Abstract
In this study, Artificial Neural Network (ANN) techniques for estimating daily global UV, PAR and broadband solar radiant fluxes have been developed. The data used in this analysis are global ultraviolet UV (GUV), global photosynthetic photon flux density (PAR-GPAR), broadband global radiant flux (G), extraterrestrial radiant flux E0, air temperature (T), relative humidity (Rh), sunshine duration (n), daylength (N), precipitable water (w) and O3 column density. By using different combinations of the above variables as inputs, numerous ANN-models have been developed. For each model, the output is the daily global UV, PAR and broadband radiant fluxes. Firstly, a set of 2 × 365 points (2 years) has been used for training each network–model, whereas a set of 365 points (1 year) has been engaged for testing and validating the ANN-models. It has been found that ANN-models’ accuracy depends on the parameters used as well as spectral range considered. Moreover, results obtained reveal that the ANN methodology is a promising tool for estimating both broadband and spectral radiant fluxes.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
