Classification of Weather Impacts on Airport Operations

Classification of weather impacts on airport operations will allow efficient consideration of local weather events in network-wide analysis. We use machine learning approaches in our contribution to correlate weather data from meteorological reports and airport performance data, which contains flight plan data with scheduled, actual movements and delays. In particular, we applied unsupervised learning to cluster performance impacts at the airport and classify the respective weather data with recurrent and convolutional neural networks. Thus, our machine learning approach allows for both an appropriate matching of decreased airport performance during the occurrence of local weather events as well as a delay estimation based on weather forecast and flight plans. This paper serves to illustrate the potential of classifications with machine learning methods and is the basis for further investigations on this topic. We update current expert-based weather classifications and provide a better understanding of local and network-wide interdependencies in air transportation.