Application of Artificial Neural Network Approach for Estimating Reference Evapotranspir

Abstract

The process of evapotranspiration (ET) is a vital part of the water cycle. Exact estimation of the value of ET is necessary for designing irrigation systems and water resources management. Accurate estimation of ET is essential in agriculture, its over-estimation leads to cause the waste of valuable water resources and its underestimation leads to the plant moisture stress and decrease in the crop yield. The well known Penman-Monteith (PM) equation always performs the highest accuracy results of estimating reference Evapotranspiration (ET0) among the existing methods is without any discussion. However, the equation requires climatic data that are not always available particularly for a developing country. ET0 is a complex process which is depending on a number of interacting meteorological factors, such as temperature, humidity, wind speed, and radiation. The lack of physical understanding of ET0 process and unavailability of all appropriate data results in imprecise estimation of ET0. Over the past two decades, artificial neural networks (ANNs) have been increasingly applied in modeling of hydrological processes because of their ability in mapping the input–output relationship without any understanding of physical process. This paper investigates for the first time in the semiarid environment of Junagadh, the potential of an artificial neural network (ANN) for estimating ET0 with limited climatic data set.

ANNs, SVM and empirical methods for modelling reference evapotranspiration with limited climatic data in the city of Xai-Xai, Mozambique / ANNs, SVM e métodos empíricos para modelar a evapotranspiração de referência com dados climáticos limitados na cidade de Xai-Xai, Moçambique

“…The positions occupied by the JRICH and MAKK models (Table 5) in relation to SVM which also appears to be a good tool for modeling ETo, is probably explained by the fact previous models have used Rs as one of the input variables, that did not occur in SVM. Several authors observed that the inclusion of Rs in the architectures of MLT improved performance (WEN et al, 2015;VYAS and SUBBAIAH, 2016). On the other hand, the results of the present research showed a strong positive correlation between Rs and ETo obtained from the method of PMF 56 (r = 0.99) in relation to the other variables used in MLT (Figure 3).…”

Real-time monitoring of water requirement in protected farms by using polynomial neural networks and image processing

“…The important feature of the PNN International GMDH algorithm is its ability to identify both linear and nonlinear polynomial models using the same approach (Tetko et al 2000). The PNN has been applied for enhancing performance of GPS in electric systems (Mosavi 2009), enhancing performance of GPS-based line fault location (Mosavi 2008) modeling complex hydrological processes (Wang et al 2005), exchange rate forecasting (Ghazali et al 2008) to financial time series prediction (Ghazali et al 2006), fault detection, isolation, estimation, and reconfigurable flight control (Barron et al 1990), for estimating reference evapotranspiration in Gujarat, India (Vyas and Subbaiah 2016), for sustainable irrigation planning of the Jayakwadi irrigation project, Maharashtra, India (Raju et al 2006). The capability of PNN in identification of optimal number of hidden layer which will be suitable for learning a problem given in the available data set based on a fitness function and the self-adaptation feature for selecting the best training algorithm from a set of programming techniques and subsequently the high level of accuracy retrieved in various studies which applied PNN for prediction purposes, encouraged the authors to use PNN model to estimate WRI.…”