Air Traffic Managers Research Articles

Teaching Artificial Intelligence Good Air Traffic Flow Management

Air traffic flow managers are continually faced with the decision of when and how to respond to predictions of future constraints. The promise of artificial intelligence, and specifically reinforcement learning, to provide decision support in this domain stems from the ability to systematically evaluate a sequence of potential actions, or strategy, across a range of uncertain futures. As decision support for human traffic managers, the generated recommendations must embody characteristics of a good management strategy; doing so requires introducing such notions to the algorithm. This paper proposes inducing stability into the strategy by dynamically constraining the design space based on upstream design decisions to promote consistency in the recommendations over time, where two such constraint sets are considered. The paper further evaluates the impact of adding a performance improvement threshold that must be overcome to accept a new strategy recommendation. The combination of search constraints and threshold values is evaluated against the agent’s reward function in addition to measures proposed to capture the stability of the strategy. The results show that the more restrictive set of constraints yields the best performance in terms of strategy stability and is more likely to reduce the delay where implementation of the threshold has a minor impact on overall performance. However, for the highest impact day of 8 June 2018, applying the threshold reverses the performance gains in delay but dramatically improves the stability of the resulting traffic flow management strategy from a flight level perspective, implying a potential tradeoff between delay optimization and flight predictability.

Short-term multi-step-ahead sector-based traffic flow prediction based on the attention-enhanced graph convolutional LSTM network (AGC-LSTM)

AbstractAccurate sector-based air traffic flow predictions are essential for ensuring the safety and efficiency of the air traffic management (ATM) system. However, due to the inherent spatial and temporal dependencies of air traffic flow, it is still a challenging problem. To solve this problem, some methods are proposed considering the relationship between sectors, while the complicated spatiotemporal dynamics and interdependencies between traffic flow of route segments related to the sector are not taken into account. To address this challenge, the attention-enhanced graph convolutional long short-term memory network (AGC-LSTM) model is applied to improve the short-term sector-based traffic flow prediction, in which spatial structures of route segments related to the sector are considered for the first time. Specifically, the graph convolutional networks (GCN)-LSTM network model was employed to capture spatiotemporal dependencies of the flight data, and the attention mechanism is designed to concentrate on the informative features from key nodes at each layer of the AGC-LSTM model. The proposed model is evaluated through a case study of the typical enroute sector in the central–southern region of China. The prediction results show that MAE reduces by 14.4% compared to the best performing GCN-LSTM model among the other five models. Furthermore, the study involves comparative analyses to assess the influence of route segment range, input and output sequence lengths, and time granularities on prediction performance. This study helps air traffic managers predict flight situations more accurately and avoid implementing overly conservative or excessively aggressive flow management measures for the sectors.

Prediction of Hourly Airport Operational Throughput with a Multi-Branch Convolutional Neural Network

Extensive research in predicting annual passenger throughput has been conducted, aiming at providing decision support for airport construction, aircraft procurement, resource management, flight scheduling, etc. However, how airport operational throughput is affected by convective weather in the vicinity of the airport and how to predict short-term airport operational throughput have not been well studied. Convective weather near the airport could make arrivals miss their positions in the arrival stream and reduce airfield efficiency in terms of the utilization of runway capacities. This research leverages the learning-based method (MB-ResNet model) to predict airport hourly throughput and takes Hartsfield–Jackson Atlanta International Airport (ATL) as the case study to demonstrate the developed method. To indicate convective weather, this research uses Rapid Refresh model (RAP) data from the National Oceanic and Atmospheric Administration (NOAA). Although it is a comprehensive and powerful weather data product, RAP has not been widely used in aviation research. This study demonstrated that RAP data, after being carefully decoded, cleaned, and pre-processed, can play a significant role in explaining airfield efficiency variation. Applying machine learning/deep learning in air traffic management is an area worthy of the attention of aviation researchers. Such advanced artificial intelligence techniques can make use of big data from the aviation sector and improve the predictability of the national airspace system and, consequently, operational efficiency. The short-term airport operational throughput predicted in this study can be used by air traffic controllers and airport managers for the allocations of resources at airports to improve airport operations.

Thunderstorm prediction during pre-tactical air-traffic-flow management using convolutional neural networks

Thunderstorms can be a large source of disruption for European air-traffic management causing a chaotic state of operation within the airspace system. In current practice, air-traffic managers are provided with imprecise forecasts which limit their ability to plan strategically. As a result, weather mitigation is performed using tactical measures with a time horizon of three hours. Increasing the lead time of thunderstorm predictions to the day before operations could help air-traffic managers plan around weather and improve the efficiency of air-traffic-management operations. Emerging techniques based on machine learning have provided promising results, partly attributed to reduced human bias and improved capacity in predicting thunderstorms purely from numerical weather prediction data. In this paper, we expand on our previous work on thunderstorm forecasting, by applying convolutional neural networks (CNNs) to exploit the spatial characteristics embedded in the weather data. The learning task of predicting convection is formulated as a binary-classification problem based on satellite data. The performance of multiple CNN-based architectures, including a fully-convolutional neural network (FCN), a CNN-based encoder–decoder, a U-Net, and a pyramid-scene parsing network (PSPNet) are compared against a multi-layer-perceptron (MLP) network. Our work indicates that CNN-based architectures improve the performance of point-prediction models, with a fully-convolutional neural-network architecture having the best performance. Results show that CNN-based architectures can be used to increase the prediction lead time of thunderstorms. Lastly, a case study illustrating the applications of convection-prediction models in an air-traffic-management setting is presented.

The Influence of Personnel Workload at the Control Area Unit to Service Quality of Air Traffic Center (ATC) in Jakarta

This study aims to investigate the influence of personnel workload at the ATC (Air Traffic Center) to service quality of ATC using quantitative approach. The data was collected using a questionnaire, to grasp the respondents’ perception. The population of this study are those who work in ATC, Jakarta, Indonesia. Purposive sampling technique is employed in this study. The number of the respondents of this study are 20 persons comprising, air traffic control staff and managers. The data was analyzed using SPSS. . The result shows that there is a significant influence on personnel workload at the control area unit to service quality of air traffic center in Jakarta, Indonesia.

Recommending Strategic Air Traffic Management Initiatives in Convective Weather

The presence of uncertainty in weather forecasts poses significant challenges for air traffic managers. These challenges can have major repercussions on stakeholders in terms of their impact on the delay within the system. In this paper, we discuss an approach for recommending traffic management initiative (TMI) parameters during uncertain weather conditions. We propose four methods for TMI selection. The first two favor random exploration of TMI decisions. An epsilon-greedy approach and a softmax algorithm are also evaluated against the two random exploration approaches. A parallel fast-time simulation framework is presented for evaluating the proposed methods over a range of weather forecast scenarios. A set of regional TMIs is applied and tested against a set of case days in which the airspace capacity in the Northeast United States was compromised by convective weather. Both the softmax and epsilon-greedy approaches demonstrate strong performance relative to the other methods. The results suggest that the approach could potentially aid air traffic stakeholders in understanding how to best deal with weather forecast uncertainty.

A Multi-Head Self-Attention Transformer-Based Model for Traffic Situation Prediction in Terminal Areas

Terminal operations management is an important part of air traffic management. Accurately detecting and predicting the operational status of the terminal area can help formulate more appropriate and efficient management methods. To achieve more accurate results in predicting the traffic situation, a ConvTrans-TCN (Convolutional Transformer with Temporal Convolutional Network) model is proposed in this paper. The model first constructs the feature extraction part using the causal-convolution multi-head self-attention module. It can effectively model the long-term dependency in the sequence and match the local patterns of the sequence, and it enhances the performance of feature extraction. Then the TCN (Temporal Convolutional Network) module is used to build the information fusion part to complete the fusion of feature data. The TCN architecture can accurately learn long-term and short-term dependencies in time series, and it has sufficient memory. Finally, the situation prediction is obtained by a feedforward neural network. The experiment’s results prove that this model is feasible and it performs better than the common models such as LSTM, BP, which can help air traffic managers to identify the operational status of the terminal area and provide decision support.

Analysis of Airport Risk Propagation in Chinese Air Transport Network

In recent years, due to the close coupling between airports, airport risk propagation has become a huge challenge. However, it has not been fully understood on the network level. Airport risk can be transferred through other airports owing to connected resources. In this study, we consider two risk factors including airport delay and saturation and propose a risk coupling model based on a clustering algorithm to fit the index and form risk series. To understand the risk propagation mechanism, we build risk propagation networks based on the Granger Causality test, and we apply complex network theory to analyze the evolution of the risk propagation network. We study the regular pattern of risk propagation from perspectives of time and space. Through network analysis, we find four time stages in the risk propagation process and the participation of airports in risk propagation has a positive correlation with airport sizes. In addition, more large airports tend to prevent risk propagation in unoccupied and normal situations, while small airports perform better than large airports in busy situations. Via the conclusion, our work can assist airlines or air traffic managers in controlling the scale of risk propagation before its key time turning point. By identifying the critical airport level and related factors in risk propagation, they can also reduce single airport risk and risk participation through corresponding risk control measures, finally avoiding the large-scale spread of risk and reducing delay or cancellation of more flights.

Predictive and Prescriptive Analytics Toward Passenger-Centric Ground Delay Programs

Ground delay programs (GDPs) comprise the main interventions to optimize flight operations in congested air traffic networks. The core GDP objective is to minimize flight delays, but this may not result in optimal outcomes for passengers—especially with connecting itineraries. This paper proposes a novel passenger-centric optimization approach to GDPs by balancing flight and passenger delays in large-scale networks. For tractability, we decompose the problem using a rolling procedure, enabling the model’s implementation in manageable runtimes. Computational results based on real-world data suggest that our modeling and computational framework can reduce passenger delays significantly at small increases in flight delay costs through two main mechanisms: (i) delay allocation (delaying versus prioritizing flights) and (ii) delay introduction (holding flights to avoid passenger misconnections). In practice, however, passenger itineraries are unknown to air traffic managers; accordingly, we propose statistical learning models to predict passenger itineraries and optimize GDP operations accordingly. Results show that the proposed passenger-centric approach is highly robust to imperfect knowledge of passenger itineraries and can provide significant benefits even in the current decentralized environment based on collaborative decision making.

Characterizing Flight Delay Profiles with a Tensor Factorization Framework

In air traffic and airport management, experience gained from past operations is crucial in designing appropriate strategies when facing a new scenario. Therefore, this paper uses massive spatiotemporal flight data to identify similar traffic and delay patterns, which become critical for gaining a better understanding of the aviation system and relevant decision-making. However, as the datasets imply complex dependence and higher-order interactions between space and time, retrieving significant features and patterns can be very challenging. In this paper, we propose a probabilistic framework for high-dimensional historical flight data. We apply a latent class model and demonstrate the effectiveness of this framework using air traffic data from 224 airports in China during 2014–2017. We find that profiles of each dimension can be clearly divided into various patterns representing different regular operations. To prove the effectiveness of these patterns, we then create an estimation model that provides preliminary judgment on the airport delay level. The outcomes of this study can help airport operators and air traffic managers better understand air traffic and delay patterns according to the experience gained from historical scenarios.

Analysis of Terminal Area Airspace Operation Status Based on Trajectory Characteristic Point Clustering

The terminal control area airspace system is one of the most complicated subsystems in the entire air traffic control system. With the continuous increase of air traffic volume, the utilization of its airspace resources has become a bottleneck restricting the sustainable development of the system. Monitor and obtain its operating status information and formulating corresponding mitigation measures are essential to improve the overall performance of the system. In order to achieve that, a new system analysis method based on clustering of trajectory characteristic point is proposed. The flight trajectories from radar position data are reconstructed at first. Followed by the method of extracting flight trajectory characteristic points including turning points, altitude transition points and speed adjustment points, all characteristic points are extracted. Then, K-means is applied for clustering according to their 3D space position, while the results are analyzed by introducing evaluation indexes based on air traffic control operation strategies. Numerical experiments show significant clustering characteristics and revealing the operation status of the terminal area airspace, which can help air traffic manager to identify defects in airspace operation and providing guidance for future airspace planning and flight procedure adjustment.

Flight Level Assignment Using Graph Coloring

This paper models an air traffic optimization problem where, on the one hand, flight operators seek to minimize fuel consumption flying at optimal cruise levels and, on the other hand, air traffic managers aim to keep intersecting airways at as distant as possible flight levels. We study such a problem as a factorized optimization, which is addressed through a spectrum graph coloring model, evaluating the effect that safety constraints have on fuel consumption, and comparing different heuristic approaches for allocation.

An overview of air delay: A case study of the Brazilian scenario

Delay is a key point in air transportation activity. As a performance metric, it affects common policy concerns. Delay impacts passenger satisfaction and imposes costs. The complexity that sets in for the air traffic manager is how to mitigate delay, especially in an environment with several stakeholders. The present article applied a problem-structuring method (PSM), named value-focused thinking (VFT), to structure the problem of the air traffic flow management arrival delay. The inflexibility of incorporating a flight operator's specific needs is considered one of the reasons for the limited success of air traffic flow management (ATFM) programs. PSM allows participants to clarify their dilemmas, converge on a mutually liable problem, or agree to the proposed solutions and compromise on what partially solves the issue. The problem is that most papers focus only on the applied solution for air delay mitigation. Before implementing operational research techniques, we investigated the nature and characteristics of air delay. Results showed that there were several stakeholders with distinctive requirements for their business and many of their objectives are interconnected. The use of VFT provided an objective map that can be used as a guide for future solutions.

Predictive and Prescriptive Analytics toward Passenger-centric Ground Delay Programs

Ground Delay Programs (GDP) comprise the main interventions to optimize flight operations in congested air traffic networks. The core GDP objective is to minimize flight delays, but this may result in optimal outcomes for passengers — especially with connecting itineraries. This paper proposes an original passenger-centric approach to GDP by leveraging data on passenger itineraries in flight networks. First, we identify analytical drivers of passenger-centric operations in transportation systems. Second, we develop an integer program that balances flight delays and passenger delays in large-scale GDP operations. A rolling procedure decomposes the problem while ensuring global feasibility, enabling the model’s implementation in short computational times. Third, we propose statistical learning models to predict passenger itineraries and optimize GDP operations accordingly, enabling the model’s implementation when passenger itineraries are unknown by air traffic managers. Computational results based on real-world data suggest that our modeling and computational framework can reduce passenger delays significantly at small increases in flight delay costs, and that these benefits are robust to imperfect knowledge of passenger itineraries. Results highlight two major levers of passenger-centric operations: (i) delay allocation (which flights to delay vs. prioritize), and (ii) delay introduction (whether to deliberately hold flights to avoid passenger misconnections).

Identifying similar days for air traffic management

Air traffic managers face challenging decisions due to uncertainity in weather and air traffic. One way to support their decisions is to identify similar historical days, the traffic management actions taken on those days, and the resulting outcomes. We develop similarity measures based on quarter-hourly capacity and demand data at four case study airports—EWR, SFO, ORD and JFK. We find that dimensionality reduction is feasible for capacity data, and base similarity on principal components. Dimensionality reduction cannot be efficiently performed on demand data, consequently similarity is based on original data. We find that both capacity and demand data lack natural clusters and propose a continuous similarity measure. Finally, we estimate overall capacity and demand similarities, which are visualized using Metric Multidimensional Scaling plots. We observe that most days with air traffic management activity are similar to certain other days, validating the potential of this approach for decision support.

Cooperation Between Science and Aviation-Sector Service Providers in Europe for Risk Management of Volcanic Ash

The eruption of Eyjafjallajökull in April–May 2010 (hereafter E2010) revealed the fragility of air traffic in the case of an ash-producing volcanic eruption. This study examines developments since E2010 of cooperation between science and aviation-sector service providers toward efforts for improved resilience against a new volcanic eruption. The research builds on literature and interviews with representatives from research and regulatory institutes, air traffic managers, aircraft operators, and engine manufacturers across Europe. The article describes how scientific advice was requested to revise the regulatory precautionary approach and reopen airspace during E2010. The paper depicts the increased effort of scientific advancement in the understanding of ash characterization, modeling of the volcanic ash plume, and atmospheric environment. Furthermore, cross-disciplinary workshops and the memorandum of understanding between Icelandic and British institutions are examined to document increased cooperation between scientists and aviation-sector service providers to provide support to decision makers. However, the science needed for improved risk management is complex and depends on the effects of volcanic ash on jet engines. The concentration levels decided on over the course of a few days in 2010 have not been revised, and the aviation industry does not seem to prioritize research into these issues. A dialogue is needed between science, governance, and engine manufacturers, as well as more collective research funding to test jet engines to improve informed decision making, rather than leaving such research only to the manufacturers and internal political agendas.

Some insights into a sequential resource allocation mechanism for en route air traffic management

This paper presents a game theoretic model of a sequential capacity allocation process in a congestible transportation system. In this particular application, we investigate the governing principles at work in how airlines will time their requests for en route resources under capacity shortfalls and uncertain conditions, when flights are not able to take their preferred route at their preferred departure time slot due to the shortfalls. We examine a sequential “First Submitted First Assigned” (FSFA) capacity allocation process within an en route air traffic flow management (ATFM) program such as the Collaborative Trajectory Options Program (CTOP), which is a Federal Aviation Administration initiative that aims to manage en route capacity constraints brought on by inclement weather and capacity/demand imbalances. In the FSFA process, flights are assigned the best available routes and slots available at the time flight operators submit their preference requests during the planning period, in a sequential manner. Because flight operators compete with one another for resources, in such an allocation process they would be expected to make their requests as early as possible. However, because weather and traffic conditions – and therefore, the values of resources – can change significantly, flight operators may prefer to request resources later in the process rather than earlier. We use a game theoretic setup to understand how flight operators might tradeoff these conflicts and choose an optimal time to submit their preferences for their flights, as submission times are competitive responses by flight operators looking to maximize their benefits. We first develop a loss function that captures the expected utility of submitting preferences under uncertainty about operating conditions. Then, a conceptual model of the FSFA process is constructed using a simultaneous incomplete information game, where flight operators compete for the “prizes” of having submitted their inputs before others. A numerical study is performed in which it is demonstrated that preference submission times are heavily influenced by the general uncertainty surrounding weather and operational conditions of the ATFM program, and each flight operator’s internal ability to handle this uncertainty. A key finding is that, in many of the scenarios presented, an optimal strategy for a flight operator is to submit their preferences at the very beginning of the planning period. If air traffic managers could expect to receive more submissions at the beginning of the planning period, they could more easily coordinate the ATFM program with other ATFM programs taking place or scheduled to take place, and they would have more opportunity to call another FSFA allocation route before the ATFM program begins, should conditions change enough to warrant this. Outputs of the model may provide some general insights to flight operators in planning submission strategies within competitive allocation processes such as FSFA. Also, this work may have a broader application to other sequential resource allocation strategies within congestible and controlled transportation systems.

Development of a Probabilistic Convective Weather Forecast Threshold Parameter for Flight-Routing Decisions

Abstract This paper presents a method for determining a threshold value of probabilistic convective weather forecast data. By synchronizing air traffic data and an experimental probabilistic convective weather forecast product, it was observed that aircraft avoid areas of specific forecasted probability. Both intensity and echo top of the forecasted weather were synchronized with air traffic data to derive the probability threshold parameter. This value can be used by dispatchers for flight planning and by air traffic managers to reroute streams of aircraft around convective cells. The main contribution of this paper is to provide a method to compute the probability threshold parameters using a specific experimental probabilistic convective forecast product providing hourly guidance up to 6 h. Air traffic and weather data for a 4-month period during the summer of 2007 were used to compute the parameters for the continental United States. The results are shown for different altitudes, times of day, aircraft types, and airspace users. Threshold values for each of the 20 Air Route Traffic Control Centers were also computed. Additional details are presented for seven high-altitude sectors in the Fort Worth, Texas, center. For the analysis reported here, flight intent was not considered and no assessment of flight deviation was conducted since only aircraft tracks were used.

FAA Air Traffic Control Front Line Manager’s Quick Reference Guide

Air Traffic Control Front Line Managers (FLMs) influence the prevention of operational incidents (OIs) and runway incursions (RIs) through practices that enable safe controller performance and mitigate problems related to specific contributing factors, including controller coordination, controller-pilot communication, and controller memory. FLMs’ proximity and frequent interactions with controllers in the operational environment place them in a unique position to impact air traffic safety through managing controller performance and mitigating OIs and RIs resulting from common contributing factors. With this understanding of the FLM role, The Federal Aviation Administration (FAA) developed the Front Line Managers Quick Reference Guide (QRG). The Civil Aerospace Medical Institute (CAMI) assisted the Air Traffic Organization (ATO) with the organization and evaluation of these materials. The guide was intended to provide a management best practices format specific to Air Traffic Control to assist FLMs in the performance of their job. To determine the utility of the QRG, CAMI developed and administered a survey of FLMs. The survey also provided the ATO with a basis for additions or deletions to the QRG. The FLM QRG was designed as a best practices guide for use by all field FLMs. Survey results and suggestions and recommendations from survey respondents are presented.

Framework for airspace planning and design based on conflict risk assessment: Part 3: Conflict risk assessment model for airspace operational and current day planning

This paper presents a natural continuation of author’s previous work that deals with the development of a conflict risk assessment model for the purpose of airspace operational and current day planning under an airspace planning and design framework based on conflict risk and task-load assessment. The model is intended to support an air traffic manager’s decision-making process during sectorization (for a given set of available sectors determined at tactical planning levels) through the evaluation of conflict risk and air traffic controller task-load. The model is based on the assumption that a conflict between a pair of aircraft exists when either horizontal or vertical separation minima are violated. Additionally, it was assumed that risk is a random variable. The developed model allows for estimation of the number of conflicts and the conflict probability, as well as their distribution at intersections and along an airway. It also allows for the determination of the air traffic controller’s task-load for a given airspace and traffic load. The model is intended for use in en-route airspace. An illustration of the model application shows that in addition to airspace geometry, the total conflict risk also depends on aircraft speed, traffic demand and its spatial and temporal distribution in the airspace as well as the applied separation minima. Finally, it was shown that the results of the model could be used by the air traffic managers in order to help them decide the necessary grouping (aggregation) or collapsing (disaggregation) of sectors (sectorization).