ارزیابی روش‌های داده‌کاوی و مدل‌های تجربی مبتنی بر دما-تشعشع در برآورد تبخیر از تشت (مطالعه موردی: شرق دریاچه ارومیه)

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری آبیاری و زهکشی، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، تبریز، ایران.

2 استادیار، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، تبریز، ایران.

3 گروه علوم و مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، تبریز

چکیده

تبخیر از تشت نقش مؤثری در مدیریت منابع آب دارد. ولی به­دلیل اثرات متقابل متغیر­های هواشناسی در محاسبه تبخیر، روابط غیرخطی متعددی ارائه شده است که با توجه به شرایط اقلیمی هر منطقه کارآیی آن­ها قابل بحث است. لذا در مطالعه حاضر، کارآیی روش­های تجربی مبتنی بر دما-تشعشع و روش­های داده‌کاوی رگرسیون ماشین بردار پشتیبان (SVR)، رگرسیون فرآیند گاوسی (GPR) و نزدیکترین همسایگی (IBK) تحت 10 سناریو مختلف حاصل از ترکیب عوامل هواشناسی در پیش­بینی و مدل­سازی تبخیر از تشت در 5 ایستگاه منتخب در شرق حوضه دریاچه ارومیه بررسی شد. برای ارزیابی نتایج از شاخص­های آماری NRMSE و MAPE استفاده شد. به­منظور مدل­سازی پارامتر­های مؤثر در تبخیر از تشت، میزان تأثیر هریک از پارامتر­ها با استفاده از روش تجزیه به مؤلفه­های اصلی از طریق مقادیر همبستگی پارامتر­ها با میزان تبخیر از تشت محاسبه گردید. نتایج نشان داد در بین متغیرهای هواشناسی موردبررسی، دما بیشترین و سرعت باد و بارش کمترین تأثیر را در مدل­سازی دارند. همچنین در بین روش­های تجربی، روش جنسن-­هیز دارای بالاترین دقت بود. علاوه بر این، در بین روش­های داده­کاوی نیز روش SVR در ایستگاه­های تبریز، سراب و هریس و روش GPR در ایستگاه­های بستان­آباد و مراغه در مقایسه با سایر روش­ها دقت بالاتری داشتند. به­طور کلی در تمام ایستگاه­ها دقت بهترین سناریوی روش­های داده­کاوی بالاتر از بهترین روش تجربی بود. در شرایط محدودیت داده نیز روش جنسن­-هیز دقت مطلوبی داشت. همچنین، علی­رغم دقت پایین روش IBK نسبت به سایر روش­های داده­کاوی، این روش با متغیر­های ورودی کمتری به بالاترین دقت خود در مدل­سازی تبخیر می­رسد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Evaluation of Data Mining Methods and Experimental Temperature-Radiation-Based Models in Estimating Evaporation from the Pan (Case Study: East of Urmia Lake)

نویسندگان [English]

  • vahid Mouneskhah 1
  • saeid samadianfard 2
  • MOEIN HADI 3
1 Ph. D Candidate of Irrigation and Drainage, Department of Water Engineering, Tabriz University, Tabriz, Iran.
2 Associate Professor, Department of Water Engineering, Tabriz University, Tabriz, Iran
3 Ph. D Candidate of Irrigation and Drainage, Department of Water Engineering, Tabriz University, Tabriz, Iran.
چکیده [English]

Evaporation from the pan has an effective role in water resources management. But due to the interaction of meteorological variables in the calculation of evaporation, several nonlinear relationships have been presented that their efficiency is arguable according to the climatic conditions of each region. Therefore, in the present study, the capabilities of temperature-radiation-based empirical equations and data mining methods of support vector regression (SVR), Gaussian process regression (GPR) and nearest neighborhood (IBK) were investigated under 10 different scenarios resulting from the combination of meteorological factors in estimating and predicting the evaporation amounts in 5 selected stations in the east of Urmia Lake basin. NRMSE and MAPE statistical indicators were used to evaluate the results. In order to model the effective parameters on pan evaporation, the effect of each parameter was calculated using the principal component analysis through the correlation values of parameters with the pan evaporation rate. The results showed that among the implemented meteorological parameters, temperature have the maximum impact and wind speed and precipitation have the minimum impacts on modeling process. Also, among the empirical methods, the Jensen-Haise method had the highest accuracy. Moreover, among the data mining methods, the SVR in Tabriz, Sarab, and Harris stations and GPR in Bostanabad and Maragheh stations had higher accuracies as compared to the others. In general, in all the studied stations, the accuracy of the best data mining scenario was higher than the best empirical method. Also, in terms of data limitation, the Jensen-Haise method had suitable accuracy. Also, despite the low accuracy of the IBK method compared to other data mining methods, this method reachs to its highest accuracy rates with the lowest input variable.

کلیدواژه‌ها [English]

  • Data Mining
  • Jensen-Haise
  • modeling
  • pan evaporation
  • temperature
Abtew W. (2001). Evaporation estimation for Lake Okeechobee in south Florida. Journal of Irrigation and Drainage Engineering, 127, 140-147.
Akbarzadeh M.S. H., Haghighatjou P. and Bagheri M.H. (2015). Estimates of evaporation from surface water bodies with SEBAL Algorithm using remote sensing techniques (case study: Chahnimeh’s Fresh Water Reservoirs of Sistan). Iranian Journal of Irrigation and Drainage, 3(9), 510-521. (In Farsi)
Bahmani R., Radmanesh F., Islamian S.S. and Parham GH. (2013). Reservoir evaporation trend analysis and its prediction using time series. Journal of Irrigation Sciences and Engineering, 36(3), 67-80. (In Farsi)
Boser B.E., Guyon I.M. and Vapnik V.N. (1992). A training algorithm for optimal margin classifiers. In D.Haussler, editor, 5th Annual ACM Workshop on COLT, Pittsburgh, PA, pp. 144-152.
Chow V. T., Maidment D. R. and Mays L.W. (1988). Applied hydrology. McGraw hill, Newyork, 570 p.
Cohen S., Ianetz A. and Stanhill G. (2002). Evaporative climate changes at bet Dagon, Israel, 1964-1998, Agricultural and Forest Meteorology, 111, 83-91.
Coulomb C.V., legesse D., Gasse F., Travi Y. and Chernet T. (2001). Lake evaporation estimates in tropical Africal (Lake Ziway, Ethiopia). Journal of Hydrology, 245, 1-18.
Dalkilic Y, Okkan U and Baykan N. (2014). Comparison of different ANN approaches in daily pan evaporation prediction. Journal of Water Resource and Protection, 6(4), 319-326.
Fallahi M.R., Varvani H. and Goliyan S. (2012). Precipitation forecasting using regression tree model to flood control. 5th national conference on watershed & soil and water management, Kerman, Iran. (In Farsi)
Gavin H. and Agnew C. A. (2004). Modelling actual reference and equilibrium evaporation from a temperate wet grassland. Hydrological Processes, 18, 229-246.
Ghahreman N. and Gharehkhani A. (2011). Evaluation of random time series models in estimating pan evaporation (case study: Shiraz station). Journal of Water Research in Agriculture, 25(1), 75-81.
Gundekar H. G., Khodke U. M. and Sarkar S. (2008). Evaluation of pan coefficient for reference crop evapotranspiration for semi-arid region. Irrigation Science, 26, 169-175.
Hassan M. (2013). Evaporation estimation for Lake Nasser based on remote sensing technology. Ain Shams Engineering Journal, 4, 593-604.
Khalili Naft Chali A., Khashei Siuki A. and Shahidi A. (2017). Compare KNN and M5 decision tree models in anticipation of evaporation and comparison with empirical equations (Case Study of Birjand). Iranian Journal of Irrigation & Drainage, 11(3), 356-366.
Kuss M. (2006). Gaussian process models for robust regression, classification, and reinforcement learning. Ph. D. dissertation, Technische Universität Darmstadt, Darmstadt, Germany.
Majidi M., Alizadeh A., FaridHosseini A. and Vazifedoust M, (2014). Lake and reservoir evaporation: energy balance estimations, evaluation of combination and radiation- temperature methods. Iranian Journal of Irrigation and Drainage, 3(8), 602-615. (In Farsi)
McGuinness J.L., Bordn, E.F. (1972). A comparson of lysimeterderived potential evapotranspiration with computed values. Technical Bulletin 1452, US Department of Agriculture Agricultural Research Service, Washington, DC.
Mouneskhah V., Majnooni-Heris A. and Fakheri-Fard A. (2018). Evaluation and calibration of empirical relationships for estimating evaporation from free water levels in Urmia Lake Basin. Iranian Journal of Irrigation and Drainage, 5(12), 1281-1291. (In Farsi)
Qasem S., Samadianfard S., Kheshtgar S., Jarhan S., Kisi O., Shamshirband SH. and Wing-Chau K. (2019). Modeling monthly pan evaporation using wavelet support vector regression and wavelet artificial neural networks in arid and humid climates. Engineering Applications of Computational Fluid Mechanics, 13(1), 177-187.
Rosenberry D.O., Winter T.C., Buso D.C., and Likens G.E. (2007). Comparison of 15 evaporation methods applied to a small mountain lake in the northeastern USA. Journal of Hydrology, 340, 149–166.
Samadianfard S., Hashemi S., and Izadyar M. (2018). Estimation of daily pan evaporation by using machine learning methods. Iranian Journal of Irrigation and Drainage, 4(12), 1004-1015. (In Farsi)
Shabani S., Samadianfard S., Sattari M.T., Mosavi A., Shamshirband Sh., Kmet T. and Annamaria R. (2020). Modeling pan evaporation using gaussian process regression k-nearest neighbors random forest and support vector machines; comparative analysis. Atmosphere, 11(66), 1-17.
Shadmani M. and  Marofi S. (2011). Comparison of some methods for estimation of daily pan evaporation: case study in Kerman Region. Journal of Science and Technology of Agriculture and Natural Resources, 15(55), 69-83. (In Farsi)
Sharifazari S. and Araghinejad S. (2013). Develop a non-parametric model to simulate monthly hydrological data. Water and Irrigation Management, 3(1), 83-95. (In Farsi)
Singh D., Ganju A. and Singh A. (2005). Weather prediction using nearest-neighbor model. Current science, 88, 8-25.
Singh A. K., Tripathy R., and Chopra U. K. (2008). Evaluation of CERESWheat and CropSystmodels for water-nitrogen interactions in wheat crop. Agricultural Water Management, 95, 776-786.
Sun Z., Wei B., Su W., Shen W., Wang C., You D and Liu Z. (2011). Evapotranspiration estimation based on the SEBAL model in the Nansi Lake Wetland of China. Mathematical and Computer Modelling, 54(3), 1086-1092.
Tabari H., Marufi S., and Sabziparvar A.A. (2010). Estimation of daily pan evaporation using artificial neural network and multivariate non-linear regression. Irrigation Science, 28(3), 399-406.
Terzi O. (2011). Modeling of daily pan evaporation of Lake Egirdir using data-driven techniques. International symposium on innovations in intelligent systems and Applications, Istanbul, Turkey, pp. 320-324.
Vapnik, V.N. (1995). The Nature of Statistical Learning Theory. Springer, New York. 314 pp.
Vapnik, V.N. (1998). Statistical Learning Theory. Wiley, New York. 736 pp.
Wu X., Kumar V., Quinlan J.R., Ghosh J., Yang Q., Motoda H., McLachlan G.J., Ng A., Liu B. and Philip S.Y. (2008). Top 10 algorithms in data mining. Knowledge and Information Systems, 14, 1–37.