Machine Learning Approach to Estimate Ultraviolet Irradiance from Solar Radiation Data

One primary cause of degradation for materials exposed to the outdoors is ultraviolet (UV) light. To estimate their rate of degradation and determine their longevity (service life), truthful quantification of the UV irradiation incident on their surfaces is needed. In this paper, several neural models are proposed to estimate three UV components based on the broadband global horizontal irradiance and various atmospheric constituents. Using spectral results obtained with the SMARTS model for a large variety of atmospheric conditions and sun positions, three groups of experiments are carried out: the first one is designed to estimate the total UV irradiance at the surface (280–400 nm), whereas the second and third groups aim at estimating its UV-A and UV-B fractions, respectively. The results generally show a good prediction performance, particularly for the first two groups.