Supervised Neural Network with multilevel input layers for predicting of air traffic delays

Air delay is a problem in most airports around the world, resulting in increased costs for airlines and discomfort for passengers. Air Traffic Flow Management (ATFM) programs were implemented with the main objective to reduce the delay levels in the whole air transportation sector. The question is to find a suitable way to predict possible delay scenarios to better apply ATFM measures. The present work seeks to enrich the academic literature on the subject and aims to present the application of Artificial Neural Networks (ANN) to a prediction model of delays in the air route between São Paulo (Congonhas) - Rio de Janeiro (Santos Dumont). The configuration of ANN exerts a great influence on its predictive power. To better adjust the parameters of the proposed ANN and for the hyperparameterization of the network to occur, the Random Search technique is used. By using the recall, precision and Fscore metrics in the performance measurement, the prediction results show the satisfactory in the case study.