Evapotranspiration Estimation Using Support Vector Machines and Hargreaves-Samani Equation for St. Johns, FL, USA

Abstract

Abstract. Information about Evapotranspiration (ET) calculations are not clear enough even it is an important part of hydrological cycle. There are many parameters which effect ET directly or indirectly such as Solar Radiation (SR) and Air Temperature (AT). In this study authors focused on the modelling ET using Support Vector Machines (SVM) method because this method has abilities to solve nonlinear problems. For the training SVM 1158 daily AT, SR, Wind Speed (U) and Relative Humidity (RH) meteorological parameters are used and model is tested using 385 daily parameters. Data set is taken from St. Johns, Florida, USA weather station. To understand the abilities of SVM for ET prediction against Hargreaves-Samani formula, the test set is applied to this empirical equation. Determination coefficient of SVM with observed daily ET values is calculated as 0.913 and determination coefficient of HargreavesSamani formula with observed daily ET is found as 0.910. Comparison between both methods is done using Mean Square Error (MSE), Mean Absolute Error (MEA) and determination coefficient statistics. As a result it is seen that SVM method is trustier than Hargreaves-Samani formula for daily ET prediction.

Evapotranspiration Calculation for South Carolina, USA and Creation Different ANFIS Models for ET Estimation.

“…However, it is not so clear and easy to estimate ET directly because of the effects of direct and indirect variables. In the past decade, scientists used different methods to estimate ET such as calibration of empirical equations and soft computing techniques (Chen, 2012;Dogan, 2009;Kaya et al, 2017Kaya et al, , 2016bKaya et al, , 2016aKisi, 2008;Kişi, 2006;Kumar et al, 2011;Mamak et al, 2017;Pal and Deswal, 2009;Ünes et al, 2017).…”

Estimation of Keban Dam Reservoir Level in Turkey Using Artificial Neural Network and Support Vector Machines.

“…The first studies on reservoir capacity determination were carried out by Ripple (1883), Hazen (1914), and Sudler (1927). Artificial intelligence was applied to dam reservoir level, dam reservoir volume, evaporation and in many different disciplines-areas by many researchers (Unes et al 2013(Unes et al , 2017a(Unes et al , 2017b(Unes et al ,2018a(Unes et al , 2018b(Unes et al , 2018c Support vector machines (SVM), which were introduced by Vapnik (1995), are a relatively new structure in the data-driven prediction field. The SVM is based on the structural risk minimization (SRM), instead of the empirical risk minimization (ERM) of ANNs, which can cause the solution to be captured in a local minimum and the network over fitted.…”

Estimation of Groundwater Level Fluctuations Using Neuro-Fuzzy and Support Vector Regression Models

“…Artificial intelligence methods collect information about the samples, make generalizations and then make decisions about the samples by using the information they have learned compared to the samples they have never seen before. Recently, artificial intelligence methods have begun to be frequently used in modeling the suspended sediment [1][2][3][4], dam reservoir level [5][6][7], density flow plunging [8], dam reservoir volume [9][10][11], sand bar crest [12], evaporation [13][14], and groundwater level [15][16], and in many different disciplines -areas [17][18][19][20][21][22][23][24][25][26]. Mohanty et al [27] investigated that artificial neural network (ANN) approach to the weekly forecasting of groundwater levels at river basin.…”