An application of artificial neural network models to estimate air temperature data in areas with sparse network of meteorological stations

Abstract

In this work artificial neural network (ANN) models are developed to estimate meteorological data values in areas with sparse meteorological stations. A more traditional interpolation model (multiple regression model, MLR) is also used to compare model results and performance. The application site is a canyon in a National Forest located in southern Greece. Four meteorological stations were established in the canyon; the models were then applied to estimate air temperature values as a function of the corresponding values of one or more reference stations. The evaluation of the ANN model results showed that fair to very good air temperature estimations may be achieved depending on the number of the meteorological stations used as reference stations. In addition, the ANN model was found to have better performance than the MLR model: mean absolute error values were found to be in the range 0.82-1.72 degrees C and 0.90-1.81 degrees C, for the ANN and the MLR models, respectively. These results indicate that ANN models may provide advantages over more traditional models or methods for temperature and other data estimations in areas where meteorological stations are sparse; they may be adopted, therefore, as an important component in various environmental modeling and management studies.

Implementation of an intelligent sensor for measurement and prediction of solar radiation and atmospheric temperature

“…Chronopoulos et al (2008) In addition, it is mentioned that the ability of ANN models to take into account any non-linear relationships among meteorological parameters, may provide advantages over traditional methods.…”

Thermal comfort estimation in relation to different orientation in mountainous regions in Greece by using artificial neural networks

“…levels taking into account the measurement time. Recent studies showed that MLP models can be effectively used to evaluate microclimatic conditions in remote mountainous canyons (Chronopoulos et al, 2008;2010).…”

“…A robust computational technique, the artificial neural network (ANN) approach, has been applied in many cases due to the advantages of iteration and learning ability, compared to simple regression techniques (Shank et al, 2008). It has been reported that the application of ANN models resulted in satisfactory estimations of air temperature in comparison with multiple linear regression approaches (Chronopoulos et al, 2008;Ustaoglou et al, 2008). Also, these models have been applied successfully to estimate the thermal comfort conditions in mountainous forested areas (Kamoutsis et al, 2010).…”

Estimation of microclimatic data in remote mountainous areas using an artificial neural network model-based approach

“…Recently ANN models have started to be applied in various aspects of the atmospheric sciences, (Benvenuto et al, 2000;Melas et al, 2000;Mihalakakou et al, 2004;Perez and Reyes, 2006;Tsiros et al, 2009). ANN model applications to meteorological data values estimations are, in general, very few (Cheng et al, 2002;Dimopoulos et al, 2005;Chronopoulos et al, 2008).…”