STM Article Repository

Design of an ATC Tool for Conflict Detection Based on Machine Learning Techniques Javier Alberto Pérez-Castán http://orcid.org/0000-0002-0112-9792 Luis Pérez-Sanz Lidia Serrano-Mira http://orcid.org/0000-0002-8172-6326 Francisco Javier Saéz-Hernando Irene Rodríguez Gauxachs http://orcid.org/0000-0001-6080-8472 Víctor Fernando Gómez-Comendador http://orcid.org/0000-0003-0961-2188

Given the ongoing interest in the application of Machine Learning (ML) techniques, the development of new Air Traffic Control (ATC) tools is paramount for the improvement of the management of the air transport system. This article develops an ATC tool based on ML techniques for conflict detection. The methodology develops a data-driven approach that predicts separation infringements between aircraft within airspace. The methodology exploits two different ML algorithms: classification and regression. Classification algorithms denote aircraft pairs as a Situation of Interest (SI), i.e., when two aircraft are predicted to cross with a separation lower than 10 Nautical Miles (NM) and 1000 feet. Regression algorithms predict the minimum separation expected between an aircraft pair. This data-driven approach extracts ADS-B trajectories from the OpenSky Network. In addition, the historical ADS-B trajectories work as 4D trajectory predictions to be used as inputs for the database. Conflict and SI are simulated by performing temporary modifications to ensure that the aircraft pierces into the airspace in the same time period. The methodology is applied to Switzerland’s airspace. The results show that the ML algorithms could perform conflict prediction with high-accuracy metrics: 99% for SI classification and 1.5 NM for RMSE.
01 26 2022 67 aerospace9020067 SESAR Joint Undertaking http://dx.doi.org/10.13039/ 892618 https://creativecommons.org/licenses/by/4.0/ 10.3390/aerospace9020067 https://www.mdpi.com/2226-4310/9/2/67 https://www.mdpi.com/2226-4310/9/2/67/pdf SESAR Joint Undertaking SESAR 2020 Concept of Operations https://ec.europa.eu/research/participants/documents/downloadPublic?documentIds=080166e5b6d2b912&appId=PPGMS European Atm Master Plan—Digitalising Europe’s Aviation Infraestructure 2019 10.1017/S0373463300019068 10.1017/S0373463300047196 10.1016/j.ast.2018.11.030 10.1016/j.ssci.2018.08.018 10.1287/trsc.7.2.158 10.1016/j.trc.2018.05.031 10.1016/j.jairtraman.2008.04.008 10.1109/6979.898217 10.1177/0954410011417347 10.1177/0954410019831198 10.2514/1.51898 The FLY AI Report Demystifying and Accelerating AI in Aviation/ATM 2020 Geron Hands-On Machine Learning with Scikit-Learn and TensorFlow 2017 Mitchell Machine Learning 1997 10.1109/TITS.2015.2437452 10.1016/j.trc.2018.08.012 Fernández DART: A machine-learning approach to trajectory prediction and demand-capacity balancing SESAR Innov. Days 2017 10.1109/TSMCC.2011.2161285 10.1029/2019EA000740 10.1177/0954410012439975 10.3390/e22020159 10.1016/j.trc.2008.12.002 The OpenSky Network API https://opensky-network.org/apidoc/index.html Boeing Commercial Airplanes Statistical Summary of Commercial Jet Airplane Accidents World Wide Operations 1959–2018 http://www.boeing.com/commercial/safety/investigate.html Geographiclib https://geographiclib.sourceforge.io/html/python AISA Concept of Operations for AI Situational Awareness https://aisa-project.eu/downloads/AISA_D2.1_CONOPS.pdf Buitinck API design for machine learning software: Experiences from the scikit-learn project arXiv 2013 PyCaret https://pycaret.org 10.1145/2786984.2786995Given the ongoing interest in the application of Machine Learning (ML) techniques, the development of new Air Traffic Control (ATC) tools is paramount for the improvement of the management of the air transport system. This article develops an ATC tool based on ML techniques for conflict detection. The methodology develops a data-driven approach that predicts separation infringements between aircraft within airspace. The methodology exploits two different ML algorithms: classification and regression. Classification algorithms denote aircraft pairs as a Situation of Interest (SI), i.e., when two aircraft are predicted to cross with a separation lower than 10 Nautical Miles (NM) and 1000 feet. Regression algorithms predict the minimum separation expected between an aircraft pair. This data-driven approach extracts ADS-B trajectories from the OpenSky Network. In addition, the historical ADS-B trajectories work as 4D trajectory predictions to be used as inputs for the database. Conflict and SI are simulated by performing temporary modifications to ensure that the aircraft pierces into the airspace in the same time period. The methodology is applied to Switzerland’s airspace. The results show that the ML algorithms could perform conflict prediction with high-accuracy metrics: 99% for SI classification and 1.5 NM for RMSE.