پیش‌بینی تلفات تبخیرو بادبردگی در سامانه‌های آبیاری بارانی با استفاده از شبکه‌های عصبی مصنوعی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه آب و خاک، دانشکده کشاورزی، دانشگاه صنعتی شاهرود

2 دپارتمان مهندسی بیوسیستم، دانشگاه ایالتی واشنگتن، امریکا

چکیده

تلفات تبخیر و بادبردگی (WDEL) در سامانه‌های آبیاری بارانی عاملی است که دریافت آب در نقاط مختلف مزرعه را دستخوش تغییر می‌کند و باعث کاهش یکنواختی پاشش می‌گردد. لذا پیش‌بینی این تلفات می‌تواند نقش مهمی در بهبود عملکرد آنها ایفا نماید. در این پژوهش از شبکه‌های عصبی‌مصنوعی برای برآورد ساعتی راندمان دبی آب‌پاش (SDE) استفاده شده‌است که این پارامتر، خود وابسته به تلفات بادبردگی و تبخیر است. پارامترهای موثر در برآورد WDEL که به عنوان ورودی شبکه عصبی مدنظر قرارگرفت با محاسبه ضرایب همبستگی رتبه‌بندی اسپرمن انتخاب شدند. بر این اساس، سرعت باد، دما، رطوبت نسبی و تبخیر- تعرق مرجع به عنوان ورودی و SDE به عنوان خروجی مدل مدنظر قرارگرفت. ارزیابی عملکرد مدل شبکه عصبی ایجاد شده با استفاده از 1024 داده بدست آمده توسط ساختار نواری برآورد WDEL صورت گرفت. مدل شبکه عصبی پیشنهادی که یک مدل 1-16-19-4 با تابع آموزش مبتنی بر تنظیم بیزین است پس از بررسی 3780 مدل متفاوت انتخاب گردید. نتایج نشان داد که مدل توسعه داده‌شده می‌تواند با دقت بالایی مقادیر ساعتی SDE را برآورد کند (19/1 =MAPE، 6/1 % =RMSE، 84/0= R) و به‌عنوان یک روش قابل اتکاء در ارزیابی عملکرد سامانه‌های آبیاری بارانی استفاده شود.

کلیدواژه‌ها


عنوان مقاله [English]

Prediction of wind drift and evaporation losses in sprinkler irrigation systems using artificial neural networks

نویسندگان [English]

  • Seyed Iman Saedi 1
  • Troy R. Peters 2
1 Department of water and soil, Shahrood University of Technology, Shahrood, Iran
2 Dept. of Biological Systems Engineering, Washington State University, Pullman, WA, USA
چکیده [English]

Wind drift and evaporation loss (WDEL) in sprinkler irrigation systems are a factor that affects the water delivery in a field and reduces the uniformity of spraying. So, predicting these losses can play an important role in improving the performance of them. In this study, artificial neural networks (ANNs) have been used to estimate the hourly sprinkler discharge efficiency (SDE), which, in turn, is dependent on WDEL. The effective parameters in estimating WDEL, which were considered as model inputs, were selected by calculating Spearman rank correlation coefficients. Accordingly, wind speed, temperature, relative humidity, and reference evapotranspiration were considered as model inputs, whereas SDE was considered as model output. The performance evaluation of the developed neural network model was done using 1024 real data obtained by the Strip structure for estimating WDEL. The proposed model, which was a 4-19-16-1 model with a Bayesian regularization training function, was selected upon testing 3780 different neural networks. The results of this study showed that the developed model can accurately estimate the hourly values of sprinkler discharge efficiency (R= 0.84, RMSE= 1.6%, MAPE= 1.19) and can be used as a reliable method in evaluating the performance of sprinkler irrigation systems.

کلیدواژه‌ها [English]

  • ANN
  • Irrigation Uniformity
  • Sprinkler
  • WDEL
روحانی، ع.، ساعدی، س.ا.، گرایلو، ه. و آق خانی، م.ح. 1394. پیش بینی حجم، سطح جانبی و ضریب کرویت انار با استفاده از شبکه عصبی مصنوعی MLP. نشریه ماشین های کشاورزی. 5 (2): 292-301.
ساعدی، ا.، علیمردانی، ر. و موسی زاده، ح. 1397. پیش بینی میزان تابش خورشیدی با استفاده از دمای روزانه و شبکه های عصبی مصنوعی در اقلیم های مختلف آب و هوایی. نشریه ماشین های کشاورزی. 8 (1): 197-211.
Abo-Ghobar, H. M.  1992. Losses from low-pressure center-pivot irrigation systems in a desert climate as affected by nozzle height.  Agric. Water Manage., 21(1): 23–32.
Al-Ghobari, H.M., El-Marazky, M.S., Dewidar, A.Z. and Mattar, M.A. 2018. Prediction of wind drift and evaporation losses from sprinkler irrigation using neural network and multiple regression techniques. Agric. Wat. Manage. 195: 211–221.
Bauder, T. A., Andales, A. A., and Waskom, R. M. 2008. Nitrogen and Irrigation Management, Colorado State University Extension.
Burt, C. M., Clemmens, A. J., Strelkoff, T. S., Solomon, K. H., Bliesner, R. D., Hardy, L. A., ... and Eisenhauer, D. E. 1997. Irrigation performance measures: efficiency and uniformity. J. Irrig. and Drain. Eng.., 123(6): 423–442.
Baiamonte, G., and Baiamonte, G. 2019. Using rotating sprinkler guns in centre-pivot irrigation systems. Irrig. Drain., 68(5): 893–908.
Cavero, J., Medina, E. T., Puig, M., and Martínez-Cob, A. 2009. Sprinkler irrigation changes maize canopy microclimate and crop water status, transpiration, and temperature. Agron. J., 101(4): 854–864.
Dumitru, C., and Maria, V. 2013. Advantages and Disadvantages of Using Neural Networks for Predictions. Ovidius University Annals, Series Economic Sciences, 13(1).
Faci, J. M., Salvador, R., Playán, E., and Sourell, H. 2001. Comparison of fixed and rotating spray plate sprinklers. J. Irrig. and Drain. Eng., 127(4): 224–233.
Keller, J., and Bliesner, R. D. 1990. Sprinkle and trickle irrigation. Van Nostrand Reinhold.
King, B. A., Dungan, R. S., and Bjorneberg, D. L. 2012. Evaluation of center pivot sprinkler wind drift and evaporation loss. In 2012 Dallas, Texas, July 29-August 1, 2012 (p. 1). American Society of Agricultural and Biological Engineers.
King, B. A., Bjorneberg, D. L., Trout, T. J., Mateos, L., Araujo, D. F., and Costa, R. N. 2015. Estimation of furrow irrigation sediment loss using an artificial neural network. J. Irrig. Drain. Eng., 142(1), 04015031.
Kohl, K. D., R. A. Kohl and D. W. DeBoer.  1987. Measurement of low pressure sprinkler loss. Trans. ASABE, 30(4):1071–1074.
Lamm, F. R., O'Brien, D. M., and Rogers, D. H. 2015. Economic comparison of subsurface drip and center pivot sprinkler irrigation using spreadsheet software. Appl. Eng. Agric., 31(6): 929.
Lazarovitch, N., Poulton, M., Furman, A., and Warrick, A. W. 2009. Water distribution under trickle irrigation predicted using artificial neural networks. J. Eng. Math., 64(2): 207–218.
Liu, J., Liu, X., Zhu, X., and Yuan, S. 2016. Droplet characterisation of a complete fluidic sprinkler with different nozzle dimensions. Biosyst. Eng., 148: 90–100.
Luz, P. B., and Heermann, D. 2005. A statistical approach to estimating runoff in center pivot irrigation with crust conditions. Agric. Water Manage.,72(1): 33–46.
Marey, S.A., El Marazky, M.S.A., Aboukarima, A.M. 2018. Prediction of wind drift and evaporation losses of a sprinkler irrigation system using principal component analysis and artificial neural network technique. Water Sa 44: 338–347.
Maroufpoor, E., Sanikhani, H., Emamgholizadeh, S., Kisi, O. 2018. Estimation of Wind Drift and Evaporation Losses from Sprinkler Irrigation systemS by Different Data-Driven Methods. Irrig. and Drain. 67: 222–232.
Mattar, M. A., Alazba, A. A., and El-Abedin, T. Z. 2015. Forecasting furrow irrigation infiltration using artificial neural networks. Agric. Water Manage.: 148, 63–71.
Mokeba, M. L., Salt, D. W., Lee, B. E., and Ford, M. G. 1997. Simulating the dynamics of spray droplets in the atmosphere using ballistic and random-walk models combined. J. Wind Eng. Ind. Aerod., 67: 923–933.
Molle, B., Tomas, S., Hendawi, M., and Granier, J. 2012. Evaporation and wind drift losses during sprinkler irrigation influenced by droplet size distribution. Irrig. and Drain., 61(2): 240–250.
Omid M, Mahmoudi A, Omid MH. 2010. Development of pistachio sorting system using principal component analysis (PCA) assisted artificial neural network (ANN) of impact acoustics. Expert Syst. Appl., 37 (10): 7205–7212.
Opoku, R. D., Shouqi, Y., Junping, L., and Livingstone, S. A. 2018. Droplet characterization and water distribution of fixed spray plate sprinkler used in linearly moved irrigation system. Poljoprivredna tehnika, 43(2): 17–29.
Ortiz, J. N., Tarjuelo, J. M., and De Juan, J. A. 2009. Characterization of evaporation and drift losses with center pivots. Agric. Water Manage., 96(11): 1541–1546.
Peters, R. T., and Evett, S. R. 2007. Spatial and temporal analysis of crop conditions using multiple canopy temperature maps created with center-pivot-mounted infrared thermometers. Trans. ASABE, 50(3): 919–927.
Playán, E., Garrido, S., Faci, J. M., and Galán, A. 2004. Characterizing pivot sprinklers using an experimental irrigation machine. Agric. Water Manage., 70(3): 177–193.
Playán, E., Salvador, R., Faci, J. M., Zapata, N., Martínez-Cob, A., and Sánchez, I. 2005. Day and night wind drift and evaporation losses in sprinkler solid-sets and moving laterals. Agric. Water Manage., 76(3): 139–159.
Rajan, N., Maas, S., Kellison, R., Dollar, M., Cui, S., Sharma, S., and Attia, A. 2015. Emitter Uniformity and Application Efficiency for Centre‐Pivot Irrigation Systems. Irrig. and Drain., 64(3): 353–361.
Raju, K. S., Kumar, D. N., and Duckstein, L. 2006. Artificial neural networks and multicriterion analysis for sustainable irrigation planning. Computers and Operations Research, 33(4): 1138-1153.
Sadeghi, S. H., Peters, T. R., Amini, M. Z., Malone, S. L., and Loescher, H. W. 2015. Novel approach to evaluate the dynamic variation of wind drift and evaporation losses under moving irrigation systems. Biosyst. Eng., 135: 44–53.
Sadeghi, S. H., Peters, T., Shafii, B., Amini, M. Z., and Stöckle, C. 2017. Continuous variation of wind drift and evaporation losses under a linear move irrigation system. Agric. Water Manage, 182: 39–54.
Santos, F. L., Reis, J. L., Martins, O. C., Castanheira, N. L., and Serralheiro, R. P. 2003. Comparative assessment of infiltration, runoff and erosion of sprinkler irrigated soils. Biosyst. Eng., 86(3): 355–364.
Sarwar, A., Peters, R. T., and Mohamed, A. Z. 2019a. Linear mixed modeling and artificial neural network techniques for predicting wind drift and evaporation losses under moving sprinkler irrigation systems. Irrig. Sci., 1–12.
Sarwar, A., Peters, R. T., Mehanna, H., Amini, M. Z., and Mohamed, A. Z. 2019b. Evaluating water application efficiency of low and mid elevation spray application under changing weather conditions. Agric. Water Manage., 221: 84–91.
Steiner, J.L., E.T. Kanemasu and R.N. Clark. 1983. Spray losses and partitioning of water under a center pivot sprinkler system. Trans. ASAE, 26(4): 1128–1134.
Thompson, A. L., Gilley, J. R., and Norman, J. M. 1993a. A sprinkler water droplet evaporation and plant canopy model: I. Model development. Trans. ASAE, 36(3): 735–741.
Thompson, A. L., Gilley, J. R., and Norman, J. M. 1993b. A sprinkler water droplet evaporation and plant canopy model: II. Model application.Tran. ASAE, 36(3): 743–750.
Thompson, A. L., Martin, D. L., Norman, J. M., Tolk, J. A., Howell, T. A., Gilley, J. R., and Schneider, A. D. 1997. Testing of a water loss distribution model for moving sprinkler systems. Transactions of the ASAE, 40(1): 81–88.
Tolk, J.A., T.A. Howell, J.L. Steiner, D.R. Krieg, and A.D. Schneider. 1995. Role of transpiration suppression by evaporation of intercepted water in improving irrigation efficiency. Irrig. Sci. 16:89–95.
Trimmer, W.L. 1987.  Sprinkler evaporation loss equation. J. Irrig. Drain. Eng., ASCE 113 (4): 616–620.
Tu, J. V. 1996. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J. Clin. Epidemiol., 49(11): 1225–1231.
Urrego-Pereira, Y., Cavero, J., Medina, E. T., and Martínez-Cob, A. 2013. Role of transpiration reduction during center-pivot sprinkler irrigation in application efficiency. J. Irrig. Drain. Eng., 139(3): 221–232.
Yazar, A.  1984. Evaporation and drift losses from sprinkler irrigation systems under various operating conditions.  Agric. Water Manage., 8: 439–449.