Estimation of Daily Reference Evapotranspiration Using a Hybrid Approach Combining Stochastic Gradient Descent Optimization and Artificial Neural Network

Document Type : Research Paper

Authors

1 Associate Prof., Soil Science Dept., Faculty of Agriculture, University of Tabriz.

2 MSc, Soil Science Dept., Faculty of Agriculture, University of Tabriz.

3 Assoc. Prof., Water Engineering Dept., Faculty of Agriculture, University of Tabriz

4 PhD candidate, Water Engineering Dept., Faculty of Agriculture, University of Tabriz

Abstract

Reference evapotranspiration (ET₀) is a crucial parameter in agricultural water management. In this study, two modeling approaches were investigated for predicting daily ET₀ at the Kish, Gorgan, and Shiraz meteorological stations: (1) a standard multilayer perceptron (MLP) model, and (2) an MLP model optimized using the stochastic gradient descent (SGD) algorithm. A dataset comprising 23 years (2000–2023; 1379–1402 in the Iranian calendar) of daily meteorological data was used to develop and validate the models under five different input scenarios, selected based on Pearson correlation analysis. Model performance was evaluated using multiple statistical metrics, including the correlation coefficient (R), root mean square error (RMSE), Nash–Sutcliffe efficiency (NSE), and the Willmott agreement index (d). Among the tested configurations, the fifth scenario of the combined MLP-SGD model showed the highest accuracy, achieving RMSE values of 1.04 mm/day, 1.20 mm/day, and 1.94 mm/day for the Shiraz, Gorgan, and Kish stations, respectively. The results indicate that the combined MLP-SGD model outperformed the standalone MLP model, demonstrating its reliability and effectiveness in predicting reference evapotranspiration. These findings underscore the potential of hybrid artificial intelligence models in improving water resource management and promoting sustainable agricultural practices.

Keywords

References

  1. میکائیلی، فاطمه و صمدیان فرد، سعید، 1402. کاربرد مدل‌های درختی و مبتنی بر کرنل در تعیین تبخیر و تعرق مرجع روزانه در دو منطقه مرطوب و خشک ایران. نشریه دانش آب‌وخاک، 33 (2)، صص. 35- 51.

 DOI: 10.22034/ws.2021.45876.2415

  1. Allen, R.G., Pereira L.S., Raes, D. and Smith, M. 1998. Crop evapotranspiration- guidelines for computing crop water requirements. Irrigation and Drainage Paper no. 56, FAO, Rome, Italy.
  2. Antonopoulos, V.Z. and Antonopoulos, A.V. 2017. Daily reference evapotranspiration estimates by artificial neural networks technique and empirical equations using limited input climate variables. Computers and Electronics in Agriculture, 132: pp.86-96. DOI:10.1016/j.compag.2016.11.011
  3. Bonnabel, S. 2013. Stochastic gradient descent on Riemannian manifolds. IEEE Transactions on Automatic Control, 58(9):2217-2229.

DOI:10.1109/TAC.2013.2254619

  1. Cai, J., Liu,Y., Lei, T. and Pereira, L.S. 2007. Estimating reference evapotranspiration with the FAO Penman–Monteith equation using daily weather forecast messages. Agricultural and Forest Meteorology 145(1-2):pp. 22-35.

DOI: 10.1016/j.agrformet.2007.04.012

  1. Dubey, S.R., Singh, S.K. and Chaudhuri, B.B. 2022. Activation functions in deep learning: A comprehensive survey and benchmark. Neurocomputing, 503: 92-108. DOI: 10.1016/j.neucom.2022.06.111
  2. Durairaj, M. and Revathi, V. 2015. Prediction of heart disease using back propagation MLP algorithm. International Journal of Scientific and Technology Research, 4(8): pp.235-239. ISSN 2277-8616
  3. Gibson, J., Holmes, T., Stadnyk, T., Birks, S., Eby, P. and Pietroniro, A. 2021. Isotopic constraints on water balance and evapotranspiration partitioning in gauged watersheds across Canada. Journal of Hydrology: Regional Studies, 37: 100878. DOI: 10.1016/j.ejrh.2021.100878
  4. Hami, Kouchebagi, M., Nazemi, A., Sadraddini, A. and Delirhasannia, R. 2017. Calculation of the reference evapotranspiration based on the statistical analysis of air temperature (case study: Tabriz area). Water and Soil Science, 26(4.2),pp. 41-54.
  5. Hu, Z., Bashir, R.N., Rehman, A.U., Iqbal, S.I., Shahid, M.M.A. and Xu, T. 2022. Machine learning based prediction of reference evapotranspiration (ET0) using iot. IEEE Access, 10. DOI:10.1109/ACCESS.2022.3187528
  6. Johnson, R .and Zhang, T. 2013. Accelerating stochastic gradient descent using predictive variance reduction. Advances in neural information processing systems 26,pp. 1-9.
  7. Kazemi, M.H., Shiri, J., Marti, P and Majnooni-Heris, A. 2020. Assessing temporal data partitioning scenarios for estimating reference evapotranspiration with machine learning techniques in arid regions. Journal of Hydrology, 590: 125252. DOI:10.1016/j.jhydrol.2020.125252
  8. Luo, Y., Gao, P. and Mu, X. 2021. Influence of meteorological factors on the potential evapotranspiration in Yanhe River Basin, China. Water, 13(9): 1222. DOI: 10.3390/w13091222
  9. Ma, L., Li, Y., Wu, P., Zhao, X., Chen, and Gao, X. 2020. Coupling evapotranspiration partitioning with water migration to identify the water consumption characteristics of wheat and maize in an intercropping system. Agricultural and Forest Meteorology, 290: 108034.

DOI: 10.1016/j.agrformet.2020.108034

  1. Mohammed, S.A., Al-Haddad, L.A., Alawee, W.H., Dhahad, H.A., Jaber, A.A. and Al-Haddad, S.A. 2023. Forecasting the productivity of a solar distiller enhanced with an inclined absorber plate using stochastic gradient descent in artificial neural networks. Multiscale and Multidisciplinary Modeling, Experiments and Design, 1-11. DOI:10.1007/s41939-023-00309-y
  2. Moriasi, D.N., Arnold, J.G., Van Liew, M.W., Bingner, R.L., Harmel, R.D., Veith, T.L. 2007. Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. Transactions of the ASABE, 50: 885-900.
  3. Panahi, S., Karbasi, M. and Nikbakht, J. 2016. Forecasting of reference evapotranspiration using MLP, RBF, and SVM neural networks. Environment and Water Engineering, 2(1), pp.51-63. DOI: 10.29252/jwmr.9.18.157
  4. Pereira, L., Paredes, P. and Jovanovic, N. 2020. Soil water balance models for determining crop water and irrigation requirements and irrigation scheduling focusing on the FAO56 method and the dual Kc approach. Agricultural water management, 241: 106357.
  5. Popescu, M.C., Balas, V,E., Perescu-Popescu, L .and Mastorakis, N. 2009. Multilayer perceptron and neural networks. WSEAS transactions on circuits and systems, 8(7), pp.579-588.
  6. Samadianfard, S., Rousta, Z. and Sharafi, M. 2024. Prediction of daily reference evapotranspiration with M5P, Gaussian process regression and support vector regression methods. Water and Soil Science, 34(2), pp.156-176.
  7. Shi, H., Yang, N., Tang, H. and Yang, X. 2022. Stochastic gradient descent with adaptive batch size for every parameter. Mathematics, 10(6): 863.
  8. Subasi, A., El-Amin, M.F., Darwich, T and Dossary, M., 2022. Permeability prediction of petroleum reservoirs using stochastic gradient boosting regression. Journal of Ambient Intelligence and Humanized Computing.1-10.
  9. Tabari, H. and Hosseinzadeh, Talaee, P. 2013. Multilayer perceptron for reference evapotranspiration estimation in a semiarid region. Neural Computing and Applications, 23,pp. 341-348.
  10. Talebi, H., Samadianfard, S. and Valizadeh, Kamran, K. 2023. Estimation of daily reference evapotranspiration implementing satellite image data and strategy of ensemble optimization algorithm of stochastic gradient descent with multilayer perceptron. Environment, Development and Sustainability: pp.1-23.
  11. Vaz, P.J., Schütz, G., Guerrero, C. and Cardoso, P.J. 2022. Hybrid neural network based models for evapotranspiration prediction over limited weather parameters. IEEE Access, 11,pp. 963-976.
Journal of Water Research in Agriculture
Volume 39, Issue 1
June 2025
Pages 65-80

Files

Share

How to cite

Statistics