York Metroplex Research Articles

Temporal logic learning-based anomaly detection in metroplex terminal airspace operations

The airspace system is a complex dynamical system with complicated controlled interactions between its constituent subsystems – terminal airspace, en-route airspace, and ground. Of these, air traffic management in the multi-airport (metroplex) terminal airspace is one of the most complicated subsystems to manage, especially due to the interactions between proximal airports. Analyzing anomalous behaviors in the metroplex is emerging as a key problem in understanding air traffic management complexity and safety. Although physics-based approaches have been studied in-depth for this application, newfound interest has been observed to use recorded time-series air traffic surveillance and airport operations datasets for this purpose. In this paper, we propose a machine learning-based anomaly detection algorithm that generates mathematical models to detect anomalies in metroplex operations. Several machine learning algorithms have been developed to detect anomalies using only air traffic surveillance data, but there is a significant scope of improvement by including airport operational characteristics as well, since integrating such closely-controlled metroplex operational datasets allows the developed models to effectively detect anomalies. The key contribution of this paper is in allowing anomaly detection models to recursively update so as to adapt to changes in metroplex operations. The proposed algorithm is demonstrated with real air traffic surveillance and airport operations datasets at LaGuardia, John F. Kennedy, and Newark airports, thereby detecting anomalies for operations in the New York metroplex.

Prediction of runway configurations and airport acceptance rates for multi-airport system using gridded weather forecast

Accurate prediction of real-time airport capacity, a.k.a. airport acceptance rates (AARs), is key to enabling efficient air traffic flow management. AARs are dependent on selected runway configurations and both are affected by weather conditions. Although there have been studies tackling on the prediction of AARs or runway configurations or both, the prediction accuracy is relatively low and only single airport is considered. This study presents a data-driven deep-learning framework for predicting both runway configurations and AARs to support efficient air traffic management for complex multi-airport systems. The two major contributions from this work are 1) the proposed model uses assembled gridded weather forecast for the terminal airspace instead of an isolated station-based terminal weather forecast, and 2) the model captures the operational interdependency aspects inherent in the parameter learning process so that proposed modeling framework can predict both runway configuration and AARs simultaneously with higher accuracy. The proposed method is demonstrated with a numerical experiment taking three major airports in New York Metroplex as the case study. The prediction accuracy of the proposed method is compared with methods in current literature and the analysis results show that the proposed method outperforms all existing methods.

Incremental-Learning-Based Unsupervised Anomaly Detection Algorithm for Terminal Airspace Operations

The terminal airspace system is one of the most complex human-made dynamical systems with a continuously evolving structure. Modern aviation technologies in the terminal airspace record detailed flight and airport information, including the states of aircraft and the operating conditions of airports as time series datasets, through on-board and ground-based systems. Detecting anomalies in such datasets is emerging as a key problem to understand air transportation system complexity and behavior. This paper proposes an incremental-learning-based anomaly detection algorithm that generates anomaly detection models from surveillance data. The algorithm is developed in a recursive fashion, such that it uses the overnight recorded data to improve the temporal-logic-based anomaly detection models daily—thus it is termed as an overnight update algorithm. The proposed algorithm is demonstrated with real air traffic surveillance data comprising of arrival flights to LaGuardia, John F. Kennedy, and Newark airports, thereby detecting anomalies for arrivals in the terminal airspace of the New York metroplex. This is followed by some analysis and insights from the results of these extensive tests.

A framework for the optimization of terminal airspace operations in Multi-Airport Systems

Major cities like London, New York, and Tokyo are served by several airports, effectively creating a Multi-Airport System (MAS), or Metroplex. The operations of individual Metroplex airports are highly interdependent, rendering their efficient management rather difficult. This paper proposes a framework for the design of dynamic arrival and departure routes in MAS Terminal Maneuvering Areas, which fundamentally changes the operation in MAS airspaces for much improved efficiency when compared to the current situation. The framework consists of three components. The first presents a new procedure for characterizing dynamic arrival and departure routes based on the spatio-temporal distributions of flights. The second component is a novel Analytic Hierarchy Process (AHP) model for the prioritization of the dynamic routes, which takes into account a set of quantitative and qualitative attributes important for MAS operations. The third component is a priority-based method for the positioning of terminal waypoints as well as the design of three-dimensional, conflict-free terminal routes. Such a method accounts for the AHP-derived priorities while satisfying the minimal separation and aircraft maneuverability constraints. The developed framework is applied to a case study of the New York Metroplex, using aircraft trajectories during a heavy traffic period on typical day of operation in the New York Terminal Control Area in November 2011. The proposed framework is quantitatively assessed using the AirTOp fast-time simulation model. The results suggest significant improvements of the new design over the existing one, as measured by several key performance indicators such as travel distance, travel time, fuel burn, and controller workload. The operational feasibility of the framework is further validated qualitatively by subject matter experts from the Port Authority of New York and New Jersey, the operator of the New York Metroplex.

Robust identification of air traffic flow patterns in Metroplex terminal areas under demand uncertainty

Multi-Airport Systems (MAS), or Metroplexes, serve air traffic demand in cities with two or more airports. Due to the spatial proximity and operational interdependency of the airports, Metroplex airspaces are characterized by high complexity, and current system structures fail to provide satisfactory utilization of the available airspace resources. In order to support system-level design and management towards increased operational efficiency in such systems, an accurate depiction of major demand patterns is a prerequisite. This paper proposes a framework for the robust identification of significant air traffic flow patterns in Metroplex systems, which is aligned with the dynamic route service policy for the effective management of Metroplex operations. We first characterize deterministic demand through a spatio-temporal clustering algorithm that takes into account changes in the traffic flows over the planning horizon. Then, in order to handle uncertainties in the demand, a Distributionally Robust Optimization (DRO) approach is proposed, which takes into account demand variations and prediction errors in a robust way to ensure the reliability of the demand identification. The DRO-based approach is applied on pre-tactical (i.e. one-day planning) as well as operational levels (i.e. 2-h rolling horizon). The framework is applied to Time Based Flow Management (TBFM) data from the New York Metroplex. The framework and results are validated by Subject Matter Experts (SMEs).

Complex Terminal Airspace Analysis Methodology for Evaluating FMS or RNAV Procedures

The paper summarizes an approach for airspace analysis methods to examine the operational suitability of proposed changes in complex, high-density airspace such as the New York Terminal Maneuvering Area. The potential of a Flight Management System (FMS) or Area Navigation (RNAV) arrival procedure to alleviate airspace constraints and increase capacity for complex traffic flow interactions is examined. A case study is developed for arrival/departure flows for Teterboro and Newark airports in the New York metroplex, where the proposed procedure eliminates some of the constraining traffic flow interactions. The study considers the operational implications of the revised flows, particularly the impact on controller workload. The analysis examines the impact on the controller’s required intervention rate based on statistical studies of opposing traffic flow encounters. The study indicates that procedures can be designed to minimize additional controller workload caused by tactical interventions. The analysis examines procedure design criteria and design alternatives that could enhance system performance.