Air Temperature Estimation by Using Artificial Neural Network Models in the Greater Athens Area, Greece

Abstract

Air temperature (T) data were estimated in the regions of Nea Smirni, Penteli, and Peristeri, in the greater Athens area, Greece, using the T data of a reference station in Penteli. Two artificial neural network approaches were developed. The first approach, MLP1, used the T as input parameter and the second, MLP2, used additionally the time of the corresponding T. One site in Nea Smirni, three sites in Penteli, from which two are located in the Pentelikon mountain, and one site in Peristeri were selected based on different land use and altitude. T data were monitored in each site for the period between December 1, 2009, and November 30, 2010. In this work the two extreme seasons (winter and summer) are presented. The results showed that the MLP2 model was better (higher and lower MAE) than MLP1 for the T estimation in both winter and summer, independently of the examined region. In general, MLP1 and MLP2 models provided more accurate T estimations in regions located in greater distance (Nea Smirni and Peristeri) from the reference station in relation to the nearby Pentelikon mountain. The greater distance T estimations, in most cases, were better in winter compared to summer.

Estimating Inside Air Temperature of a Glasshouse Using Statistical Models

“…The more sophisticated model, D, based on MLP method, in which the input parameters were both T at ATM and T at ATM-2 of S1, produced better results than any other model we tested, in terms of the highest R 2 and lowest MAE (Figure 2b). It has been reported that the introduction of ATM as an input in ANN models, produces better results in an urban area, concerning the estimation of T. 13 The ability of the ANNs to take into account the nonlinear characteristics of the T data, produced better results than the LRs models, especially when we used combined input of the same data with a time lag of two hours. This clear improvement when using time lag can possibly be explained by the distance of the two sites, combined with the influence of the terrain profile.…”

“…These models were named A, B, C and D. In model A, a SLR analysis was used, while in model B, a MLR analysis was adopted. Regarding models C and D, custom multilayer perceptrons (MLPs), which belong to the most commonly used ANN architectures 13 , were used.…”

Developing machine learning models for air temperature estimation using MODIS data

“…The results of the proposed model showed that the best coefficient of determination and Root Mean Squared Error were 0.98, and 0.4 ºC, respectively. Kamoutsis et al (2013) estimated mean temperature in Greece (urban and adjacent mountain regions) using data of reference stations, with ANN, for one year (December 2009-November 2010). They presented results with determination coefficients between 0.74 and 0.93.…”

“…These techniques include Bayesian-based modeling, support vector regression, ANN and RF (Kamoutsis et al, 2013, Noi et al, 2017, Zhao et al, 2019.…”