In this study, ten-minute meteorological data-sets recorded at Burgos, Spain, are used to develop models of
Photosynthetic Active Radiation (PAR) following two different procedures: multilinear regression and Artificial
Neural Networks. Ten Meteorological Indices (MIs) are chosen as inputs to the models: clearness index (kt),
diffuse fraction (kd), direct fraction (kb), Perez’s clear sky index (ε), brightness index (Δ), cloud cover (CC), air
temperature (T), pressure (P), solar azimuth cosine (cosZ), and horizontal global irradiation (RaGH). The
experimental data are clustered according to the sky conditions, following the CIE standard sky classification. A
previous feature selection procedure established the most adequate MIs for modelling PAR in clear, partial and
overcast sky conditions. RaGH was the common MI used by all models and for all sky conditions. Additional
variables were also included: the geometrical parameter, cosZ, and three variables related to the sky conditions,
kt, ε, and Δ. Both modelling methods, multilinear regression and ANN, yielded very high determination coefficients (R2) with very close results in the models for each of the different sky conditions. Slight improvements
can be observed in the ANN models. The results underline the equivalence of multilinear regression models and
ANN models of PAR following previous feature selection procedures.
