasting
  • Hybrid Model
  • Kernel function
  • Classification
  • Karkheh
  • CPHM
Abbot J, Marohasy J (2014) Input selection and optimization for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks. Atmospheric Research 138:166-178
Afshin S, Fahmi H, Alizadeh A, Sedghi H, Kaveh F (2011) Long term rainfall forecasting by integrated artificial neural network-fuzzy logic-wavelet model in Karoon basin. Scientific Research and Essays 6(6):1200-1208
Bahrami M, Amiri MJ, Rezaei Maharluei F, Ghaffari KA (2017) Data pre-processing effects on the artificial neural network performance to predict monthly rainfall (case study: Abadeh county). Iranian Journal of Eco hydrology 4(1):29-37 (In Persian)
Coulibaly P, Anctil F, Bobe’e B (2000) Daily reservoir inflow forecasting using artificial neural networks with stopped training approach. Journal of Hydrology 230(3-4):244-257
Danandeh Mehr A, Nourani V, Karimi Khosrowshahi V, et al. (2019) A hybrid support vector regression–firefly model for monthly rainfall forecasting. International Journal of Environmental Science and Technology16:335–346
Dayal D, Swain S, Gautam AK, et al (2019) Development of ARIMA model for monthly rainfall forecasting over an Indian river basin. In: Proc. of World Environmental and Water Resources Congress, 19–23 May, Pittsburgh, Pennsylvania
Diaz-Ramirez JN, McAnally WH, Martin JL (2011) Analysis of hydrological processes applying the HSPF model in selected watersheds in Alabama, Mississippi, and Puerto Rico. Applied Engineering in Agriculture 27(6):937-954
Fallah-Ghalhary GA, Mousavi Baygi M, Habibi Nokhandan M (2009) Annual rainfall forecasting by using mamdani fuzzy interface system. Research Journal of Environmental Sciences 3(4):400-413
Farajzadeh J, Fakhari Fard A, Lotfi S (2014) Modeling of monthly rainfall and runoff of Urmia lake basin using "feed-forward neural network" and "time series analysis" model. Water Resources and Industry 7(8):38-48
Fatehi Marj A, Mahdian MH (2009) Autumn rainfall forecasting using ENSO indices by Neural Network method in Urmia lake basin. Watershed Management Researches 84:42-52 (In Persian)
Kalra A, Ahmad S (2012) Estimating annual precipitation for the Colorado river basin using oceanic-atmospheric oscillations. Water Resources Research 48:W06527
Mahmud I, Bari SH, Rahman MT (2017) Monthly rainfall forecasting using autoregressive integrated moving average method. Environmental Engineering Research 22(2):162-168
Menhaj MB (2017) Fundamentals of neural networks: Computational intelligence (Vol. 1). Amirkabir University Press, 716 p (In Persian)
Modaresi F, Araghinejad S, Ebrahimi K (2015) Assessment of model fusion strategy for increasing the accuracy of autumn rainfall forecasting. Journal of Agricultural Meteorology 2(2):62-69 (In Persian)
Moriasi DN, Arnold JG, Van Liew MW, et al. (2007) Model evaluation guidelines for systemic quantification of accuracy in watershed simulations. Transactions of ASABE 50(3):885-900
Mozafari GA, Shafie Sh, Hemati HR (2016) Predicting monthly precipitation of Kermanshah synoptic station using the hybrid model of neural network and wavelet. Water and Soil Conservation 22(6):135-152 (In Persian)
Nazemosadat MJ, Cordery I (2000) On the relationships between Enso and autumn rainfall in Iran. International Journal of Climatology 20(1):47-61
Nazemosadat MJ (2008) Improving neural network models for forecasting seasonal precipitation in southwestern Iran: The evaluation of oceanic-atmospheric indices. Advances in Geosciences 16:133-145
Nirmala M, Sundaram SM (2010) A seasonal ARIMA model for forecasting monthly rainfall in Tamilandu. Advances in building Sciences and Mechanics 1(2):43-47
Ouyang Q, Lu W, Xin X, et al. (2016) Monthly rainfall forecasting using EEMD-SVR based on phase-space reconstruction. Water Resources Management 30(7):2311–2325
Rahiminasab M, Amerian Y (2019) Prediction of monthly rainfall in Iran using the combination of artificial neural networks and extended Kalman filter. Journal of Geographical Data (SEPEHR) 28(110):77-90 (In Persian)
Rezaei Banafsheh M, Jahanbakhsh S, Khatibi M, Zeinali B (2010) Forecast of autumn and winter rainfall in the western half of Iran using Mediterranean SST in summer and autumn. Natural Geography Journal 74:47-62 (In Persian) 
Roghani R, Soltani S, Bashari H (2012) Investigation of the relationship between Southern Oscillation Index, Pacific and Indian sea surface temperature versus monthly and seasonal rainfall in Iran. Journal of Water and Soil Science 16(61):273-292
Schepen A, Wang QJ, Robertson D (2012) Evidence for using lagged climate indices to forecast Australian seasonal rainfall. Journal of Climate 25(4):1230–1246
Silverman D, Dracup JA (2000) Artificial neural networks and long-range precipitation prediction in California. Journal of Applied Meteorology 39(1):57-66
Solgi A, Zarei H (2018) Application of gene expression programming and support vector regression models to modeling and prediction monthly precipitation. Researches in Geographical Sciences 18(50):91-103 (In Persian)
Swain S, Nandi S, Patel P (2018) Development of an ARIMA model for monthly rainfall forecasting over Khordha District, Odisha, India. Advances in Intelligent Systems and Computing 708:158942575