ارایه تکنیک پیش بینی غیر- نظارت شونده در برآورد تبخیر-تعرق گیاه مرجع

نوع مقاله: مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری آبیاری و زهکشی/ دانشکده کشاورزی، دانشگاه فردوسی مشهد، ایران

2 دانشجوی کارشناسی ارشد آبیاری و زهکشی/دانشکده کشاورزی، دانشگاه فردوسی مشهد، ایران

3 استاد /گروه مهندسی آب، دانشکده کشاورزی، دانشگاه فردوسی مشهد، ایران

4 دانشیار هیدرولوژی، دانشکده منابع طبیعی، گروه احیای مناطق خشک و کوهستانی، دانشگاه تهران، ایران

چکیده

تبخیر-تعرق از اجزاء اصلی چرخه هیدرولوژی است و در تعیین نیاز آبی گیاه، مطالعات بیلان آبی و مدیریت منابع آب نقش مهمی دارد. تاکنون روش‌های مستقیم و غیر مستقیم متعددی برای برآورد تبخیر- تعرق گیاه مرجع ارائه شده است، اما هر یک از این روش‌ها دارای محدودیت‌هایی هستند. به عنوان مثال، از محدودیت‌های روش‌های اندازه‌گیری مستقیم می‌توان به عدم دقت وسایل اندازه‌گیری و مسائل مربوط به مقیاس اشاره کرد، در حالیکه روش‌های غیر مستقیم نظیر معادله پنمن-مانتیث، به پارامترهای اقلیمی روزانه زیادی نیاز دارند. در این تحقیق سعی گردید از روش نگاشت خود-سامان به عنوان یک روش شبکه عصبی مصنوعی غیر نظارت شونده در پیش‌بینی تبخیر-تعرق با حداقل پارامترهای هواشناسی به عنوان ورودی، استفاده گردد. براساس شاخص‌ های ارزیابی خوشه‌ بندی فازی، مقادیر ETo در مشهد به دو خوشه با تبخیر-تعرق کم و زیاد  تقسیم شد که با اقلیم منطقه مطابقت نشان داد. همچنین به منظور ارزیابی کارایی مدل ارائه شده از معیارهای آماری شامل (ریشه میانگین مربعات خطا، ضریب تعیین ومعیار ناش-ساتکلیف) استفاده گردید و نتایج حاصله با برآوردهای حاصل از مدل‌های تجربی مقایسه گردید. نتایج حاصله نشان داد که حتی ساده‌ترین مدل نگاشت خود-سامان با ترکیب متوسط دمای هوا و حداکثر ساعات آفتابی به عنوان ورودی نیز خطای کمتری نسبت به معادلات تجربی دارد.

کلیدواژه‌ها


عنوان مقاله [English]

Using Unsupervised Estimator Technique to Predict Reference Crop Evapotranspiration

نویسندگان [English]

  • F. Farsadnia 1
  • S. Zahmati 2
  • B. Ghahreman 3
  • A.R. Moghaddam Nia 4
1 Ph.D. Student in irrigation and drainage, Department of Water EngineeringCollege of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran.
2 M.Sc. Student, Department of Water Engineering, College of Agriculture
3 Professor, Department of Water Engineering, College of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran
4 Associate Professor of Hydrology, Faculty of Natural Resources, University of Tehran, Karaj, Iran.
چکیده [English]

Evapotranspiration is the main component of hydrologic cycle and has an important role in crop water requirement estimations, water balances studies, and water resource management. There are a lot of direct and indirect methods to estimate reference crop evapotranspiration, but each has some limitations. For example, limitations that can be mentioned for direct measuring are the insufficient precision in measuring devices and the scale problems. An indirect method like Penman-Monteith on the other hand needs a lot of daily climatic parameters. This research tried to use self-organizing maps as an unsupervised artificial neural network method to predict evapotranspiration by minimum meteorological data input. Based on fuzzy clustering indices, evapotranspiration values in the study area, Mashhad plain, are divided into two clusters with low and high ETo coincided with the climate of the area. Also, in order to validate the model, statistical indices containing root mean square error, determination coefficient, and Nash–Sutcliffe model efficiency coefficient are used and the results are compared with the experimental models output. The results showed that even the simplest SOM model which employs mean temperature and maximum sunshine duration as input have less errors compared to the experimental equations.

کلیدواژه‌ها [English]

  • Self-Organizing map
  • FAO-Penman-Monteith equation
  • Crop reference evapotranspiration
  • Mashhad plain
Adeloye AJ, Rustum R and Kariyama ID (2011) Kohonen self-organizing map estimator for the reference crop evapotranspiration. Water Resource Research 47 (8).

Allen RG (1986) A penman for all season. Irrigation and Drainage 122 (4): 348-368.

Allen RG (2001) REF-ET= Refrence evapotranspiration calculation software.

Allen RG, Pereira LS, Rae D and Smith M (1998) Crop evapotranspiration: Guidelines for computing crop water requirements-FAO Irrigation and Drainage Paper 56, Food and Agriculture Organization of the United Nations, Rome.

Bezdek JC (1981) Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum, New York.

Chang FJ, Chang LC, Kao HS and Wu GR (2010) Assessing the effort of meteorological variables for evaporation estimation by self-organizing map neural network. Journal of Hydrology 384:118-129.

Farsadnia F, Rostami Kamrood M, Moghaddam Nia A, Modarres R, Bray MT and Han D, Sadatinejad J (2014) Identification of homogeneous regions for regionalization of watersheds by two-level self-organizing feature maps. Journal of Hydrology 509: 387–397.

Hargreaves GH and Samani ZA (1985) Reference crop evapotranspiration from temperature. Applied Engineering in Agriculture 2: 96–99.

Haykin S (2003) Neural networks: A comprehensive foundation. Fourth Indian Reprint, Pearson Education, Singapore, p. 842.

Herbst M and Casper MC (2008) Towards model evaluation and identification using Self-Organizing Maps. Hydrology and Earth System Sciences 12: 657-667.

Jensen ME, Burman RD and Allen RG (1990) Evapotranspiration and irrigation water requirements. ASCE Manual and Report on Engineering Practice No.7. New York.

Kalteh AM and Berndtsson R (2007) Interpolating monthly precipitation by self-organizing map (SOM) and multilayer perceptron (MLP). Hydrology Science Journal 52: 305–317.

Kohonen T (1982) Self-organized formation of topologically correct feature maps. Biological Cybernetics 43: 59–69.

Kohonen T (2001) Self-Organizing Maps. Springer, Berlin, Germany.

Kumar M, Raghuwanshi NS and Singh R (2011) Artificial neural networks approach in evapotranspiration modeling: a review. Irrigation Science 29(1):11–25.

Kwon SH (1998) Cluster validity index for fuzzy clustering. Electronics Letters 34 (22): 2176–2177.

Ley R, Casper MC, Hellebrand H and Merz R (2011) Catchment classification by runoff behavior with self-organizing maps (SOM). Hydrology and Earth System Sciences 15(9): 2947-2962.

Lin GF and Wu MC (2011) An RBF network with a two-step learning algorithm for developing a reservoir inflow forecasting model. Journal of Hydrology 405 (3-4): 439–450.

Makkink GF (1957) Testing the Penman formula by means of lysimeters. International Journal of Water Engineering 11(3): 277-288.

Monteith JL (1965) The state and movement of water in living organisms. Proc., Evaporation and Environment, XIXth Symp., Soc. For Exp. Biol., Swansea, Cambridge University Press, New York, 205–234.

Mwale FD, Adeloye AJ and Rustum R (2012) Infilling of missing rainfall and streamflow data in the Shire River basin, Malawi – A self-organizing map approach. Physics and Chemistry of the Earth 50: 34–43.

Nash JE and Sutcliffe JV (1970) River flow forecasting through conceptual models part I: A discussion of principles. Journal of Hydrology 10 (3): 282-290.

Penman HL (1948) Natural evaporation from open water, bare soil and grass. Proceedings of the Royal Society of London 193 (1032): 120–146.

Penn BS (2005) Using self-organizing maps to visualize high dimensional data. Computers & Geosciences 31(5): 531–544.

Priestley CHB and Taylor RJ (1972) On the assessment of surface heat flux and evaporation using large-scale parameters, Mon. Weather Rev100 (2): 81–92.

Rustum R, Adeloye AJ and Scholz M (2008) Applying Kohonen Self-Organizing Map as a software sensor to predict biochemical oxygen demand. Water Environment Research 80(1): 32-40.

Rustum R, Adeloye AJ and Simala A (2007) Kohonen self-organizing map (KSOM) extracted features for enhancing MLP-ANN prediction models for BOD5. IAHS-AISH Publication 314: 181–178.

Shuttleworth WJ (1993) Evaporation, in Handbook of Hydrology, edited by Maidment DR, Chapter 4, McGraw Hill, New York.

Turc L (1961) Evaluation des besoins en eau d’irrigation, evapotranspiration potentielle, formule  climatique simplifice et mise a jour. (in French).  Ann. Agron 12:13-49.

Vesanto J, Himberg J, Alhoniemi E and Parhankangas J (2000) SOFM Toolbox for Matlab 5. Technical Report A57. Neural Networks Research Centre, Helsinki University of Technology, Helsinki, Finland.

Wilppu R (1997) The visualization capability of self organizing maps to detect deviation in distribution control. TUCS Technical Report No. 153. Turku Centre for Computer Science, Finland.

Xie XL and Beni G (1991) A validity measure for fuzzy clustering. IEEE Transactions on pattern analysis and machine intelligence 13 (8): 841–847.