کاربرد تلفیقی شبکه عصبی و روش های محاسباتی جهت تخمین دقیق تر تبخیر-تعرق مرجع

نوع مقاله: مقاله پژوهشی

نویسندگان

1 استادیار /بخش مهندسی آب. دانشگاه فسا.

2 استاد/ بخش مهندسی آب. دانشگاه شیراز

3 استادیار/ بخش مهندسی آب. دانشگاه فسا.

4 استادیار /بخش مهندسی آب. دانشگاه شیراز.

چکیده

در بسیاری از مسائل آبیاری و زهکشی، هیدرولوژی، محیط زیستی، فرسایش خاک و منابع آب تخمین دقیق تر تبخیر-تعرق اهمیت زیادی دارد. استفاده از شبکه عصبی مصنوعی یکی از روش های تخمین تبخیر-تعرق مرجع می‌باشد. تاکنون در بیشتر مقالات منتشر شده داده های اقلیمی به عنوان ورودی شبکه عصبی جهت تخمین تبخیر-تعرق مرجع مورد استفاده قرار گرفته است. در این تحقیق از تبخیر-تعرق محاسبه شده بوسیله روش های محاسباتی هارگریوز ـ سامانی، جنسن ـ هیز، تورک و روش تشت تبخیر در کنار داده های هواشناسی به عنوان داده های ورودی شبکه عصبی مصنوعی استفاده شد. نتایج نشان داد که از بین روش های مذکور که به همراه داده های هواشناسی به عنوان داده های ورودی شبکه عصبی استفاده شده تنها روش جنسن ـ هیز منجر به تخمین تبخیر-تعرق مرجع روش استاندارد پنمن-مانتیس-فائو با دقت بالا گردید و در بقیه روش ها استفاده از شبکه عصبی مصنوعی به همراه روش های محاسباتی اگرچه اندکی دقت تخمین را بهبود داده اما همچنان دقت این روش ها برای محاسبه تبخیر – تعرق مرجع پایین می‌باشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Combined Application of Artificial Neural Network and Computational Methods to Estimate the Reference Evapotranspiration

نویسندگان [English]

  • A. Shabani 1
  • A.R Sepaskhah 2
  • M. Bahrami 3
  • F. Razzaghi 4
1 Assis. Prof., Water Engineering Dept., Fasa University, Iran
2 Prof. of Irrigation science, Shiraz University, College of Agriculture, Shiraz, I.R. of Iran,
3 Assis. Prof., Water Engineering Dept., Fasa University, Iran.
4 Assis. Prof., Water Engineering Dept., Shiraz University, Iran.
چکیده [English]

Estimation of reference evapotranspiration (ETo) is essential for many issues i.e., irrigation and drainage, hydrology, environment, soil erosion and water resources. Using the artificial neural network (ANN) to estimate ETo is common in a lot of studies. But what has not been addressed in previous studies is using meteorological data as an input of neural network together with computational methods. In this study, calculated ETo by computational methods including Jensen-Haise, Turc, Hargreaves-Samani and pan evaporation methods accompanying with meteorological data were used as input data. Results showed that using the calculated ETo by Jensen-Haise method together with meteorological data as input data resulted in closer estimation to calculated ETo by Penman-Montieth-FAO among all of computational methods. Using the calculated ETo by other methods along with meteorological data improved the ETo estimation compared with using the meteorological data lonely, however, accuracy of ETo estimation by using these methods were still low.

کلیدواژه‌ها [English]

  • Artificial Neural Network
  • Penman-Montieth-FAO
  • Jensen-Haise
  • Turc
  • Hargreaves-Samani

Abedi-Koupai J, Amiri MJ, Eslamian SS (2009) Comparison of artificial neural network and physically based models for estimating of reference evapotranspiration in greenhouse. Australian Journal of Basic and Applied Sciences 33:2528-2535

Allen RG (1999) Reference evapotranspiration calculation software for FAO and ASCE standardized equations. University of Idaho Research and Extension Center, 76p

Allen RG, Pereira LS, Raes D, Smith M (1998) Crop evapotranspiration: guidelines for computing crop water requirements. Irrigation and Drainage Paper 56 Rome: Food and Agriculture Organization of the United Nations, 300p

Cuenca RH (1989) Irrigation system design: An engineering approach Englewood Cliffs. NJ, Prentice-Hall, 552p

Dehbozorgi F, Sepaskhah AR (2012) Comparison of artificial neural networks and prediction models for reference evapotranspiration estimation in a semi-arid region. Archives of Agronomy and Soil Science 585:477–497 doi:10.1080/03650340.2010.530255

Ghasemi A, Zare Abyaneh H, Amiri Chaichian R, Mohammadi K (2007) Assessing artificial neural network and empirical methods to estimate the reference evapotranspiration of Hamedan province in Iran. Proceedings of the 9th Conference of Irrigation and decreasing the evapotranspiration. Kerman, Iran (In Persian).

Hargreaves GH, Samani ZA (1985) Reference crop evapotranspiration from temperature. Applied Engineer in Agriculture 12:96–99

Jain SK, Nayak PC, Sudheer KP (2008) Models for estimating evapotranspiration using artificial neural networks, and their physical interpretation. Hydrological Processes 2213:2225–2234 doi:10.1002/hyp.6819

Jamieson PD, Porter JR, Wilson DR (1991) A test of computer simulation model ARC-WHEAT1 on wheat crops grown in New Zealand. Field Crops Research 27:337–350 http://dx.doi.org/10.1016/0378-42909190040-3

Jensen ME, Burman RD, Allen RG (1990) Evapotranspiration and irrigation water requirements. American Society of Civil Engineers, Engrg Pract Manual No. 70, 332p

Kisi O, Kilic Y (2015). An investigation on generalization ability of artificial neural networks and M5 model tree in modeling reference evapotranspiration. Theoretical and Applied Climatology. doi:10.1007/s00704-015-1582-z

Kumar M, Raghuwanshi N, Singh R, Wallender W, and Pruitt W (2002) Estimating evapotranspiration using artificial neural network. Journal of Irrigation and Drainage Engineering 1284:224-233 doi:10.1061/ASCE0733-94372002128:4224, 224-233

Landeras G, Ortiz-Barredo A, López JJ (2008) Comparison of artificial neural network models and empirical and semi-empirical equations for daily reference evapotranspiration estimation in the Basque Country Northern Spain. Agricultural Water Management 955:553–565 doi:10.1016/j.agwat. 2007.12.011

Razzaghi F, Sepaskhah AR (2010) Assessment of nine different equations for ETo estimation using lysimeter data in a semi-arid environment. Archives of Agronomy and Soil Science 561:1–12 doi:10.1080/03650340902829180

Shamshirband S, Amirmojahedi M, Gocić M, Akib S, Petković D, Piri J, Trajkovic S (2015) Estimation of reference evapotranspiration using neural networks and Cuckoo search algorithm. Journal of Irrigation and Drainage Engineering 142(2):04015044 doi:10.1061/(ASCE) IR.1943-4774.0000949, 04015044

Shiri J, Kişi Ö (2011) Application of artificial intelligence to estimate daily pan evaporation using available and estimated climatic data in the Khozestan province south western Iran. Journal of Irrigation and Drainage Engineering 1377:412-425 doi:10.1061/ASCEIR.1943-4774.0000315, 412-425

Shiri J, Marti P, Nazemi A H, Sadraddini A A, Kisi O, Landeras G, Fakheri Fard A (2015) Local vs. external training of neuro-fuzzy and neural networks models for estimating reference evapotranspiration assessed through k-fold testing. Hydrology Research 46 (1) 72-88

Trajkovic S (2005) Temperature-based approaches for estimating reference evapotranspiration. Journal of Irrigation and Drainage Engineering 1314:316–323 doi:10.1061/asce0733-94372005131:4316

Trajkovic S, Todorovic B, Stankovic M (2003) Forecasting of reference evapotranspiration by artificial neural networks. Journal of Irrigation and Drainage Engineering 129(6):454-457 doi:10.1061/ASCE0733-94372003129:6454, 454-457

Traore S, Luo Y, Fipps G (2016) Deployment of artificial neural network for short-term forecasting of evapotranspiration using public weather forecast restricted messages. Agricultural Water Management, 163:363–379

Traore S, Wang YM, Kerh T (2010) Artificial neural network for modeling reference evapotranspiration complex process in Sudano-Sahelian zone. Agricultural Water Management 975:707–714 doi:10.1016/j.agwat.2010.01.002

Zare Abyaneh H, Gasemi A, Bayat Varkeshi M, Mohammadi K, Sabziparvar AA (2009) Evaluation of two artificial neural network software in the prediction of crop reference evapotranspiration. Water and Soil Science 19(1):201-212 (In Persian)