مدل سازی تبخیرتعرق با استفاده از رگرسیون خطی، غیرخطی و شبکه عصبی مصنوعی در گلخانه (مطالعه موردی گیاه مرجع، خیار و گوجه‌فرنگی)

نوع مقاله : مقالات پژوهشی

نویسندگان

• وحید رضا وردی نژاد
• مریم شبانیان اصل
• سینا بشارت

دانشگاه ارومیه

https://doi.org/10.22067/jsw.v0i0.31432

چکیده

در این مطالعه تبخیرتعرق روزانه گیاه مرجع، گوجه فرنگی و خیار گلخانه ای به روش لایسیمتری در منطقه ارومیه اندازه گیری شد. برای مدل-سازی تبخیرتعرق در گلخانه، انواع مدل های رگرسیون های خطی، غیرخطی و شبکه های عصبی مصنوعی در نظر گرفته شد. برای این منظور پارامترهای اقلیمی مؤثر بر فرایند تبخیرتعرق شامل دما (T)، رطوبت نسبی (RH)، فشار هوا (P)، کمبود فشار بخار اشباع (VPD)، تشعشع داخل گلخانه (SR)، تعداد روز پس از کشت (N) اندازه گیری و در نظر گرفته شدند. براساس نتایج، تابع نمایی سه متغیره از VPD، RH و SR با RMSE برابر 378/0 میلیمتر بر روز، دقیق ترین مدل رگرسیون در تخمین تبخیرتعرق مرجع به دست آمد. RMSE مدل بهینه شبکه عصبی مصنوعی در تخمین تبخیرتعرق مرجع برای داده های آزمایش و آزمون به ترتیب 089/0 و 364/0 میلیمتر بر روز به دست آمد. در تخمین تبخیرتعرق خیار، عملکرد مدل های لگاریتمی و نمایی به ویژه در تعداد متغیر مستقل زیاد، مناسب بود و دقیق ترین مدل رگرسیون مربوط به تابع نمایی با پنج متغیر N، VPD، T، RH و SR با RMSE برابر با 353/0 میلیمتر بر روز به دست آمد. همچنین در تخمین تبخیرتعرق گوجه فرنگی، دقیق ترین عملکرد مدلهای رگرسیون برای تابع نمایی چهار متغیره از N، VPD، RH و SR با RMSE برابر 329/0 میلی‌متر بر روز به دست آمد. بهترین عملکرد شبکه عصبی مصنوعی برای تخمین تبخیرتعرق هر دو محصول خیار و گوجه‌فرنگی، با پنج پارامتر ورودی VPD، T، N، RH و SR به دست آمد. مقادیر RMSE داده‌های آزمون تبخیرتعرق خیار و گوجه‌فرنگی به ترتیب 24/0 و 26/0 میلی‌متر بر روز به دست آمد که نشان دهنده‌ی عملکرد دقیق تر شبکه های عصبی در مقایسه با رگرسیون خطی و غیرخطی می باشد.

کلیدواژه‌ها

• ارزیابی عملکرد
• رگرسیون چندمتغیره
• متغیرهای هواشناسی

20.1001.1.20084757.1395.30.5.29.7

عنوان مقاله [English]

Evapotranspiration Modeling by Linear, Nonlinear Regression and Artificial Neural Network in Greenhouse (Case study Reference Crop, Cucumber and Tomato)

نویسندگان [English]

• vahid Rezaverdinejad
• M. Shabanialasl
• S. Besharat

چکیده [English]

Introduction: Greenhouse cultivation is a steadily developing agricultural sector throughout the world. In addition, it is known that water is a major issue almost all part of the world especially for countries which have insufficient water source. With this great expansion of greenhouse cultivation, the need of appropriate irrigation management has a great importance. Accurate determination of irrigation scheduling (irrigation timing and frequency) is one of the main factors in achieving high yields and avoiding loss of quality in greenhouse tomato and cucumber. To do this, it is fundamental to know the crop water requirements or real evapotranspiration. Accurate estimation on crop water requirement is needed to avoid the excess or deficit water application, with consequent impacts on nutrient availability for plants. This can be done by using appropriate method to determine the crop evapotranspiration (ETc). In greenhouse cultivation, crop transpiration is the most important energy dissipation mechanisms that influence ETc rate. There are a large number of literatures on methods to estimate ETc in greenhouses. ETc can be measured or estimated by direct or indirect methods. The most common direct method estimates ETc from measurements with weighing lysimeters. Thisalsoincludes the evaporation measuring equipment, class A pan, Piche atmometer and modified atmometer. Indirect method includes the measurement of net radiation, temperature, relative humidity, and air vapour pressure deficit. A large number of models have been developed from these measurements to estimate ETc. Due to the fast development of under greenhouse cultivation all around the world, the needs of information on how it affects ETc in greenhouses has to be known and summarized. The existing models for ETc calculation have to be studied to know whether it is reliable for greenhouse climate (hereafter, microclimate) or not. Regression and artificial neural network models are two important models to estimate ETc in greenhouse. The inputs of these models are net radiation, temperature, day after planting and air vapour pressure deficit (or relative humidity).
Materials and Methods: In this study, daily ETc of reference crop, greenhouse tomato and cucumber crops were measured using lysimeter method in Urmia region. Several linear, nonlinear regressions and artificial neural networks were considered for ETc modelling in greenhouse. For this purpose, the effective meteorological parameters on ETc process includes: air temperature (T), air humidity (RH), air pressure (P), air vapour pressure deficit (VPD), day after planting (N) and greenhouse net radiation (SR) were considered and measured. According to the goodness of fit, different models of artificial neural networks and regression were compared and evaluated. Furthermore, based on partial derivatives of regression models, sensitivity analysis was conducted. The accuracy and performance of the employed models was judged by ten statistical indices namely root mean square error (RMSE), normalized root mean square error (NRMSE) and coefficient of determination (R2).
Results and Discussion: Based on the results, the most accurate regression model to reference ETc prediction was obtained three variables exponential function of VPD, RH and SR with RMSE=0.378 mm day-1. The RMSE of optimal artificial neural network to reference ET prediction for train and test data sets were obtained 0.089 and 0.365 mm day-1, respectively. The performance of logarithmic and exponential functions to prediction of cucumber ETc were proper, with high dependent variables especially, and the most accurate regression model to cucumber ET prediction was obtained for exponential function of five variables: VPD, N, T, RH and SR with RMSE=0.353 mm day-1. In addition, for tomato ET prediction, the most accurate regression model was obtained for exponential function of four variables: VPD, N, RH and SR with RMSE= 0.329 mm day-1. The best performance of artificial neural network for ET prediction of cucumber and tomato were obtained with five inputs include: VPD, N, T, RH and SR. The RMSE values of test data sets for cucumber and tomato ET were obtained 0.24 and 0.26 mm day-1. Moreover, the sensitivity analysis results showed that VPD is the most sensitive parameter on ETc.
Conclusion: The greenhouse industry has expanded across many parts of the word and the need of information on a reliable ETc method especially by indirect method is crucial. In this research, the artificial neural network models indicated good performance compared with linear and nonlinear regressions. The evaluated method could be used for scheduling irrigation of greenhouse tomato and cucumber.

کلیدواژه‌ها [English]

• Performance Evaluation
• Multivariable Regression
• Meteorological Variables

مراجع

1- Abedi-Koupai J., Eslamian S.S. and Zareiyan M.J. 2011. Measurement and modeling of water requirement and crop coefficient for cucumber, tomato and pepper using microlysimeter in greenhouse. journal of science and technology of greenhouse culture, 2(7): 51-64. (in Persian with English abstract (

2- Abghari H., Ahmadi H., Besharat S. and Rezaverdinejad V. 2012. Prediction of daily pan evaporation using Wavelet Neural Networks, Water Resources Management, 26: 3639-3652.

3- Allen R.G., Pereira L.S., Raes D. and Smith M. 1998. Crop evapotranspiration, guidelines for computing crop water requirements. Irrigation and Drainage Paper 56, FAO, Rome, Italy, 300 pp.

4- Alizadeh A. 2004. Water, soil and plant relationship. Ferdowsi University of Mashhad, Mashhad, 470 pp.

5- Amiri M.J., Abedi-Koupai J. and Eslamian S.S. 2011. Evaluation of the performance of evaporation pans in greenhouse environment. journal of science and technology of greenhouse culture, 2(5): 63-73. (in Persian with English abstract)

6- Assari M., Kouchakzadeh M., Shahabifar M. and Bayat K. 2009. Estimation of reference evapotranspiration in greenhouse by artificial neural network. Journal of water and soil conservation, 16(1): 107-121. (in Persian with English abstract)

7- Babtista J.F., Bailey B.J. and Meneses J.F. 2005. Measuring and modeling transpiration versus evapotranspiration of a tomato crop grown on soil in a Mediterranean greenhouse. Acta Horticulturae, 691: 313 – 319.

8- Bayat Varkeshi M., Zare Abyaneh H., Marofi S., Sabziparvar A.A. and Soltani F. 2009. Simulation of reference evapotranspiration using Artificial neural method and empirical methods and comparison with experimental lysimeter data in cold semi-arid climate of Hamedan. Journal of water and soil conservation, 16(4): 79-100. (in Persian with English abstract)

9- Ehsani M., Hayati B., Dashty G., Gahremanzadeh M. and Hossenzad J. 2011. Water economic value estimation in Barley production at Qazvin plane irrigation network. Water and soil science (Agricultural science), 22 (1): 187-200. (in Persian with English abstract)

10- Fathalian F., Moazenzadeh R. and Nouri Emamzadei M.R. 2009. Evaluation and prediction of greenhouse Cucumber evapotranspiration at different growth stages. Journal of water and soil, 23(4): 16-27. (in Persian with English abstract)

11- Fathi P. and Koochakzadeh M. 2004. Estimation of cucumber evapotranspiration in greenhouse by Artificial Neural Network. Journal of water and soil science, 18 (2): 212-221. (in Persian with English abstract)

12- Fazilah W.F. 2009. Evapotranspiration models in greenhouse. M.Sc. thesis, Wageningen University, the Netherlands.

13- Fu G. 2005. Modeling water availability and its response to climate change for the Spokane river watershed. PhD dissertation. Washington state university, Department of Biological Systems Engineering.

14- Harmanto V.M., Salokhe M.S. and Babel H.J. 2005. Water requirement of drip irrigated tomatoes grown in greenhouse in tropical environment. Agricultural water management, 71: 225-242.

15- Heydari N., Entesari M.R., Kheyrabi J., Farshi A.A., Vaziri ZH. and Alaei M. 2006. Water use efficiency in greenhouse production. Iranian National Committee on Irrigation and Drainage (IRNCID). 180 pp. (in Persian with English abstract)

16- Jain S.K., Das A. and Srivastava D.K. 1999. Application of ANN for reservoir inflow prediction and operation. Journal of water resources planning and management, 125(5): 263-271.

17- Karimi S., Kisi O., Shiri J. and Makarynskyy O. 2013. Neuro-fuzzy and neural network techniques for forecasting sea level in Darwin Harbor, Australia. Computers and Geosciences, 52: 50-59.

18- Karimi N., Nazemi A.H., Sadraddini A.A., farsadizadeh D., Hoseinzade Dalir A. and Dehghani F. 2007. Water requirement of greemhouse grown cucumber in Yazd climate. Agricultural research: soil water and plant, 7 (4): 151-160. (in Persian with English abstract)

19- McCuen R.H. 1974. A sensitivity and error analysis of procedures used for estimating evapotranspiration. Water Resources Bulletin, 10(3): 486-498.

20- Mujahed H. 2007. Estimation of crop water requirement for Cucumber (Cucumis sativus) grown in green houses. M.Sc. thesis, College of Graduate Studies and Academic Research. Hebron University, Palestine.

21- Rezaverdinejad V., Rezaie H., Ababaie B., Ahmadi H. and Behmanesh J. 2012. Application SWAP agrohydrological model to predict crop yield, soil water and solute transport with shallow groundwater condition. 8th International Soil Science Congress Çeme-Izmir, Turkey.

22- Zare Abyaneh H., Bayat Varkeshi M., Marofi S. and Amiri Chayjan R. 2010. evaluation of artificial neural network and adaptive neuro fuzzy inference system in decreasing of reference evapotranspiration parameters. Journal of water and soil, 24 (2): 297-305. (in Persian with English abstract)