Generalized regression neural networks for evapotranspiration modelling

Abstract

The potential is investigated of the generalized regression neural networks (GRNN) technique in modelling of reference evapotranspiration (ET 0 ) obtained using the FAO Penman-Monteith (PM) equation. Various combinations of daily climatic data, namely solar radiation, air temperature, relative humidity and wind speed, are used as inputs to the ANN so as to evaluate the degree of effect of each of these variables on ET 0 . In the first part of the study, a comparison is made between the estimates provided by the GRNN and those obtained by the Penman, Hargreaves and Ritchie methods as implemented by the California Irrigation Management System (CIMIS). The empirical models were calibrated using the standard FAO PM ET 0 values. The GRNN estimates are also compared with those of the calibrated models. Mean square error, mean absolute error and determination coefficient statistics are used as comparison criteria for the evaluation of the model performances. The GRNN technique (GRNN 1) whose inputs are solar radiation, air temperature, relative humidity and wind speed, gave mean square errors of 0.058 and 0.032 mm 2 day , and determination coefficients of 0.985 and 0.986 for the Pomona and Santa Monica stations (Los Angeles, USA), respectively. Based on the comparisons, it was found that the GRNN 1 model could be employed successfully in modelling the ET 0 process. The second part of the study investigates the potential of the GRNN and the empirical methods in ET 0 estimation using the nearby station data. Among the models, the calibrated Hargreaves was found to perform better than the others.

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

“…Hence, in the past decade some artificial intelligence and data mining methods are used to estimate daily ET, evaporation and pan evaporation. For instance M5T method is used to estimate Reference ET (Pal, Deswal 2009), artificial neural networks for ET prediction (Kumar et al 2011) and generalized neural networks for ET prediction (Kişi 2006).…”

Discussion of “Evapotranspiration modelling using support vector machines”

“…raised the issue of unreported missing records in data sets used by Kisi (2006) to model reference crop evapotranspiration in California, USA. It was argued that if a particular data set had some missing observations, that fact should be reported clearly (particularly in journal papers) even if the number of missing cases was small, so that the reported results are comparable with other studies.…”

“…It was argued that if a particular data set had some missing observations, that fact should be reported clearly (particularly in journal papers) even if the number of missing cases was small, so that the reported results are comparable with other studies. Kisi (2007), in response to this challenge, subsequently disclosed that a linear regression model had actually been used to provide estimated records for a 12-day period and this too should have been reported in the original paper, not only to ensure others could repeat the work, but also because, through this data-infilling process, the authors had introduced an untested assumption of linearity in the data. Abrahart et al (2009) questioned the operational processes involved in the removal of incomplete entries by Aytek et al (2008); also modelling reference crop evapotranspiration in California.…”

An explicit neural network formulation for evapotranspiration

“…It was observed that only a few studies existed in the literature related to the use of ANNs in modelling ET 0 . For example, Kumar et al (2002) studied a multi-layer NN using a backpropagation training algorithm for the estimation of ET 0 ; Sudheer et al (2003) modelled ET 0 using a radial basis NN with limited data; Trajkovic et al (2003) examined a radial basis type NN in forecasting ET 0; Trajkovic (2005) used a temperature-based radial basis NN for modelling FAO 56 ET 0 ; and Kişi (2006) applied the generalized regression neural networks (GRNN) to ET 0 estimation. The use of ANNs has recently been under discussion (Aksoy et al, , 2008Koutsoyiannis, 2007).…”