A Machine Learning Framework to Predict General Aviation Traffic Counts

General Aviation traffic prediction is a major concern for Air Navigation Service Providers as it has a direct impact on air traffic flow and capacity management measures. However, today, few tools are available to address this issue. This paper proposes a methodology to predict GA traffic based on Machine Learning models training with historical data. Initial promising results are obtained on Nice Cote D’Azur Terminal Control Center sectors case study using meteorological and calendar data with an increase of the prediction performance of 25% compared to current tools used in operation.