A new journal paper on the research line of weather prediction and artificial intelligence has been published in the Aircraft Operations Lab. Authored by Iván Martínez as main writer, the paper “Predicting Air Traffic Flow Management hotspots due to weather using Convolutional Neural Networks” addresses the pressing issue of understanding how convective weather impacts air traffic flows, using three different deep learning model architectures to detect traffic hotspots subject to regulation due to weather conditions.
Abstract
Convective weather is a major source of disruption to air traffic operations, responsible for roughly one third of en-route delay in the network. Understanding how weather impacts air traffic flows is an important first step in improving Air Traffic Flow Management (ATFM) operations during convective weather events. In this research we exploit advances in machine learning to find the spatial correlations between convective weather and regulated air traffic flows. Our approach utilises historical satellite observations and traffic data from the summers of 2018 and 2019. Three deep learning model architectures are trained to detect traffic hotspots subject to regulation due to weather conditions. We also establish a baseline indicator to assess prediction quality. The weather and traffic data are transformed into images using a 2D grid covering a substantial portion of Europe, with a high-resolution spatial resolution. The temporal dimension is considered through hourly or 15-minute time windows, depending on the model architecture. By integrating this information, our models are able to capture relevant correlations effectively. Results indicate a clear correlation between weather and regulated traffic and reveal that our machine learning model is able to learn from the spatial correlations in the data and thus characterise the geographical areas where traffic volumes regulated due to convective weather are expected to appear during Air Traffic Flow Management practice.
Predicting Air Traffic Flow Management hotspots due to weather using Convolutional Neural Networks.Iván Martínez, Javier García-Heras, Aniel Jardines, Alejandro Cervantes, Manuel Soler. Engineering Applications of Artificial Intelligence. Volume 133, Part A, 2024, 108014, ISSN 0952-1976, https://doi.org/10.1016/j.engappai.2024.108014