Predictability of Fog Visibility with Artificial Neural Network for Esenboga Airport

Fog event affects air, land and sea transportation adversely by reducing visibility, thus causes economic loss. Besides, it has an important place in the planning of constructions. For this reason, it is very important to predict reducing visibility due to the fog event. In this study, visibility prediction was made with artificial neural networks and validations were made for Esenbo？a Airport. Temperature, dew point temperature, pressure, wind speed and relative humidity, those are the most important parameters for fog occurrence, were used for 2013-2015 years to train in artificial neural network. We selected only January, February, November and December months those are the foggiest months for Esenbo？a airport. Then, the whole data for 2016-2017 years regardless of fog were used for validation of the results. As a result, we found R=0.80 for the test part of 2013-2015 years, R=0.41 and RMSE = 2652m for all data of the 2016 year, and R = 0.53 and RMSE = 2464m for all data of the 2017 year. The error rate (R = 0.80) for the test part was found to be acceptable. However, consistencies for the years 2016 and 2017, when all data were tested regardless of fog and haze, were found to when all data were tested regardless of fog and haze, were found to be as below expectations