Estimating Pan Evaporation in Three Different Climates using Data-driven Methods

Authors

1 Ph.D. Student, Dept. of Water Eng., Faculty of Agric., University of Tabriz, Iran

2 University of Tabriz

3 Water Eng. Dept, Tabriz University

4 Prof.,

Abstract

Abstract
Background and Objectives: Evaporation is one of the most complex and important processes in studying hydrological and meteorological factors and plays a major role in determining the energy balance equations on the earth's surface. So, knowing the exact amount of evaporation volume is important for monitoring and correct management of water resources, irrigation planning, determining the irrigation needs, estimating evaporation from the reservoir of dams and modeling hydrological projects, especially in arid and semi-arid regions. On the other hand, modeling such a complex process in which many parameters interact with each other is so difficult that it is not possible to simplify this issue without multiple assumptions. Therefore, accurate estimation of evaporation has always been of great importance. Many experimental methods have been presented in estimating evaporation, but since these methods require a lot of input data or it is not possible to measure the variables in all areas, many of these methods have lost their effectiveness. Therefore, it is necessary to use methods which need fewer number of meteorological variables and estimate the evaporation with high accuracy. Therefore, the aim of the current research is to evaluate and present the most accurate model of evaporation estimation using three data-driven models in six synoptic stations in arid, semi-arid and humid climates of Iran, so that the proposed model, in addition to having sufficient accuracy, requires fewer input parameters to estimate evaporation even when there is no sufficient data.
Methodology: In this regard, the ability of three machine-learning methods of gradient boosted tree (GBT), generalized linear model (GLM) and artificial neural network-multi layer perceptron (MLP) in estimating the amount of pan evaporation in dry (Yazd and Bafq stations), semi-arid (Birjand and Siah-Bisheh stations) and humid climates (Sari and Ferdous stations) were investigated. Daily parameters of some fundamental and effective meteorological variables on evaporation during the time period of 2001-2020 were collected. In order to investigate the possibility of using different combinations of meteorological parameters to estimate the evaporation as accurately as possible, six different combinations of meteorological parameters (average temperature, relative humidity, and wind speed and sunshine hours) were considered. Also, to evaluate the accuracy of the mentioned models, four assessment criteria were used including root mean square error (RMSE), mean absolute error (MAE), correlation coefficient (R) and scatter index (SI). Furthermore, diagrams of time series of the best models and the distribution diagram of observed and predicted pan evaporation by the models were presented and the most suitable combination of meteorological parameters that had suitable accuracy for estimating pan evaporation was suggested.
Findings: The results showed that in Birjand, Yazd, Ferdos, and Siah-Bisheh stations, MLP-VI with RMSE of 1.97, 1.95, 1.97, 2.91, respectively, performed more accurate than other studied models. Moreover, In Sari station MLP-IV and in Bafq station, MLP-V, with RMSE of 1.41 and 1.92, respectively, provided the most precise estimates of evaporation values. Finally, it can be comprehended that in all three studied stations, MLP provided the most accurate estimations of the amount of pan evaporation and it is suggested as a method with high degree of accuracy. Furthermore, GBT presented the weakest performance in comparison with other studied models. The mentioned trend about the high accuracy of the mentioned models for all studied stations can also be concluded from presented Figures. So, it can be inferred that the accurate models mentioned in each station had the least distribution around the bisector line and had the most accuracy and the least error. In other words, it is possible to estimate the evaporation values in all stations with the meteorological data of temperature, relative humidity, sunshine hours and wind speed with acceptable accuracy.
Conclusion: Evaporation is one of the main components of water balance in agriculture and is one of the effective and influential factors for suitable irrigation planning. Therefore, accurate estimation of this parameter has a significant role on reducing excessive water consumption. So, in this study, three data-driven models of MLP, GBT and GLM were implemented in six stations including Yazd, Birjand, Sari, Bafq, Siah-Bisheh and Ferdous. The obtained results indicated that the sixth scenario using all utilized meteorological parameters in Yazd, Birjand, Siah-Bisheh, and Ferdous stations, forth scenario in Sari and fifth scenario in Bafq station with the lowest error provided the most accurate estimates of the evaporation and may be recommended for proper estimation of pan evaporation values.

Keywords


Afkhami H, Habibipur A and Ekhtesasy M, 1397. Performance assessment of data mining techniques for Forecast for one year evaporation - Case study of Yazd synoptic station. Iranian Journal of Natural Resources 3: 594-579. (In Persian with English abstract).
Khorshiddoost AM, Mirhashemi H and Nazari M, 1398. Evaluation of the performance of artificial neural network and support vector machine models in estimation of daily evaporation amounts - Case study of Tabriz and Maragheh Synoptic Stations. Journal of Geography and Planning 68(23): 71-90 (In Persian with English abstract).
Ghaemi A, Rezaie Balf M, Adamowski J, Kisi O and Quilty J, 2019. On the applicability of maximum overlap discrete wavelet transform integrated with MARS and M5 model tree for monthly pan evaporation prediction. Agricultural and Forest Meteorology 278: 397-428.
Wu L, Haung G, Fan J, Ma X, Zhou H and Zeng W, 2020. Hybrid extreme learning machine with meta-heuristic algorithms for monthly pan evaporation prediction. Computers and Electronics in Agriculture 168: 105-115.
Majhi B and Naidu D, 2021. Pan evaporation modeling in different agroclimatic zones using functional link artificial neural network. Information Processing in Agriculture 8: 134-147.
Mir Mohammad Sadeghi SA, Ghobadniyam M and Rahimian MH, 2018. Estimation of evaporation from Zayandeh-Rood Dam Lake using SEBAL. Water and Soil 33(4): 548-537 (In Persian with English abstract).
Moneskhah V, SamadianFard S and Hadi M, 2019. Evaluation of data mining methods and experimental temperature-radiation-based models in estimating evaporation from the Pan - Case study of the East Lake Urmia. Journal of Water and Soil Research 51(9): 2348-2337 (In Persian with English abstract).
Sharfi M and SamadianFard S, 1400.  Prediction of daily evaporation using hybrid support vector regression-firefly optimization algorithm and multilayer perceptron. Journal of Rainwater 9(4): 53-66 (In Persian with English abstract).
Shadkani S, Abbaspour A, Samadianfard S, Hashemi S, Mosavi A and Shamshirband S, 2021. Comparative study of multilayer perceptron-stochastic gradient descent and gradient boosted trees for predicting daily suspended sediment load - Case study of the Mississippi river. US International Journal of Sediment Research 36(4): 512-523.
Qamarnia H, Naseri S, Amini A and Sargardi F, 1400. Comparison of SEBAL algorithm and meteorological data results in estimating daily evaporation from free water surface - Case study of Soleimanshah dam. Environmental and Water Engineering Journal 7(3): 494-506 (In Persian with English abstract).
Farasaty M, Seydian M and Dab K, 1400. Evaporation modeling of free surface water using SVM and LSSVM models. Water and Irrigation 11(3): 288-272 (In Persian with English abstract).
Seifzadeh Kh, 1402. Estimation of daily evaporation from class A pan using five data mining methods - Case study of Tabriz Meteorological Station. MSc Thesis, Tabriz University of Technology. (In Persian with English abstract).