William H. Semke

This paper investigates the detection of Global Positioning System (GPS) interference during the Dallas Fort Worth (DFW) event from 17 to 19 October 2022, utilizing various machine learning (ML) models. The study examines the effectiveness of several ML models, including neural networks (NN), tree-based models, regression-based models, Bayesian classifiers, distance-based models, and stochastic classifiers, in identifying GPS interference. A simulated training signature was created with 180,000 data points, of which 25,792 were modeled as positive samples indicating GPS interference. Preliminary results reveal that the Multi-Layer Perceptron (MLP) model outperformed others, achieving a 99.8% True Positive Rate (TPR). Additionally, permutation feature importance was utilized to understand how model feature prioritization impacts the detection outcomes. Given the increasing frequency of GPS interference, these findings underscore the critical importance of ML techniques in detecting GPS interference patterns in Automatic Dependent Surveillance-Broadcast (ADS-B) data.

This work analyzes the severity and risk associated with automatic dependent surveillance-broadcast (ADS-B) message drop-out in detect and avoid (DAA) function of unmanned aircraft systems (UAS). Performance assessment of the universal access transceiver (UAT) ADS-B message implies that, in some cases, ADS-B fails to update within a specified update interval, which is referred to as ‘drop-out’ in this work. ADS-B is a fundamental surveillance sensor for both class 1 and class 2 DAA systems. Message loss or drop-out has been found as one of the common limitations of the ADS-B system. The key feature of this study is incorporating the update rate of real ADS-B data transmitted from the manned aircraft. The data were received from the Grand Forks International Airport, North Dakota. Monte Carlo method has been adopted to resolve encounter scenarios in the presence of drop-out. The change in the alert triggered by the UAS DAA in the presence of ADS-B drop-out has been investigated. Furthermore, the risk matrices are created to quantify the associated risk with drop-out affected alerts. Simulation results depict that both the duration of drop-out and DAA look-ahead time affect the alert-triggering function of UAS. With a small look-ahead window and longer duration of drop-out, the number of warning alerts increases. Also, alerts are affected more during an overtaking encounter than that of a head-to-head encounter. A system-level analysis is also carried out to recognize the potential reasons behind the ADS-B drop-out.

An analysis of the performance of automatic dependent surveillance-broadcast (ADS-B) data received from the Grand Forks, North Dakota International Airport was carried out in this study. The purpose was to understand the vulnerabilities of the universal access transceiver (UAT) ADS-B system and recognize the effects on present and future air traffic control (ATC) operation. The Federal Aviation Administration (FAA) mandated all the general aviation aircraft to be equipped with ADS-B. The aircraft flying within United States and below the transition altitude (18,000 feet) are more likely to install a UAT ADS-B. At present, unmanned aircraft systems (UAS) and autonomous air traffic control (ATC) towers are being integrated into the aviation industry and UAT ADS-B is a basic sensor for both class 1 and class 2 detect-and-avoid (DAA) systems. As a fundamental component of future surveillance systems, the anomalies and vulnerabilities of the ADS-B system need to be identified to enable a fully-utilized airspace with enhanced situational awareness. The data received was archived in GDL-90 format, which was parsed into readable data. The anomaly detection of ADS-B messages was based on the FAA ADS-B performance assessment report. The data investigation revealed ADS-B message suffered from different anomalies including dropout, missing payload, data jump, low confidence data, and altitude discrepancy. Among those studied, the most severe was dropout and 32.49% of messages suffered from this anomaly. Dropout is an incident where ADS-B failed to update within a specified rate. Considering the potential danger being imposed, an in-depth analysis was carried out to characterize message dropout. Three flight parameters were selected to investigate their effect on dropout. Statistical analysis was carried out and the Friedman Statistical Test identified that altitude affected dropout more than any other flight parameter.

Detect and Avoid (DAA) systems are complex communication and locational technologies comprising multiple independent components. DAA technologies support communications between ground-based and space-based operations with aircraft. Both manned and unmanned aircraft systems (UAS) rely on DAA communication and location technologies for safe flight operations. We examined the occurrence and duration of communication losses between radar and automatic dependent surveillance–broadcast (ADS-B) systems with aircraft operating in proximate airspace using data collected during actual flight operations. Our objectives were to identify the number and duration of communication losses for both radar and ADS-B systems that occurred within a discrete time period. We also investigated whether other unique communication behavior and anomalies were occurring, such as reported elevation deviations. We found that loss of communication with both radar and ADS-B systems does occur, with variation in the length of communication losses. We also discovered that other unexpected behaviors were occurring with communications. Although our data were gathered from manned aircraft, there are also implications for UAS that are operating within active airspaces. We are unaware of any previously published work on occurrence and duration of communication losses between radar and ADS-B systems.