Investigating the effectiveness of transfer functions based on machine learning methods for predicting reference evaporation and transpiration (Case study: Bushehr)

Document Type : Research Article

Authors

1 Associate Professor, Department of Water Engineering, Faculty of Water and Soil, University of Zabol. Zabol, Iran

2 Graduate student, Department of Water Engineering, Faculty of Water and Soil, University of Zabol. Zabol, Iran

Abstract

Accurate calculation of reference evapotranspiration is one of the basic tasks to achieve optimal management of water resources. In this research, the evapotranspiration of Bushehr reference was calculated by the Fau‌ Penman‌ Mantis method. Then, temperature methods (Hargreaves‌ Samani and Blaney‌ Cridle) and radiation methods (modified Mc‌ King, Tork and Prestley‌ Taylor) were also used to calculate evaporation‌ transpiration. The results obtained from these methods were compared with the combined Fau‌ Penman‌ Mantis method. The results showed that among the two temperature methods, the Hargreaves‌ Samani method and among the radiation methods, the Prestley‌ Taylor method had closer results to the combined Fau‌ Penman‌ Mantis method. Artificial intelligence, support vector machine, random forest and cubist models were also used to estimate reference evaporation‌ transpiration. The data used included minimum, maximum and average temperature, relative humidity, sunshine hour and wind speed during a thirty‌ year statistical period from 1370 to 1400. In order to check the results of the mentioned models, the standard evaluation criteria of error mean square, absolute mean error and R2 explanation coefficient were used. The results showed that all three models were highly accurate in simulating evaporation‌ transpiration. Cubist model with higher R2 (0.95), the lowest mean squared error (0.87) and the lowest absolute mean error (0.38) was chosen as the best method for evaporation‌ transpiration.

Keywords

Main Subjects

References

  • M, Selle. B, Wang, Q. Understanding and predicting deep percolation under surface irrigation. Journal of Water Resour. 2008: 15(4). 120‌ 134.
  • Siaser, H., and Dindarlou, A. Estimation of daily reference evaporation and transpiration using deep learning model, random forest and decision tree (case study: Sistan plain). Iranian Water Research, 2019: 14(1):108‌ [Persian].
  • Maeda,E.E., Wiberg,D.A., and Pellikka,P.K.E. Estimating reference evapotranspiration using sensing empirical models in a region with limited data availability in Kenya. Applied Geography. 2010: 31: 251‌ 258
  • Bos,M.G., Kselik,R.G., Allen,k., Molden,D.J. Water Requirements for Irrigation and the Environment. Springer,2009: 186p.
  • Panahi, S. F. Rezvanizadeh and Samadianfard, S. Evaluation and comparison of experimental methods for estimation of reference evapotranspiration in Tabriz station. The first international conference on Iran's natural hazards and environmental crises, solutions and challenges,2016: 9 p. [Persian]
  • Pandey, P.K., P.P. Dabral., and Pandey, V. Evaluation of reference evapotranspiration methods for the northeastern region of India. International Soil and Water Conservation Research, 2016: 4(1), 52‌
  • ,H and Poozan., M. Evaluation of 24 evapotranspiration models in different climates of Iran. Ecohydrology, 2019: 6(3):611‌ 622.
  • Wang, Z., P. Xie., C. Lai., X. Chen., X. Wu., Z. Zeng and J. Li. Spatiotemporal variability of reference evapotranspiration and contributing climatic factors in China during 1961– 2013. Journal of Hydrology, 2017: 544, 97‌
  • Hengl, T., Nussbaum, M., Wright, M. N., Heuvelink, G. B., and Gräler, B. Random forest as a generic framework for predictive modeling of spatial and spatio‌ temporal variables. PeerJ, 2018: 6, e5518.‏
  • Pai, P., F. and W. C. Hong. A recurrent support vector regression model in rainfall forecasting. Hydrological Process. 2007: 21:819‌
  • Kihani, A., Akhundali, A., and Fathian, H. Uncertainty analysis of parameters of SVM model for estimation of suspended sediment load and bed in Sierra Karaj station with Monte Carlo simulation method. Iran Water and Soil Research (Agricultural Sciences of Iran), 2021: 52(1), 195‌ 212. [Persian].
  • Breiman L. Application and analysis of random forests and machine learning. Journal of Water Management.2001; 15(1): 5‌ 32
  • Kuhn, M., Weston, S., Keefer, C., Coulter, N., and Quinlan, R. Cubist: Rule‌ and Instance‌ based Regression Modeling, R package version 0.4.2.1. (https://cran.r‌ org/web/ packages/Cubist/Cubist.pdf. Last access date: 3 May 2023)
  • Ahmadi, F., Aysham, S., Khalili, K., and Beahmanesh, J. performance evaluation of artificial neural network (ANN) and support vector machine (SVM (in estimating daily evaporation values) (Case study: Tabriz and Maragheh meteorological stations). Soil and Water,2016: 1(49):151‌
  • Hajari, Z., Naserzadeh, M.H., Tagvi Guderzi, S. Preparation of Persian Gulf ecotourism calendar based on bioclimatic indicators of MEMI model (case study: Bushehr). Scientific Quarterly Journal of Tourism Management Studies, 2018:14(46): 282‌ 245. [Persian].
  • Hastie, T. and Pregibon, J. Generalized linear models. Eberly College of Science, London. 1992
  • Burges, C.J. A tutorial on support vector machines for pattern recognition. Data mining and knowledge discovery,1998: 2: 121‌ 167
  • Norouzi Ghoshbalagh, H., Nadiri, A., Asghari Moghaddam, A. and Qarahkhani, M. Comparison of the efficiency of artificial neural networks, fuzzy logic and random forest in estimating the aquifer transfer capability of Malekan plain. Echo Hydrology, 2018, 5(3): 739‌ [Persian]
  • Nosrati Karizak, F., Movahedi Naeni, S.A., and Hezarjaribi, A. Using Artificial Neural Networks to estimate saturated hydraulic conductivity from easily available soil properties. J. Soil Manage. Sust. Prod. 2012, 2(1): 95‌ [Persian].
  • Wosten, J.H.M., Pachepsky ,Ya.A. and Rawls, W.J.Pedotransfer functions: bridging the gap between available basic soil data and missing soil hydraulic characteristics.J.Hydrol. 2001, 251:123–150.
  • Breiman L. Application and analysis of random forests and machine learning. Journal of Water Management.2001; 15(1): 5‌ 32
  • Siasar, H, and Honar, T. The application of support vector machine, chaid and random forest models in estimating daily reference transpiration evaporation in the north of Sistan and Baluchistan province. Iran Irrigation and Drainage.2018 ;2(13):378‌ [Persian].
  • Quinlan, J.R.Learning with continuous classes. P 343‌ 348, In: Proceedings of 5th Australian conference on artificial intelligence. World Scientific. Singapore, 1992.
  • Zhou, Z. Ensemble Methods: Foundations and Algorithms. Chapman and Hall/CRC. 23p.2012.
  • Nazari, R., Kaviani, A. Evaluation of potential evaporation and transpiration methods and evaporation pan with lysimeter values in a semi‌ arid climate (case study, Qazvin Plain). Ecohydrology, 2015, 3(1):19‌ 30. [Persian]
  • Hosseini‌ Vardanjani, S.M., Ganji‌ Khoram‌ Del, N., and Khalt‌ Abadi‌ Farahani, A.H. Evaluation and sensitivity analysis of different methods of daily reference evaporation and transpiration estimation in a cold climate. Applied Water Science Research,2014, 1(2):29‌ 40. [Persian].
  • Tavakoli, A., Hero b., Davari, K., and Ansari, H. Estimation of reference evapotranspiration in data‌ deficient conditions (case study: North Khorasan province), Journal of Agricultural Sciences and Techniques and Natural Resources, 2012: 65: 222‌ 211. [Persian].
  • Sabzevari, Y., Parsai, A., and Haqi‌ Abi, A.H. Modeling and estimation of daily evaporation and transpiration of a reference plant with soft computing models (case study: Aliguderz station), 2023:13(52):292‌ 306. [Persian].
  • Hosseini‌ Vardanjani, S.M., Ganji‌ Khoram‌ Del, N., and Khalt‌ Abadi‌ Farahani, A.H. Evaluation of experimental and intelligent models in estimation of reference evaporation and transpiration in the conditions of minimum climatic data; A case study of Kurd city. Water and Irrigation Engineering, 2015: 25(7):141‌ 128. [Persian].

 

Iranian journal of Ecohydrology
Volume 10, Issue 3
October 2023
Pages 421-434

Files

History

  • Receive Date: 23 October 2023
  • Revise Date: 22 November 2023
  • Accept Date: 06 December 2023
  • First Publish Date: 12 December 2023
  • Publish Date: 12 December 2023

Share

How to cite

Statistics