Reconstruction of Missing Data of Monthly Total Sunshine Hours Using Artificial Neural Networks

Document Type : Original Article

Author

Assistant professor of water Engineering Department of University of Zanjan., Zanjan., Iran

Abstract

Reference crop evapotranspiration is one of the important factors of hydrological cycle. This parameter is used to design irrigation systems, hydraulic structures and drainage systems. One of data that required to calculate the amount of reference crop evapotranspiration is solar radiation which in the absence of this data, monthly sunshine duration data will be used. At the most of the weather stations of Iran the data of monthly total sunshine hours is not available at previous years, so the need to rebuild the data is felt. In the present study two kind of artificial neural network model (MLP and RBF) and meteorological data of target station and monthly total sunshine hours of neighbor stations are used to rebuild the missing data. The results showed that using data from meteorological data of target station and neighbor station, the total monthly sunshine reconstructed with high precision. The results of the different scenarios showed that if only the meteorological of target station such as minimum and maximum temperature, average relative humidity, solar radiation, extraterrestrial radiation and straight, dark and cloudy days number is used, with a precision of RMSE=16.79 hour and MAR=6.44% the monthly total sunshine hours is estimated. Also if only the data from nearby stations is used, the estimates would be more conducive to accuracy (RMSE=14.25 hour and MARE=5.71%). The best results were obtained when both weather data set of target station and adjacent stations are used (RMSE=13.78 hour and MARE=4.97%). Comparison of the performance of the ANN-MLP and RBF ANN-MLP showed that the accuracy of MLP neural network is somewhat greater. Finally the time series of monthly total sunshine hours and reference evapotranspiration were renovated.

Keywords

References

بیات،ک و میرلطیفی،م. 1388 . تخمین تابش کل خورشیدی روزانه با استفاده از مدل‌های رگرسیونی و شبکه‌های عصبی مصنوعی. مجله علوم کشاورزی و منابع طبیعی. 16.3 : 1-11
خلیلی،ع.، رضایی صدر،ح. 1376. برآورد تابش کلی در گستره ایران بر مبنای داده‌های اقلیمی. تحقیقات جغرافیایی. 46.2 : 15-35
خورشید دوست،ع.، نساجی زواره،م و قرمز چشمه،ب. 1391. بازسازی سری‌های زمانی دمای حداکثر و حداقل روزانه با استفاده از روش نزدیک‌ترین همسایه و شبکه عصبی مصنوعی (مطالعه موردی غرب استان تهران). فصلنامه‌ی علمی-پژوهشی فضای جغرافیایی. 12.38 : 197-214.
صیادی،ح.، غفاری،ا.،  فعالیان،ا و صدرالدینی،ع. 1388. مقایسه عملکرد شبکه­های عصبی RBFو  MLPدر برآورد تبخیروتعرق گیاه مرجع. مجله دانش آب و خاک، 19.1 :1-12
کریمی­زاد،ف و شاهسوند،ا. 1392. مقایسه نتایج حاصل از شبکه‌های عصبی MLP و RBF در پیش‌بینی نتایج حاصل از هم­زمانی پدیده‌های انتقال جرم و انتقال حرارت. مجله مدل‌سازی در مهندسی. 11.33 :27-43
مجنونی،ا.، زند پارسا،ش.، سپاسخواه،ع و ناظم السادات،م.ج. 1387. توسعه و ارزیابی مدل‌های تخمین تابش خورشیدی بر اساس ساعات آفتابی و اطلاعات هواشناسی. علوم و فنون کشاورزی و منابع طبیعی12.(46 : 491-499
Abebe,AJ., Solomatine,D.P., Venneker,R.G.W. 2000. Application of adaptive fuzzy rule-based models for reconstruction of missing precipitation events. Hydrological Science Journal 45.3:425–436
Atsu,S.S., Dorvlo Joseph,A., Jervase, Ali Al-Lawati .2002. Solar radiation estimation using artificial neural networks. Applied Energy. 71.4:307-319.
Bilgili,M and Ozgoren,M. 2011. Daily total global solar radiation modeling from several meteorological data. Meteorology and Atmospheric Physics. 112.3-4:125-138.
Coulibaly,P.N.D., Evora,B. 2007. Comparison of neural network methods for infilling missing daily weather records. Journal of hydrology. 341: 27-41
Goyal,M.K., Bharti,B., Quilty,J., Adamowski,J and Pandey,A. 2014. Modeling of daily pan evaporation in sub-tropical climates using ANN, LS-SVR, Fuzzy Logic, and ANFIS. Expert systems with applications. 41.11:5267-5276.
Hasanpour,M., Dinpashoh,Y. 2012. Evaluation of efficiency of different estimation methods for missing climatological data. Stochastic Environment  Research and Risk Assessment 26:59–71
Hykin,S. 1999. Neural Networks: A Comprehensive Foundation. Printice-Hall, New Jersey.
Kim,J.W and Pachepsky,Y.A. 2010. Reconstructing missing daily precipitation data using regression trees and artificial neural networks for SWAT streamflow simulation. Journal of hydrology. 394.3:305-314.
Kadirgama,K., Amirruddin,A.K., Bakar,R.A .2014. Estimation of Solar Radiation by Artificial Networks: East Coast Malaysia. Energy Procedia. 52.3: 383-388
Koca,A., Hakan,F., Varol,Y., Koca,G.O. 2011. Estimation of solar radiation using artificial neural networks with different input parameters for Mediterranean region of Anatolia in Turkey. Expert Systems with Applications. 38.7: 8756-8762.
Londhe,S., Dixit,P., Shah,S and Narkhede,S., 2015. Infilling of missing daily rainfall records using artificial neural network. ISH Journal of Hydraulic Engineering. 21.3:255-264.
Rehman,S., Mohandes,M. 2008. Artificial neural network estimation of global solar radiation using air temperature and relative humidity. Energy Policy. 36.2: 571-576.
Tabari,H and Talaee,P.H. 2015. Reconstruction of river water quality missing data using artificial neural networks. Water Quality Research Journal of Canada. 50.4:326-335.
Yadav,A.K., Chandel,S.S. 2014. Solar radiation prediction using Artificial Neural Network techniques: A review. Renewable and Sustainable Energy Reviews.33.5: 772-781
Iranian Journal of Irrigation & Drainage
Volume 10, Issue 5 - Serial Number 59
November and December 2016
Pages 570-580

Files

Share

How to cite

Statistics