Open AccessEstimation of future Reference Crop Evapotranspiration Using Soft Computing Techniques
Author(s) -
L Gowri,
K. Sasireka
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.12.16438
Subject(s) - evapotranspiration , artificial neural network , water cycle , estimation , computation , soft computing , computer science , component (thermodynamics) , environmental science , machine learning , algorithm , engineering , ecology , systems engineering , biology , physics , thermodynamics
Estimation of Evapotranspiration forms the basis for computation of irrigation requirement of crop, and also it is considered as one of the vital component of hydrological cycle. This study describes the conceptual outline and implementation to test the ability of an artificial neural network (ANN) for accurate estimation of reference evapotranspiration (ETo). There are many conventional methods like FAO modified Penman method, temperature-based and radiation-based empirical methods are used to estimate (ETo). Among the conventional methods, Thronthwaite method and Hargreaves method perform well in the selected region. An ANN network is trained to recognize patterns of the daily meteorological variables and their corresponding evapotranspiration which is estimated using FAO-modified Penman method. The advantage of using ANN technique is the network’s ability to use minimum number of meteorological parameters, hence economical.