نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، تبریز، ایران

2 دانشجوی کارشناسی ارشد، گروه مهندسی آب، دانشکده کشاورزی، دانشگاه تبریز، تبریز، ایران

چکیده

تخمین دقیق تبخیر و تعرق گیاه مرجع در برنامه‌ریزی‌های آبیاری اهمیت ویژه‌ای دارد. همچنین، عدم دسترسی به داده‌های لایسیمتری باعث شده است پژوهش­گران به استفاده از روش‌های غیرمستقیم از جمله روش‌های داده‌محور روی آورند. در پژوهش حاضر، توانایی روش‌های داده‌محور رگرسیون فرآیند گاوسی (GPR)، رگرسیون بردار پشتیبان (SVR) و جنگل تصادفی (RF) در تخمین تبخیر و تعرق گیاه مرجع موردبررسی قرار گرفت. بدین منظور، داده‌های هواشناسی دمای میانگین، سرعت باد، رطوبت نسبی و ساعات آفتابی در بازه زمانی 97-1392 در نه ایستگاه شمالی کشور از جمله آستارا، بندر انزلی، رشت، رامسر، نوشهر، ساری، بندر ترکمن، گرگان، گنبدکاووس جمع‌آوری شد. تبخیر و تعرق محاسبه‌شده با استفاده از روش فائو-پنمن-مونتیث به‌عنوان خروجی‌های هدف در نظر گرفته‌شده و چهار سناریو ترکیبی از پارامترهای هواشناسی برای واسنجی و صحت‌سنجی روش‌های موردمطالعه، مدنظر قرار گرفتند. دقت روش‌های مذکور با استفاده از پارامتر‌های آماری ضریب همبستگی، شاخص پراکندگی و ضریب ویلموت مورد مقایسه قرار گرفت. نتایج نشان داد که مدلGPR4  با شاخص پراکندگی در محدوده 132/0 تا 179/0 در ایستگاه‌های آستارا، بندر انزلی، رشت، رامسر، نوشهر و ساری، مدلSVR4   با شاخص پراکندگی 116/0 تا 120/0 در ایستگاه‌های بندر ترکمن و گنبدکاووس و روش هارگریوز-سامانی با شاخص پراکندگی 509/0 در ایستگاه گرگان برآوردهای به‌مراتب دقیق‌تری از تبخیر و تعرق گیاه مرجع داشته‌اند.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Estimation of Daily Reference Evapotranspiration in Humid Climates Using Data-Driven Methods of Gaussian Process Regression, Support Vector Regression and Random Forest

نویسندگان [English]

  • Saeed Samadianfard 1
  • Mobarak Salarifar 2
  • Sahar Javidan 2
  • Fatemeh Mikaeili 2

1 Assist. Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran

2 M.S student, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran

چکیده [English]

Accurate estimation of reference evapotranspiration has great importance in irrigation scheduling. Moreover, the lack of availability of lysimetric data has led researchers to use indirect methods, including data-driven approaches. In the present study, the ability of Gaussian process regression (GPR), support vector regression (SVR) and random forest (RF) data-driven methods was investigated to estimate the evapotranspiration of the reference plant. For this purpose, meteorological data on average temperature, wind speed, relative humidity and sunny hours in the period 2013-18 were collected in nine northern stations of Iran including Astara, Bandar Anzali, Rasht, Ramsar, Nowshahr, Sari, Turkmen port, Gorgan, and Gonbad Kavous. Evapotranspiration calculated using FAO-Penman-Montith method was considered as the target output and four combined scenarios of meteorological parameters were considered to calibrate and validate the studied methods. The accuracy of the mentioned methods was compared using the statistical parameters of correlation coefficient, scatter index, and Wilmott’s coefficient. The results showed that GPR4 model with scatter index in the range of 0.132 to 0.179 in Astara, Bandar Anzali, Rasht, Ramsar, Nowshahr and Sari stations, SVR4 model with dispersion index of 0.116 to 0.120 in Turkmen and Gonbad Kavous stations and the Hargreaves-Samani method with a scatter index of 0.509 at Gorgan station had much more accurate estimates of the evapotranspiration of the reference plant.

کلیدواژه‌ها [English]

  • Data Driven Methods
  • FAO Penman–Monteith Method
  • Hargreaves-Samani Equation
  • North of Iran
  • Reference Evapotranspiration
Allen R. G., Pereira L. S., Raes D. and M. Smith. (1998). Crop Evapotranspiration. Guidelines for Computing Crop Water Requirements. Irrigation and Drainage Paper No. 56, FAO, Rome, Italy, 300pp.
Azimi A., Rangzan K., Kaboulizade M. and Khoramian M. (2016). Estimating of evapotranspiration using remote sensing, artificial neural network and comparison with the experimental method (Penman-Monteith-FAO). J. R. S. GIS Nat. Resour., 6(4), 61-75.
Basak D., Pal S. and Patranabis D. C. (2007). Support vector regression. Neu. Inform. Process., 11, 203-225.
Behmanesh J., Azadtala Tape N., Montaseri M. and Besharat S. (2014). Evaluation of linear and nonlinear series models in predicting evatranspiration of reference plant in Urimia synoptic station. J. Wat. Res. Agri. B., 28(1), 85-96.
Boser B. E., Guyon I. M. and Vapnik V. N. (1992). A training algorithm for optimal margin classifiers. In Haussler D., Editor, 5th Annual ACM workshop on COLT, pages 144-152, Pittsburgh, PA.
Breiman L. (2001). Application and analysis of random forests and machine learning. J. Wat. Manag., 15(1(, 5-32.
Carter C. and Liang S. (2019). Evaluation of ten machine learning methods for estimating terrestrial evapotranspiration from remote sensing. Int J. Appl. Earth Obs. Geoinform., 78, 86-92.
Cui N., Feng Y., Gong D., Zhang Q. and Zhao L. (2017). Evaluation of random forests and generalized regression neural networks for daily reference evapotranspiration modelling. Agri. Wat. Manag., 193, 163-173.
Granata F. (2019). Evapotranspiration evaluation models based on machine learning algorithms—A comparative study. Agri. Wat. Manag., 217, 303-315.
Hashemi S., Izadyar M., and Samadianfard S. (2019). Comparion of radiant basis methods in estimating evapotranspiration. 4th International congress on natural resources development, agriculture, environment and tourism of Iran. Tabriz University of Islamic Art In collaboration with Shiraz University and Yasuj University.
Huang J., Chen H. and McBean E. (2020). Partitioning of daily evapotranspiration using a modified shuttleworthwallace model, random Forest and support vector regression, for a cabbage farmland. Agri. Wat. Manag., 228, 1-12.
Kaviyani A., Bahmanabadi B., Daneshkararaste P. and Nazari R. (2018). Estimation of actual evatranspiration of crops using energy balance algorithms in Qazvin plain. Echo. Hydrol., 5(4), 1103-1117.
Khorsand Movaghar M. and Sima S. (2019). Comparison of the remote sensing based-energy balance models for estimating evaporation from salin lakes. J. Geos. Inform. Technol., 2, 155-175.
Khoshhal J., Zareh H. and Joshani A. (2015). Different methods for estimating reference evatraspiration by FAO evaporation pan method in the east and southeast of the country. Quart. J. Nat. Geogr., 8(28), 1-16.
Moqbeli Dameneh M. and Sanaeinejad S.H. (2018). Estimate of potential evapotranspiration in Freiman using the priestileytaylor method and remote sensing technique. R. S. GIS Nat. Resour., 3, 72-84.
Najafi P. (2006). Application of Hargreaves of Samani and Jensen – hayes modes in the evaluation of alfalfa evatranspiration in Isfahan. Ecol. Crop., 2(5), 57-68.
Saghebian M., and Roushangar K. (2019). Prediction of total and bedform roughness coefficient in alluvial channels based on experimental data via Gaussian process regression method. Iran. J. Irrig. Drain., 2, 437-499.
Samadianfard S. and Panahi S. (2018). Estimating daily reference evapotranspiration using data mining methods of support vector regression and M5 model tree. J. Watershed Manag. Res., 18, 157-167.
Saremi M. and Farhadi Bansouleh B. (2015). Determination of effective parameterse in estimating reference crop evapotranspiration using artificial neural networks. Iran. J. Irrig. Drain., 4, 614-623.
Shabani A., Sepaskhah A. R., Bahrami M. and Razzaghi F. (2017). Combined application of artificial neural network and computational methods to estimate the reference evapotranspiration. Iran. Wat. Resour. Res., 1, 152-162.
Sharifian H., Dehgani, A. and Karimi rad A. (2012). Presentation of correction coefficient for Hargreaves Samsni methods as estimating evatranspiration of reference plant (case study of Gorgan synoptic station). Soil Wat. Conserv. Res. Agri. Sci. Nat. Resour., 19(3), 227-236.
Siasar H. and Honar T. (2019). Application of support vector machine, CHAID and random forest models, in estimated daily reference evapotranspiration in northern Sistan and Baluchestan Province. Iran. J. Irrig. Drain., 2, 378-388.
Trajkovic S. (2007). Hargreaves versus Penman-Monteith under humid conditions. J. Irrig. Drain. Eng., 133(1), 38-42.
Wang Y. M., Traore S. and Kerh T. (2008). Neural network approach for estimating reference evapotranspiration from limited climatic data in Burkina Faso. WSEAS Transact. Comput. )7(, 704-713.
Izadyar M., Hashemi S. and Samadianfard S. (2018). Estimation of refrence crop evapotranspiration by using basal temperature and mass transfer methods. 4th International congress on Natural Resources Development, Agriculture, Environment and Tourism of Iran, Tabriz University of Islamic Art in collaboration with Shiraz University and Yasuj University.