Aircraft Proximity Maps Based on Data-Driven Flow Modeling

Abstract

With the forecast increase in air traffic demand over the next decades, it is imperative to develop tools to provide traffic flow managers with the information required to support decision making. In particular, decision-support tools for traffic flow management should aid in limiting controller workload and complexity, while supporting increases in air traffic throughput. Indeed, the growth of air transportation is conditioned on the ability to maintain acceptable safety. While many decision-support tools exist for short-term traffic planning, few have addressed the strategic needs for medium-and long-term planning for time horizons greater than 30 minutes. This paper seeks to address this gap through the introduction of 3D aircraft proximity maps that evaluate the future probability of presence of at least one or two aircraft at any given point of the airspace. Three types of proximity maps are presented: (i) presence maps that indicate the local density of traffic, (ii) conflict maps that determine locations of potential conflicts and their corresponding probabilities, and (iii) outlier proximity maps that show the probability of conflict due to aircraft not belonging to dominant traffic patterns. These maps provide traffic flow managers with information relating to the complexity and difficulty of managing an airspace. The intended purpose of the maps is to anticipate how aircraft flows interact, and how outliers impact the dominant traffic flow for a given time period. This formulation is able to predict which "critical" regions may be subject to conflicts between aircraft, thereby requiring careful monitoring and additional effort to manage the airspace. These probabilities are computed using a generative aircraft flow model. Time-varying flow characteristics, such as geometrical configuration, speed, and probability density function of aircraft spatial distribution within the flow, are determined from archived Enhanced Traffic Management System data, using a tailored clustering algorithm. Aircraft not belonging to flows are identified as outliers.

Modeling the Dispersion of Aircraft Trajectories Using Gaussian Processes

“…is used), it is possible to find the probability distribution of y at any given τ using equation (6). The solution fits into a GP framework, where a function is defined as a Gaussian process by a mean function m(τ) and a covariance kernel k(τ, τ ):…”

“…The result is an envelope with a splinelike representation, capturing a given percentage of trajectories in a two-dimensional space. [6] extended this approach to aircraft trajectories. Here the nodes are again discrete, but in a threedimensional space, and as a result the cross-section perpendicular to the nodes is no longer a line, but a surface.…”

“…As a method to generate aircraft proximity maps [6], i.e. creating a map that holds the probability an aircraft is present at any given point.…”

Teetool -- a probabilistic trajectory analysis tool

“…Motion patterns found in three-dimensional aircraft trajectory data have been visualised as flight corridors, where the data were clustered according to the flightpath [4]. The properties of the flight corridors are such that there is an average trajectory, and a dispersion in vertical and lateral direction, perpendicular to the mean trajectory.…”

A Gaussian process based decision support tool for air traffic management

“…Technically, it is possible to process the data real-time by using a GPU-based visualisation pipeline [10], but the occlusion of information remains a problem. The use of flight corridors to visualise the air-traffic is seen in work by Salaun et al [11], replacing the raw trajectory data with flight corridors. Here the flight corridor is represented via window frames, each defined by a vertical and a horizontal line that encloses the airtraffic.…”