Nothing Special   »   [go: up one dir, main page]
Next Issue
Volume 60, IECB 2020
Previous Issue
Volume 58, WEF 2020
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Proceedings
Volume 59
Issue 1
proceedings-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Proceedings, 2020, OpenSky 2020

8th OpenSky Symposium 2020

Online| 12–13 November 2020

Volume Editors:
Xavier Olive, Université de Toulouse, France
Enrico Spinielli, Eurocontrol, Belgium
Rainer Koelle, Eurocontrol, Belgium

Number of Papers: 15
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Cover Story (view full-size image): Since its launch in 2013, the OpenSky Network has quickly evolved to a large-scale air traffic control data collection and sharing platform. With now more than 1000 sensors operated by volunteers [...] Read more.
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Other

8 pages, 1083 KiB  
Proceeding Paper
Research Usage and Social Impact of Crowdsourced Air Traffic Data
by Martin Strohmeier
Proceedings 2020, 59(1), 1; https://doi.org/10.3390/proceedings2020059001 - 1 Dec 2020
Cited by 3 | Viewed by 2522
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Coverage of OpenSky on 5 October 2014 (<b>top</b>) and 1 November 2020 (<b>bottom</b>). © Google Maps.</p> Full article ">Figure 2
<p>Publications with OpenSky data from 2014 to November 2020. Overall numbers as bars on the right vertical axis. Subfield numbers as lines on the left vertical axis. Publications may have multiple fields.</p> Full article ">Figure 3
<p>Map of academic research institutions with data access rights granted in 2019.</p> Full article ">
11 pages, 385 KiB  
Proceeding Paper
Combined Multilateration with Machine Learning for Enhanced Aircraft Localization
by Benoit Figuet, Raphael Monstein and Michael Felux
Proceedings 2020, 59(1), 2; https://doi.org/10.3390/proceedings2020059002 - 1 Dec 2020
Cited by 3 | Viewed by 2669
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Basic sensors/airplane architecture. OSN, OpenSky Network.</p> Full article ">Figure 2
<p>Pairwise median error distribution in ns.</p> Full article ">Figure 3
<p>Pairwise error interdecile range distribution in ns.</p> Full article ">Figure 4
<p>Error distributions for barometric altitude and predictions with respect to geometric altitude. LGBM, LightGBM.</p> Full article ">Figure 5
<p>Example of LGBM latitude prediction for a trajectory.</p> Full article ">Figure 6
<p>Example of LGBM longitude prediction for a trajectory.</p> Full article ">Figure 7
<p>2D errors box plots for different numbers of receivers.</p> Full article ">Figure 8
<p>Localization solution for a trajectory sample.</p> Full article ">
11 pages, 368 KiB  
Proceeding Paper
On ADS-B Sensor Placement for Secure Wide-Area Multilateration
by Ala’ Darabseh, Evangelos Bitsikas, Brice Tedongmo and Christina Pöpper
Proceedings 2020, 59(1), 3; https://doi.org/10.3390/proceedings2020059003 - 1 Dec 2020
Cited by 4 | Viewed by 1758
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Simulated k-coverage heatmap for a random placement of <math display="inline"> <semantics> <mrow> <mi>n</mi> <mo>=</mo> <mn>30</mn> </mrow> </semantics> </math> automatic dependent surveillance–broadcast (ADS-B) sensors.</p> Full article ">Figure 2
<p>Simulated geometric dilution of precision (GDOP) distribution for the random placement of <math display="inline"> <semantics> <mrow> <mi>n</mi> <mo>=</mo> <mn>30</mn> </mrow> </semantics> </math> ADS-B sensors. The corresponding k coverage heatmap is given in <a href="#proceedings-59-00003-f001" class="html-fig">Figure 1</a>.</p> Full article ">Figure 3
<p>Simulated k-coverage heatmap for optimal placement of ADS-B sensors after solving scenario one.</p> Full article ">Figure 4
<p>Simulated GDOP distribution of optimal placement of ADS-B sensors. The corresponding k coverage heatmap is given in <a href="#proceedings-59-00003-f003" class="html-fig">Figure 3</a>.</p> Full article ">Figure 5
<p>Scenario #1.</p> Full article ">Figure 6
<p>Scenario #2.</p> Full article ">Figure 7
<p>Scenario #3.</p> Full article ">
9 pages, 465 KiB  
Proceeding Paper
Mode S Transponder Comm-B Capabilities in Current Operational Aircraft
by Junzi Sun, Huy Vû, Xavier Olive and Jacco M. Hoekstra
Proceedings 2020, 59(1), 4; https://doi.org/10.3390/proceedings2020059004 - 1 Dec 2020
Cited by 2 | Viewed by 2383
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Data processing flow.</p> Full article ">Figure 2
<p>Available GICB capability statistics among all aircraft with valid aircraft typecode information, with a total of around 50,000 aircraft.</p> Full article ">Figure 3
<p>GICB capabilities of the top 50 aircraft types. Darkness and size of a dot represent the fraction of aircraft that have a certain capability enabled.</p> Full article ">Figure 4
<p>Aircraft that are compliant with EHS and ADS-B services.</p> Full article ">Figure 5
<p>Aircraft with meteorological capabilities enabled. Aircraft typecode and number of aircraft are shown. The total number of aircraft shown is 1811. Only typecodes with more than 20 aircraft are listed in detail.</p> Full article ">
10 pages, 3828 KiB  
Proceeding Paper
Using Open Source Data for Landing Time Prediction with Machine Learning Methods
by Gong Chen, Judith Rosenow, Michael Schultz and Ostap Okhrin
Proceedings 2020, 59(1), 5; https://doi.org/10.3390/proceedings2020059005 - 1 Dec 2020
Cited by 4 | Viewed by 2087
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>(<b>Left</b>) Sixty sample trajectories approaching Zurich Airport between 5 October 2019 and 31 October 2019, used for landing time prediction in this study. (<b>Right</b>) Entry points of aircraft when 45, 100, 150, 200, and 250 nautical miles away from the runways. The red point in the middle denotes the reference point 47.45 latitude and 8.56 longitude of Zurich Airport.</p> Full article ">Figure 2
<p>The difference in the track angle between the entering point on the circle and the landing point. (<b>Left</b>) Trajectories with less landing time; (<b>right</b>) trajectories with more landing time.</p> Full article ">Figure 3
<p>K-means clustering and landing time by clustering. (<b>Left</b>) Clustered entry points with the radius as 45 NM; (<b>right</b>) density plot of landing time grouped by K-means clusters.</p> Full article ">Figure 4
<p>Traffic density of the day.</p> Full article ">Figure 5
<p>Histogram of predictors and landing time.</p> Full article ">Figure 6
<p>Spearman correlation between features and landing time.</p> Full article ">Figure 7
<p>Line plot of MAE and RMSE depending on the radius by GBM, NN, and RF.</p> Full article ">Figure 8
<p>Density plot of errors on the test set depending on the radius by the RF, GBM, and NN methods.</p> Full article ">Figure 9
<p>Unconditional Feature importance evaluated by random forest permutation.</p> Full article ">
12 pages, 2157 KiB  
Proceeding Paper
Predicting Airplane Go-Arounds Using Machine Learning and Open-Source Data
by Benoit Figuet, Raphael Monstein, Manuel Waltert and Steven Barry
Proceedings 2020, 59(1), 6; https://doi.org/10.3390/proceedings2020059006 - 1 Dec 2020
Cited by 2 | Viewed by 2479
Abstract
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. [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Overview of the situation at Zurich airport. Blue and green: departures on runway 16, red: go-arounds (GAs) on runway 14.</p> Full article ">Figure 2
<p>Runway 14 at Zurich Airport and its approach corridor.</p> Full article ">Figure 3
<p>Smooth terms; the solid line is the fitted smooth and the dashed lines are the 95% confidence intervals.</p> Full article ">Figure 4
<p>Predicted probabilities. Red: distribution of the predictions when no GAs occurred. Blue: distribution when at leas one GA occurred. Dashed: median.</p> Full article ">Figure 5
<p>GA initiation distances from runway.</p> Full article ">Figure 6
<p>Profile of stability metrics and mean distributions.</p> Full article ">Figure 7
<p>Receiver operating characteristic for GA prediction on all of the data.</p> Full article ">Figure 8
<p>Distance from runway at which GAs are initiated for confident false negatives and confident true positives.</p> Full article ">Figure 9
<p>Glideslope for the subset of “true negative” (blue) and “false positive” (red) predictions.</p> Full article ">
10 pages, 628 KiB  
Proceeding Paper
Trajectory Clustering within the Terminal Airspace Utilizing a Weighted Distance Function
by Samantha J. Corrado, Tejas G. Puranik, Oliva J. Pinon and Dimitri N. Mavris
Proceedings 2020, 59(1), 7; https://doi.org/10.3390/proceedings2020059007 - 1 Dec 2020
Cited by 15 | Viewed by 2633
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Weighting schemes utilized.</p> Full article ">Figure 2
<p>Daily datasets: Mean distance between trajectories assigned to a flow and their respective flow centroid.</p> Full article ">Figure 3
<p>Flows identified utilizing the euclidean distance versus Weighting 1 for a single day.</p> Full article ">Figure 4
<p>Purple flow identified utilizing the euclidean distance versus Weighting 1 on a single day.</p> Full article ">Figure 5
<p>Weekly datasets: Mean distance between trajectories assigned to a flow and their respective flow centroid.</p> Full article ">
10 pages, 1354 KiB  
Proceeding Paper
Detecting Events in Aircraft Trajectories: Rule-Based and Data-Driven Approaches
by Xavier Olive, Junzi Sun, Adrien Lafage and Luis Basora
Proceedings 2020, 59(1), 8; https://doi.org/10.3390/proceedings2020059008 - 1 Dec 2020
Cited by 9 | Viewed by 2542
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Many wildfires occurred in California during September 2020. The heat map (<b>left</b>) shows the locations of fires according to the NASA Fire Information for Resources Management Systems together with the trajectories of aircraft owned by the firefighting administration of California. Selecting parts of trajectories where aircraft circle can help produce the different heat maps (<b>right</b>) inferring the locations of fires from aircraft trajectories.</p> Full article ">Figure 2
<p>(Left) Flight <tt>DLH83K</tt>on 25 February 2017: it is very difficult to determine the exact landing point: the <tt>onground</tt> flag was activated after the vertical rate came close to zero. A long landing in this situation is not unreasonable, but these data cannot reasonably support this hypothesis. (Right) No <tt>onground</tt> flag is activated, but the trajectory of aircraft identifier <tt>ae0455</tt>on 14 September 2020 suggests landing practice activity on an aircraft carrier off California.</p> Full article ">Figure 3
<p>Different trajectories from Paris–Orly <tt>LFPO</tt> to Toulouse <tt>LFBO</tt> range from a direct to <tt>NARAK</tt>(entry point to the TMA) to a route following all the points of the flight plan. A long interval without a flight plan navigational point in heading may suggest an instruction from the ATC.</p> Full article ">Figure 4
<p>Successive runway alignments may suggest different situations depending on the configuration of the airport and on the vertical speed: runway change with parallel runways at Toulouse <tt>LFBO</tt> airport on the left, failed landing attempts with go-around at Zürich <tt>LSZH</tt> airport in the middle or circle to land manoeuvres at Paris–Orly <tt>LFPO</tt> airport.</p> Full article ">Figure 5
<p>Example of flight phase identification using fuzzy logic, with fuzzy logic member functions (left) and the vertical profile with identified flight phases (right).</p> Full article ">Figure 6
<p>The statistical method did not detect runway changes happening beyond eight nautical miles (out of scope) and within four nautical miles: the statistical model is to be refined, taking the fourth component (i.e., variation mode [<a href="#B4-proceedings-59-00008" class="html-bibr">4</a>]) of the PCA into account.</p> Full article ">Figure 7
<p>The rule-based method did not match situations that had similar characteristics to regular runway changes. This late runway alignment on 32R with a late catching of the glide plan after the aircraft attempted an alignment on 32L is detected by the statistical method.</p> Full article ">Figure 8
<p>Holding patterns: A set of rules based on sets of parallel lines or self-intersecting segments may mistakenly select different patterns like those displayed on the first line. On the other hand, the line between a holding pattern and other sequencing procedures is thin: the trajectory in a. has been subject to sequencing actions by the ATC because of heavy traffic, but the oval shape is not visible; the trajectory in b. looks like a holding pattern was initiated, but the full shape is not visible. The trajectory in c. stacks two holding patterns, but the way out of the pattern should probably be labelled as well.</p> Full article ">Figure 9
<p>The 19,480 trajectories are split into sliding windows, rescaled and resampled (30 samples per window). The resulting 72,353 samples are then projected with a PCA. Holding patterns cluster in the latent space: the red part of the trajectory is well identified as a holding pattern, whereas the green trajectory, in spite of a pattern easily mistaken with rule-based models, stays in the regular cluster.</p> Full article ">
10 pages, 383 KiB  
Proceeding Paper
Improved Testing of AI-Based Anomaly Detection Systems Using Synthetic Surveillance Data
by Antoine Chevrot, Alexandre Vernotte, Pierre Bernabe, Aymeric Cretin, Fabien Peureux and Bruno Legeard
Proceedings 2020, 59(1), 9; https://doi.org/10.3390/proceedings2020059009 - 1 Dec 2020
Cited by 1 | Viewed by 1830
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Data discrepancies on a flight between Madrid and Moscow.</p> Full article ">Figure 2
<p>FDI-T Framework Architecture.</p> Full article ">
11 pages, 4911 KiB  
Proceeding Paper
GNSS Interference Characterization and Localization Using OpenSky ADS-B Data
by Zixi Liu, Sherman Lo and Todd Walter
Proceedings 2020, 59(1), 10; https://doi.org/10.3390/proceedings2020059010 - 1 Dec 2020
Cited by 6 | Viewed by 2739
Abstract
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, [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>Flowchart of ADS-B data processing.</p> Full article ">Figure 2
<p>Top view of ADS-B data at KHWD airport.</p> Full article ">Figure 3
<p>Top view of an airspace under impact of interference event.</p> Full article ">Figure 4
<p>3D model of objective function.</p> Full article ">Figure 5
<p>Sample data of receiver with inconsistent internal clock.</p> Full article ">Figure 6
<p>Time versus altitude plot for same flight with respect to different receivers.</p> Full article ">Figure 7
<p>Sample data of receiver with incorrect timestamp.</p> Full article ">Figure 8
<p>Time versus altitude plot of same flight with respect to different receivers.</p> Full article ">Figure 9
<p>Altitude versus time plot for all flights passing target airspace on 6 January 2019.</p> Full article ">Figure 10
<p>Result under theoretical test.</p> Full article ">Figure 11
<p>Heat map of cost function.</p> Full article ">Figure 12
<p>Result from real data: on 3D plot (<b>left</b>); and on Google Earth map (<b>right</b>).</p> Full article ">
8 pages, 3722 KiB  
Proceeding Paper
Integrating the OpenSky Network into GNSS-R Climate Monitoring Research
by Mike Laverick, Delwyn Moller, Christopher Ruf, Stephen Musko, Andrew O’Brien, Ryan Linnabary, Wayne Thomas, Chris Seal and Yvette Wharton
Proceedings 2020, 59(1), 11; https://doi.org/10.3390/proceedings2020059011 - 1 Dec 2020
Viewed by 1407
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>An example of how the state-vector data for an OpenSky flight was extrapolated and interpolated ready for science processing. (<b>Top left</b>) A plot of the coordinates (in blue) of a flight from Auckland to Kerikeri. (<b>Top right</b>) A schematic of start and end airport derivation for the flight. Blue circles denote a 2 km radius around an airport and the red semicircle denotes the field of view (extending to infinity), based upon craft heading, in which destination airports must fall. (<b>Bottom left</b>) The full flight data extrapolated between airports and interpolated down to a 1 s cadence. (<b>Bottom right</b>) Only extrapolated and interpolated data for the flight, shown in red.</p> Full article ">Figure 2
<p>Snapshot of the flight visualisation tool currently in development. The visualisation shows an OpenSky flight (in yellow) along with the corresponding simulated specular point reflections (in pink) produced as the flight progresses. Video examples of the full flight can be found here (<a href="https://www.youtube.com/watch?v=GbmFFjoQtr8" target="_blank">https://www.youtube.com/watch?v=GbmFFjoQtr8</a>) and here (<a href="https://www.youtube.com/watch?v=xcSlaXDtd8w" target="_blank">https://www.youtube.com/watch?v=xcSlaXDtd8w</a>).</p> Full article ">Figure 3
<p>OpenSky Network Q300 data coverage maps over New Zealand during the periods of January 2019 (<b>top left</b>), August 2019 (<b>top right</b>), December 2019 (<b>bottom left</b>), and August 2020 (<b>bottom right</b>). We found that the OpenSky network covers the Auckland and Christchurch regions fairly well, but does not quite extend as far eastwards as Gisborne or as far northwards as Kerikeri. Coverage of the South Island seems sufficient to capture the limited quantity of South Island Q300 flights. There also appear to have been temporal coverage gaps over the central North Island during the period of 2019.</p> Full article ">
10 pages, 889 KiB  
Proceeding Paper
Validating Aircraft Noise Models
by Ran Giladi and Eliav Menachi
Proceedings 2020, 59(1), 12; https://doi.org/10.3390/proceedings2020059012 - 3 Dec 2020
Cited by 2 | Viewed by 2172
Abstract
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, [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>NMTs location at Heathrow Airport.</p> Full article ">Figure 2
<p>Noise map of A320 at SERFR direct approach for landing ILS 28 R/L at SFO.</p> Full article ">Figure 3
<p>Flight path variations and correlation to the SEL: (<b>a</b>) distribution of aircraft altitude and lateral distance from NMT 404 in Palo-Alto when LAmax was recorded; (<b>b</b>) LAmax in dB(A) vs. slant distance when LAmax was recorded.</p> Full article ">Figure 4
<p>TLV airport with two sets of MNTs. Map obtained using Google Maps.</p> Full article ">Figure 5
<p>AEDT calculated SEL in dB(A) vs. Measured SEL. the red line presents a perfect match, the dotted black line presents the trendline of the linear regression: (<b>a</b>) comparison at NMT3; (<b>b</b>) at NMT5; (<b>c</b>) at NMT4; (<b>d</b>) at NMT 9.</p> Full article ">
10 pages, 608 KiB  
Proceeding Paper
Detecting and Correlating Aircraft Noise Events below Ambient Noise Levels Using OpenSky Tracking Data
by Luc Dekoninck
Proceedings 2020, 59(1), 13; https://doi.org/10.3390/proceedings2020059013 - 3 Dec 2020
Cited by 1 | Viewed by 2066
Abstract
Noise annoyance due to aircraft operations extends well beyond the 55 Lden 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. [...] Read more.
Noise annoyance due to aircraft operations extends well beyond the 55 Lden 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 LAmax 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 LAeq,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 LAeq,max, depending on the ambient levels. Using a detection algorithm sensitive to third-octave band levels, aircrafts can be detected down to 40 LAmax 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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>The propagation time of sound affects the correlating noise event significantly for high-altitude flights. At an altitude of 12 km, the event starts about 30 s after the closest point to the receiver. The directivity of the sound emission of the aircraft results in peak immission 60–90 s later. The aircraft can travel up to 20 km before the peak exposure occurs.</p> Full article ">Figure 2
<p>Spectrogram in third-octave bands of a low-exposure aircraft event (in dBA). The aircraft event is the blob between 90 and 150 s (<b>top</b>). The same event as a time series with L<sub>Aeq,1sec</sub> (black), the detector (red) and the detection threshold (purple dotted line) (<b>bottom</b>).</p> Full article ">Figure 2 Cont.
<p>Spectrogram in third-octave bands of a low-exposure aircraft event (in dBA). The aircraft event is the blob between 90 and 150 s (<b>top</b>). The same event as a time series with L<sub>Aeq,1sec</sub> (black), the detector (red) and the detection threshold (purple dotted line) (<b>bottom</b>).</p> Full article ">Figure 3
<p>Time series of a standard event with L<sub>Amax</sub> of 65 dBA that could/should be detected with ISO 20906:2009; the detector threshold is set to 52 dBA, showing L<sub>Aeq,1sec</sub>, the detector and the detection threshold (40 dBA). The third-octave bands used in the detector are also shown (40–250 Hz). Higher-frequency bands are attributed significantly to the aircraft sound exposure level (SEL).</p> Full article ">Figure 4
<p>Three time series of a events with L<sub>Amax</sub> below 50 dBA at ambient levels of 45–48 dBA.</p> Full article ">Figure 4 Cont.
<p>Three time series of a events with L<sub>Amax</sub> below 50 dBA at ambient levels of 45–48 dBA.</p> Full article ">Figure 5
<p>Tonal spectrogram in third-octave bands of a propeller aircraft event with a duration of 3.5 min (Antonov AN-12BK Ukraine Air Alliance). The shift in spectral content from high to low is the result of the Doppler effect increasing the frequency at the receiver for an approaching source and decreasing for a receding source. The L<sub>Amax</sub> is 50 dBA for a pass-by at a 15-km horizontal distance and an altitude of 6500 m with horizontal speed of 250 km/h and a vertical speed of 0 m/s.</p> Full article ">Figure 6
<p>Noise time series with three consecutive events (<b>left</b>) and flight data (<b>right</b>) for the L<sub>LF,T,e</sub> window and the MP<sub>box</sub>. One event triggers the selected threshold. The sound arrival time window, matching the detector window L<sub>LF,T,w</sub>, is highlighted in the flight data. A lower threshold is capable of identifying each of the three events individually.</p> Full article ">Figure 7
<p>Colliding events (<b>left</b>) and flight data (<b>right</b>) for the L<sub>LF,T,e</sub> window and the MP<sub>box</sub>. The sound arrival time windows of three flights match the detector windows L<sub>LF,T,w</sub> and are highlighted in the flight data.</p> Full article ">
10 pages, 4849 KiB  
Proceeding Paper
Automatic Call Sign Detection: Matching Air Surveillance Data with Air Traffic Spoken Communications
by Juan Zuluaga-Gomez, Karel Veselý, Alexander Blatt, Petr Motlicek, Dietrich Klakow, Allan Tart, Igor Szöke, Amrutha Prasad, Saeed Sarfjoo, Pavel Kolčárek, Martin Kocour, Honza Černocký, Claudia Cevenini, Khalid Choukri, Mickael Rigault and Fabian Landis
Proceedings 2020, 59(1), 14; https://doi.org/10.3390/proceedings2020059014 - 3 Dec 2020
Cited by 11 | Viewed by 3200
Abstract
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 [...] Read more.
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 ATCO2, 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 ATCO2 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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Figure 1

Figure 1
<p>ATCO<math display="inline"> <semantics> <msup> <mrow/> <mn>2</mn> </msup> </semantics> </math>proposed workflow for matching air surveillance data and spoken Air-Traffic Controller (ATCo)-pilot utterances gathered from the OpenSky Network API with speech data collected by VHF receivers. Each source (i.e., speech and air surveillance) is pre-processed before matching, e.g., speech data undergo voice activity detection and diarization. (i) Green blocks correspond to technologies either already on the market or available from previous projects, e.g., Active Listening Assistant (AcListant), MAchine Learning Of speech Recognition models for Controller Assistance (MALORCA), Air-Navigation Service Providers (ANSPs), OSN, or earlier. (ii) Red blocks summarize the task/technologies that ATCO<math display="inline"> <semantics> <msup> <mrow/> <mn>2</mn> </msup> </semantics> </math> is aiming to develop or improve.</p> Full article ">
9 pages, 547 KiB  
Proceeding Paper
Frequency of ADS-B Equipped Manned Aircraft Observed by the OpenSky Network
by Andrew Weinert, Marc Brittain and Randal Guendel
Proceedings 2020, 59(1), 15; https://doi.org/10.3390/proceedings2020059015 - 8 Dec 2020
Cited by 1 | Viewed by 2009
Abstract
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 [...] Read more.
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
(This article belongs to the Proceedings of 8th OpenSky Symposium 2020)
►▼ Show Figures

Graphical abstract

Graphical abstract
Full article ">Figure 1
<p>Airspace segmentation map of North Carolina for altitudes of 0–499 feet above ground level (AGL); low regions are visualized in green, medium in blue, and high in orange. The majority of the airspace was classified as medium or high. This map is dependent upon generalized operations defined by airspace class, population density, and aerodromes. It is completely independent of the OpenSky Network and its ground receivers.</p> Full article ">Figure 2
<p>Altitude and airspace distributions for fixed wing multi-engine aircraft below 18,000 feet.</p> Full article ">Figure 3
<p>Altitude and airspace distributions for fixed wing single engine aircraft below 18,000 feet.</p> Full article ">Figure 4
<p>Altitude and airspace distributions for rotorcraft below 18,000 feet.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-15
Previous Issue
Next Issue
Back to TopTop