Proceedings, 2020, OpenSky 2020

Crowdsourced data have played an increasing role in research in the sciences over the past decades. From their early instantiations in the 1990s to the search for extraterrestrial intelligence, the concepts of crowdsourcing and citizen science have gained renewed popularity with the broad availability of big data systems. The OpenSky Network has been a poster child of the successful use of crowdsourced data in research and citizen science for many years, with more than 150 peer-reviewed publications using its data. In this article, we follow the efforts made and the results achieved by the OpenSky Network as a non-profit organization with the mission to advance research in and around aviation. We examine the backgrounds and typical usage patterns of OpenSky’s users, both academic and non-academic. We further look at the social impact of air traffic data, particularly during the COVID-19 crisis, and finally examine ways to improve some existing gaps in the data. Full article

In this paper, we present an aircraft localization solution developed in the context of the Aircraft Localization Competition and applied to the OpenSky Network real-world ADS-B data. The developed solution is based on a combination of machine learning and multilateration using data provided by time synchronized ground receivers. A gradient boosting regression technique is used to obtain an estimate of the geometric altitude of the aircraft, as well as a first guess of the 2D aircraft position. Then, a triplet-wise and an all-in-view multilateration technique are implemented to obtain an accurate estimate of the aircraft latitude and longitude. A sensitivity analysis of the accuracy as a function of the number of receivers is conducted and used to optimize the proposed solution. The obtained predictions have an accuracy below 25 m for the 2D root mean squared error and below 35 m for the geometric altitude. Full article

As automatic dependent surveillance–broadcast (ADS-B) becomes more prevalent, the placement of on-ground sensors is vital for Air Traffic Control (ATC) to control the airspace. However, the current sensors are placed in an unstructured way that keeps some areas without coverage, and others are over-densified by sensors. Therefore, areas with coverage anomalies may cause issues that inhibit accurate ADS-B verifications as well as the availability of ADS-B altogether. In this paper, we tackle the ADS-B-specific optimal sensor placement (OSP) problem. Of importance are both the optimal coverage and the secure and accurate verification of received ADS-B messages. Specifically, we take into account the following objectives. First, we determine the minimum required number of sensors in order to cover a certain area like Europe. Second, we produce a better placement of the current sensors with respect to the security and accuracy of geometric dilution of precision (GDOP). Finally, we calculate how far the current sensor setup is from our derived optimal solution as well as the cost to reach the optimality. Our experiments show that the ideal fitness score for solving the OSP is below 0.1, meaning that the mean squared error (MSE) of the required and achieved GDOPs is significantly small, thus accomplishing a near-optimal setup. Full article

Mode S surveillance allows air traffic controllers to interrogate certain information from aircraft, such as airspeeds, turn parameters, target altitudes, and meteorological conditions. However, not all aircraft have enabled the same capabilities. Before performing any specific interrogation, the surveillance radar must acquire the transponder capabilities of an aircraft. This is obtained via the common usage Ground-initiated Comm-B (GICB) capabilities report (BDS 1,7). With this report, third-party researchers can further improve the identification accuracy of different Mode S Comm-B message types, as well as study the compliance of surveillance standards. Thanks to the OpenSky network’s large-scale global coverage, a full picture of current Mode S capabilities over the world can be constructed. In this paper, using the OpenSky Impala data interface, we first sample over one month of raw BDS 1,7 messages from around the world. Around 40 million messages are obtained. We then decode and analyze the GICB capability messages. The resulting data contain Comm-B capabilities for all aircraft available to OpenSky during this month. The analyses in this paper focus on exploring statistics of GICB capabilities among all aircraft and within each aircraft type. The resulting GICB capability database is shared as an open dataset. Full article

Increasing demands on a highly efficient air traffic management system go hand in hand with increasing requirements for predicting the aircraft’s future position. In this context, the airport collaborative decision-making framework provides a standardized approach to improve airport performance by defining operationally important milestones along the aircraft trajectory. In particular, the aircraft landing time is an important milestone, significantly impacting the utilization of limited runway capacities. We compare different machine learning methods to predict the landing time based on broadcast surveillance data of arrival flights at Zurich Airport. Thus, we consider different time horizons (look ahead times) for arrival flights to predict additional sub-milestones for n-hours-out timestamps. The features are extracted from both surveillance data and weather information. Flights are clustered and analyzed using feedforward neural networks and decision tree methods, such as random forests and gradient boosting machines, compared with cross-validation error. The prediction of landing time from entry points with a radius of 45, 100, 150, 200, and 250 nautical miles can attain an MAE and RMSE within 5 min on the test set. As the radius increases, the prediction error will also increase. Our predicted landing times will contribute to appropriate airport performance management. Full article

Go-arounds (GAs) are standard air traffic control procedures during which aircraft approach a runway but do not land. The incidence of a GA can subsequently affect the workload of flight crews and air traffic controllers, and might impact an airport runway’s throughput capacity. In this study, two different modeling methods for predicting the occurrence of GAs based on open-source Automatic Dependent Surveillance–Broadcast (ADS-B) and meteorological data are presented. A macroscopic model quantifies the probability of a GA within the next hour for an airport by applying a generalized additive model. A microscopic model employs a number of machine learning classifiers on trajectories of aircraft on approach in order to predict if a GA will be performed. Even though the results of the macroscopic model are promising, the information currently available to predict the probability of a GA is not detailed enough to achieve satisfactory predictions. Similarly, the microscopic model is capable of predicting 50% of all GAs, with false positive rate below 7%. Despite the limitations of the quality of the results, the authors are convinced that both modeling methods can be inspiring to other researchers and provide useful insights into the airport system under scrutiny. Full article

To support efforts to modernize aviation systems to be safer and more efficient, high-precision trajectory prediction and robust anomaly detection methods are required. The terminal airspace is identified as the most critical airspace for individual flight-level and system-level safety and efficiency. To support successful trajectory prediction and anomaly detection methods within the terminal airspace, accurate identification of air traffic flows is paramount. Typically, air traffic flows are identified utilizing clustering algorithms, where performance relies on the definition of an appropriate distance function. The convergent/divergent nature of flows within the terminal airspace makes the definition of an appropriate distance function challenging. Utilization of the Euclidean distance is standard in aviation literature due to little computational expense and ability to cluster entire trajectories or trajectory segments at once. However, a primary limitation in the utilization of the Euclidean distance is the uneven distribution of distances as aircraft arrive at or depart from the airport, which may result in skewed classification and inadequate identification of air traffic flows. Therefore, a weighted Euclidean distance function is proposed to improve trajectory clustering within the terminal airspace. In this work, various weighting schemes are evaluated, applying the HDBSCAN algorithm to cluster the trajectories. This work demonstrates the promise of utilizing a weighted Euclidean distance function to improve the identification of terminal airspace air traffic flows. In particular, for the selected terminal airspace, if trajectory points closer to the border of the terminal airspace, but not necessarily at the border, are weighted highest, then a more accurate clustering is computed. Full article

The large amount of aircraft trajectory data publicly available through open data sources like the OpenSky Network presents a wide range of possibilities for monitoring and post-operational analysis of air traffic performance. This contribution addresses the automatic identification of operational events associated with trajectories. This is a challenging task that can be tackled with both empirical, rule-based methods and statistical, data-driven approaches. In this paper, we first propose a taxonomy of significant events, including usual operations such as take-off, Instrument Landing System (ILS) landing and holding, as well as less usual operations like firefighting, in-flight refuelling and navigational calibration. Then, we introduce different rule-based and statistical methods for detecting a selection of these events. The goal is to compare candidate methods and to determine which of the approaches performs better in each situation. Full article

Major transportation surveillance protocols have not been specified with cyber security in mind and therefore provide no encryption nor identification. These issues expose air and sea transport to false data injection attacks (FDIAs), in which an attacker modifies, blocks or emits fake surveillance messages to dupe controllers and surveillance systems. There has been growing interest in conducting research on machine learning-based anomaly detection systems that address these new threats. However, significant amounts of data are needed to achieve meaningful results with this type of model. Raw, genuine data can be obtained from existing databases but need to be preprocessed before being fed to a model. Acquiring anomalous data is another challenge: such data is much too scarce for both the Automatic Dependent Surveillance–Broadcast (ADS-B) and the Automatic Identification System (AIS). Crafting anomalous data by hand, which has been the sole method applied to date, is hardly suitable for broad detection model testing. This paper proposes an approach built upon existing libraries and ideas that offers ML researchers the necessary tools to facilitate the access and processing of genuine data as well as to automatically generate synthetic anomalous surveillance data to constitute broad, elaborated test datasets. We demonstrate the usability of the approach by discussing work in progress that includes the reproduction of related work, creation of relevant datasets and design of advanced anomaly detection models for both domains of application. Full article

There is a growing dependence of critical and safety-of-life systems on the Global Navigation Satellite System (GNSS). GNSS interference events can cause severe impacts on aircraft safety, including unavailability of GNSS-based landing services. Therefore, it is important to be able to identify, localize, and remove interference sources that may cause these impacts. This project concentrates on events that affect the the airport environment and aims to provide improved situational awareness and safety for local airspace users. This paper contains three main sections: OpenSky ADS-B data processing, interference event characterization, and interference source localization. Specifically, we identified and removed incorrect timestamps from ADS-B ground receivers. We characterized the impact of interference events based on reported interference events that occurred at a San Francisco bay area airport. In addition, we designed a convex optimization model for localizing the interference sources given the ADS-B measurement. This article looks at common characteristics caused by the impact of interference events and shows a possible way to localize interference sources using ADS-B data. Full article

Global Navigation Satellite System Reflectometry (GNSS-R) provides a unique means of inferring geophysical conditions of the Earth’s surface without the need for costly, and often infeasible, in-situ climate monitoring systems. As part of NASA’s Cyclone Global Navigation Satellite System (CYGNSS) mission, and in conjunction with Air New Zealand, we are taking the novel approach of mounting a GNSS-R receiver on a commercial aircraft, which shall allow for an unprecedented collection of climate data over and around the islands of New Zealand. Such data include inundation and coastal dynamics, and soil moisture content and variability. We report back to the community how the OpenSky Network data support our climate monitoring research. We discuss how we use the historical database state-vectors to simulate and visualise the predicted geographical coverage of the airborne GNSS-R receiver. We also discuss how the live API can help monitor our payload in-flight, our investigations into the OpenSky ADS-B coverage over New Zealand, and our plans to expand the coverage. Full article

Aircraft noise, especially at takeoffs and landings, became a major environmental nuisance and a health hazard for the population around metropolitan airports. In the battle for a better quality of life, wellbeing, and health, aircraft noise models are essential for noise abatement, control, enforcement, evaluation, policy-making, and shaping the entire aviation industry. Aircraft noise models calculate noise and exposure levels based on aircraft types, engines and airframes, aircraft flight paths, environment factors, and more. Validating the aircraft noise model is a mandatory step towards the model credibility, especially when these models play such a key role with a huge impact on society, economy, and public health. Yet, no validation procedure was offered, and it turns out to be a challenging task. The actual, measured, aircraft noise level is known to be subject to statistical variation, even for the same aircraft type at the same situation and flight phase, executing the same flight procedure, with similar environmental factors and at the same place. This study tries to validate the FAA’s AEDT aircraft noise model, by trying to correlate the specific flight path of an aircraft with its measured noise level. The results show that the AEDT noise model underestimates the actual noise level, and four validation steps should be performed to correct or tune aircraft noise databases and flight profiles. Full article

Noise annoyance due to aircraft operations extends well beyond the 55 L_den noise contours as calculated according to the Environmental Noise Directive (END). Noise mapping beyond these contours will improve the understanding of the perception, annoyance and health impact of aircraft operations. OpenSky data can provide the spatial data to create an aircraft noise exposure map for lower exposure levels. This work presents the first step of region-wide noise exposure methodology based on open source data: detecting low L_Amax aircraft events in ambient noise using spectral noise measurements and correlating the detected noise events to the matching flights retrieved from the OpenSky database. In ISO 20906:2009, the specifications of noise monitoring near airports is standardized, using L_Aeq,1sec values for event detection. This limits the detection potential due to masking by other noise sources in areas with low maximum levels of aircraft noise and in areas with medium maximum levels of high ambient exposure areas. The typical lower detection limit in airport-based monitoring systems ranges from 55 to 60 L_Aeq,max, depending on the ambient levels. Using a detection algorithm sensitive to third-octave band levels, aircrafts can be detected down to 40 L_Amax in ambient noise levels of a similar magnitude. The measurement approach is opportunistic: aircraft events are detected in available environmental noise data series registered for other applications (e.g., road noise, industrial noise, etc.). Most of the measurement locations are not identified as high-exposure areas for aircraft noise. Detection settings can vary to match ambient noise levels to improve the correlation success. Full article

Voice communication is the main channel to exchange information between pilots and Air-Traffic Controllers (ATCos). Recently, several projects have explored the employment of speech recognition technology to automatically extract spoken key information such as call signs, commands, and values, which can be used to reduce ATCos’ workload and increase performance and safety in Air-Traffic Control (ATC)-related activities. Nevertheless, the collection of ATC speech data is very demanding, expensive, and limited to the intrinsic speakers’ characteristics. As a solution, this paper presents ATCO${}^2$, a project that aims to develop a unique platform to collect, organize, and pre-process ATC data collected from air space. Initially, the data are gathered directly through publicly accessible radio frequency channels with VHF receivers and LiveATC, which can be considered as an “unlimited-source” of low-quality data. The ATCO${}^2$ project explores employing context information such as radar and air surveillance data (collected with ADS-B and Mode S) from the OpenSky Network (OSN) to correlate call signs automatically extracted from voice communication with those available from ADS-B channels, to eventually increase the overall call sign detection rates. More specifically, the timestamp and location of the spoken command (issued by the ATCo by voice) are extracted, and a query is sent to the OSN server to retrieve the call sign tags in ICAO format for the airplanes corresponding to the given area. Then, a word sequence provided by an automatic speech recognition system is fed into a Natural Language Processing (NLP) based module together with the set of call signs available from the ADS-B channels. The NLP module extracts the call sign, command, and command arguments from the spoken utterance. Full article

To support integration of unmanned aerial systems into the airspace, the low altitude airspace needs to be characterized. Identifying the frequency of different aircraft types, such as rotorcraft or fixed wing single engine, given criteria such as altitude, airspace class, or quantity of seats can inform surveillance requirements, flight test campaigns, or simulation safety thresholds for detect and avoid systems. We leveraged observations of Automatic Dependent Surveillance-Broadcast (ADS-B) equipped aircraft by the OpenSky Network for this characterization. Full article