Reference evapotranspiration modeling using radial basis function neural network in different agro-climatic zones of Chhattisgarh

Diwakar Naidu Diwakar Naidu,Babita Majhi Babita Majhi

doi:10.54386/jam.v21i3.254

Abstract

Precise estimation of evapotranspiration (ET) is extremely essential for efficient utilization of available water resources. Among the empirical models, FAO-Penman-Monteith equation (FAO-PM) is considered as standard method to determine reference evapotranspiration (ET ). In developing countries like India, application of FAO-PM equation for ET estimation has certain limitations due to unavailability of specific data requirements. Several empirical models such as Hargreaves, Turc, Blaney-Criddle etc., arealso considered for ET estimation. However, ET estimates obtain with these models are not comparable with benchmark FAO-PM ET . To address this issue, potential of radial basis function neural network (RBFNN) is investigated to estimate FAO-PM ET . Result obtained with proposed RBFNN models are compared with equivalent multi-layer artificial neural network (MLANN) and empirical approach of Hargreaves, Turc and Blaney-Criddle. Lower RMSE values obtained with RBFNN and MLANN models is an indication of improved performance over empirical models. Similarly, higher R2 and Efficiency Factor obtained with RBFNN and MLANN models also approves the superiority of machine learning techniques over empirical models. Among the two machine learning techniques, RBFNN models performed better as compared to MLANN. In a nut shell, proposed RBFNN models can simulate FAO-PM ET even with limited meteorological parameters and consistence degree of accuracy level.

Highlights

Evapotranspiration (ET) is considered as one of most important parameter for agro-climatic analyses such as determination of crop water requirement and computation of water balance parameters
Simulations studies are carried out to investigate the potential of proposed radial basis function neural network (RBFNN) models as compared to corresponding multi-layer artificial neural network (MLANN) and equivalent empirical models (Hargreaves, Turc and BlaneyCriddle) for estimating FAO-Penman-Monteith equation (FAO-PM) ET0
The investigation was carried out with an objective to examine the potential of RBFNN models for estimating FAOPM ET0 with available climatic data

Summary

Introduction

Evapotranspiration (ET) is considered as one of most important parameter for agro-climatic analyses such as determination of crop water requirement and computation of water balance parameters. Shiri et al (2014) has computed ET0 estimates using heuristic data driven (HDD) models such as ANN, ANFIS, SVM and gene expression programming (GEP) for a wide range of weather stations in Iran and compared the same with corresponding empirical models (Hargreaves–Samani, Makkink, Priestley–Taylor and Turc). SVM-Wavelet and support vector machine-firefly algorithm (SVM-FFA) methods produced higher correlation coefficient with ET0 as compared to Artificial Neural network (ANN) and Genetic programming (GP) computational methods. They have found that HDD models generally outperformed empirical models, whereas among the HDD models GEP-based model produced higher accuracy. Significant finding of the study are given in the concluding section

Methods

Results

Conclusion