Artificial Neural Network models for estimating daily solar global UV, PAR and broadband radiant fluxes in an eastern Mediterranean site C.P. Jacovides a, ⁎, F.S. Tymvios b , J. Boland c , M. Tsitouri b a Department of Environmental Physics-Meteorology, Athens University Campus, Builds. PHYS-5, Athens 15784, Greece b Meteorological Service of Cyprus, Nicosia, Cyprus c Barbara Hardy Institute & School of Information Technology and Mathematical Sciences, University of South Australia, Australia article info abstract Article history: Received 13 March 2013 Received in revised form 5 September 2013 Accepted 5 November 2013 Available online xxxx In this paper, simple Artificial Neural Network (ANN) models for estimating daily solar global broadband as well as solar spectral global UV and PAR radiant fluxes have been established. The data used in this analysis are global ultraviolet UV (G UV ), global photosynthetic photon flux density (PPFD-Q P ), broadband global radiant flux (G h ), extraterrestrial radiant flux (G 0 ), air temperature (T), relative humidity (rh), sunshine duration (n), theoretical sunshine duration (N), precipitable water (w) and ozone column density (O 3 ). 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 G UV ,Q P and G h solar radiant fluxes. Firstly, a set of 2 × 365 point (2 years) has been used for training each network-model, whereas a set of 365 point (1 year) has been engaged for testing and validating the ANN-models. It has been found that the ANN-models' accuracy depends on the parameters employed as well as spectral range considered. Comparisons between proposed ANN-models and conventional regression models revealed that the results of both methods are statistically significant. On closer examination of many error measures, though, it is clear that the ANN-models perform better overall. From this point of view, it turned out that the neural network technique is better suited further suggesting that the ANN methodology is a promising and a more accurate tool for estimating both broadband and spectral radiant fluxes. © 2013 Elsevier B.V. All rights reserved. Keywords: ANN-models Spectral PAR and UV solar radiant fluxes Conventional regression models 1. Introduction The increasing global energy demands and the increasing fossil fuel prices stimulate countries to downsize energy consumption and exploit renewable energy sources. Addition- ally, environmental problems caused by mass consumption of fossil energy (e.g. global warming) are also reason for concern. Reliable solar radiant flux measurements for estimating the dynamic behavior of solar energy systems and for simulating long-term operations are required. For thermal analysis perfor- mance through transient simulation algorithms, a crucial input is the solar radiant energy components incident on the collector surfaces. Nevertheless, direct measurements of solar radiant components at the site of interest are not available in many instances so only the use of either modeling simulations or empirically derived estimates can fill this gap (Lopez et al., 2001; Schiller, 2006; Jacovides et al., 2007). Moreover, during the last two decades the solar radiant component (G h ) has been approximated by using the Artificial Neural Network (ANN) method which constitutes now a widely accepted technique offering an alternative way to synthesize complex problems of the solar energy. In the literature there exist numerous articles for modeling global radiant flux reaching the ground by means of neural network technique (Kalogirou, 2000; Mellit et al., 2005; Tymvios et al., 2005; Rehman and Mohandes, 2008; Benghanem et al., 2009; Karoro et al., 2011; Mohandes, 2012; Notton et al., 2013; and others). Atmospheric Research xxx (2013) xxx–xxx ⁎ Corresponding author. Tel.: +30 2107276931; fax: +30 2107295281. E-mail address: kiakovid@phys.uoa.gr (C.P. Jacovides). ATMOS-03014; No of Pages 8 0169-8095/$ – see front matter © 2013 Elsevier B.V. All rights reserved. http://dx.doi.org/10.1016/j.atmosres.2013.11.004 Contents lists available at ScienceDirect Atmospheric Research journal homepage: www.elsevier.com/locate/atmos Please cite this article as: Jacovides, C.P., et al., Artificial Neural Network models for estimating daily solar global UV, PAR and broadband radiant fluxes in an eastern Mediterranea..., Atmos. Res. (2013), http://dx.doi.org/10.1016/j.atmosres.2013.11.004