Global NEST Journal, Vol 14, No 4, pp 532-539, 2012 Copyright© 2012 Global NEST Printed in Greece. All rights reserved THERMAL COMFORT ESTIMATION IN RELATION TO DIFFERENT ORIENTATION IN MOUNTAINOUS REGIONS IN GREECE BY USING ARTIFICIAL NEURAL NETWORKS K.I. CHRONOPOULOS 1 1 Laboratory of Physics, Division of Chemical and Physical A.P. KAMOUTSIS 2, * Sciences, Department of Sciences, Agricultural University of Athens A.S. MATSOUKIS 2 75, Iera Odos Str., 118 55 Athens, Greece 2 Laboratory of General and Agricultural Meteorology Division of Geological Sciences and Atmospheric Environment, Department of Sciences, Agricultural University of Athens, 75, Iera Odos Str., 118 55 Athens, Greece Received: 05/07/10 *to whom all correspondence should be addressed: Accepted: 17/02/12 e-mail: akamoutsis@aua.gr ABSTRACT This study focuses on the estimation of thermal comfort conditions in a high alt. site (1455 m) in Apodotia (MA), Greece, by using the MLP neural network model. This estimation is based on the air temperature (t) and relative humidity (f) data of the middle (1078-1163 m) and of the low altitude levels (816-862 m) in relation to different orientations in MA. Also, the MLP model was applied on the top of the Mt. Koromilies (alt. 1350 m) for the estimation of thermal comfort conditions based on the t and f of a site (alt. 797 m) on the northern slope of Mt. Parnassos. In both MA and Parnassos regions the “Cold” and “Comfortable” classes of thermal comfort prevailed. The MLP model provided more satisfactory estimations of the THI values from the t and f of the middle alt. level compared to the respective estimations from the low alt. level. The model provides less accurate estimations of the THI values at 1455 m alt., in the case of sites located near watery surfaces in MA. The application of the MLP model in the case of the Mt. Koromilies, in Parnassos indicated more accurate estimations of the THI values compared to the respective estimations in Apodotia. KEYWORDS: multilayer perceptron model, air temperature, relative humidity, thermohygrometric index, Apodotia, Parnassos. INTRODUCTION Mountainous regions are remote from major centers of human activity (Barry, 2001) and they are often considered as marginal from an economical point of view (Price, 1995). However, in recent years these regions have become attractive destinations of large numbers of people for their recreation and tourism (Beniston, 2003). The aforementioned regions are characterized by distinct relief elements such as summits, slopes and valleys (Barry, 2001). The amounts of radiation ending on inclined ground surface depends on the solar declination (time of year), the solar altitude (time of day), the cloudiness, as well as on the direction, the angle and the azimuth of the slope (Geiger et al., 2003). The differences in the total monthly solar radiation for the various slopes with different orientations affect air temperature of the layers near the ground surface. It has been reported that the eastern slopes are cooler than the western ones (Seemann, 1979). Thermal comfort may be expressed by a large number of biometeorological indices and it is used to quantify the integral effects of the heat exchange between the human body and the thermal environment (Nastos and Matzarakis, 2006; Jendritzky and de Dear, 2009). The thermal comfort conditions can be evaluated by using a widely and easily used biometeorological index, the thermohygrometric index which requires only temperature and humidity data (Toy et al., 2007). The