Prediction of daily evapotranspiration using the strategy of combining tree models with empirical Hargreaves method

Abstract
Background and Objectives: The constant need to increase agricultural production, along with more and more frequent drought events in the country, requires a more accurate assessment of irrigation needs and thus a more accurate estimate of actual evapotranspiration. Prediction of water consumption over agricultural areas is important for agricultural water resources planning, management, and regulation. It leads to the establishment of a sustainable water balance, mitigates the impacts of water scarcity, as well as prevents the overusing and wasting of precious water resources. As evapotranspiration is a major consumptive use of irrigation water and rainwater on agricultural lands, improvements of water use efficiency and sustainable water management in agriculture must be based on the accurate estimation of ET. Irrigated agriculture is expected to produce more crops with less water consumption in the future. Therefore, accurate forecasting of water demand along with sustainable management and more efficient methods to meet the growing demand under scarce water resources is necessary. The models used to predict evapotranspiration should be used in different regions with different climates to evaluate their performance. Therefore, in this research, tree models and Hargreaves were used in Yazd and West Azerbaijan provinces, which have different climates, in order to evaluate the performance of the models used.
Methodology: In recent years, water management issues have been addressed using models derived from artificial intelligence research. In recent years, water management issues have been addressed using models obtained from multiple types of research. The use of combined models has made significant progress in recent years. combined models are able to perform processing in a short period of time and at the same time with high accuracy. Using these models, the main challenging aspects are represented by the selection of the best possible algorithm, the selection of suitable representative variables and the availability of suitable data sets. Therefore, in this study, the ability of tree models (M5P and RF) with Hargreaves model (Hs) in estimating daily evapotranspiration in Urmia and Yazd stations during the period of 2000-2021. The noteworthy point is that in the combined tree-Hargreaves model, the used tree models were used as input to the Hargreaves model. The combined model has been used for the first time in this research and the use of this model can predict daily evapotranspiration as well as possible.
Findings: The results of the model are performed using 5 evaluation criteria of Coefficient of determination, Root mean square error, Nash-Sutcliffe coefficient, and Wilmot’s index of agreement. In all the used models, the best scenario was the model whose input included parameters of minimum temperature, maximum temperature, relative humidity, wind speed, and sunshine hours. Comparison and evaluation of standalone tree models showed that in the Urmia station two models RF-5 and M5P-5 had less error (0.4 and 0.38-mm day-1, respectively) than other standalone models. Similarly, in the Yazd station, RF-5 and M5P-5 models have higher accuracy (0.36 and 0.35 mm day-1(, respectively) than other standalone models. For combined models, the obtained results showed that the fifth scenario of the M5P-Hs model provided the best performance in Urmia and Yazd stations with the lowest error (0.33 and 0.24 mm day-1) respectively. It was also concluded that the fifth scenario of the RF-Hs model in Urmia and Yazd stations had a lower error (0.36 and 0.26 mm day-1) than other models, respectively. Finally, tree models have increased the accuracy of the Hargreaves model in this research.

Conclusion: Finally, the RF, M5P, RF-Hs and M5P-Hs models were able to predict daily evapotranspiration values in the shortest time and with the highest accuracy. However, the results showed that the lower the model inputs, the weaker the model prediction. The results of this research showed that the combination of tree models with Hargreaves model is able to predict daily evapotranspiration values with high accuracy compared to individual models. The results of this research showed that the wind speed parameter is one of the most important meteorological parameters needed in estimating daily evapotranspiration, so adding this parameter results in the highest accuracy in all models. Also, due to the important role of wind speed in predicting daily evapotranspiration values and the unavailability of the maximum wind speed parameter in this research, it is recommended to use the maximum wind speed parameter as one of the model inputs for further studies.