Efficient Air Traffic Management Research Articles

A deep learning-based approach for predicting in-flight estimated time of arrival

AbstractPredictability is key for efficient and safe air traffic management. In particular, accurately estimating time of arrival for current passenger flights may help terminal controllers to plan ahead and optimize airport operations in terms of safety and resource allocation. While traditional physics-based simulations are still widely used, they are complex to model and often fail to include many factors affecting the progress of a flight. In this paper, we propose a deep learning approach based on LSTM that leverages the 4D trajectory of the flight and weather data at the destination airport, to accurately predict estimated time of arrival. We evaluate our model on flights arriving at Adolfo Suárez-Madrid Barajas airport (Spain), in the first three quarters of 2022, achieving a mean absolute error of 2.65 min over the entire flight and reporting competitive short- and long-term predictions at different spatial and temporal horizons.

Runway Capacity Studies for Major Indian Airports

The two principal measures of performance of Air Traffic management (ATM) systems are Capacity and Delay. Significant growth in Indian air traffic is causing congestions and hence delays in the en-route airspace and at airports. The main reason for the delay at airports is insufficient capacity in terms of facilities such as runways, taxiways or gates to accommodate peak period demands. The delays at airports would cause inconvenience to the passengers, airliners and the airport authorities. The airport runway capacity information will be useful to manage demand and minimize the delay. Prediction of runway capacity aids in developing strategies for efficient air traffic management. This paper presents the airport runway capacity studies carried out using Time Space diagrams for major Indian Airports.

Spatiotemporal Image-Based Flight Trajectory Clustering Model with Deep Convolutional Autoencoder Network

Recent studies in four-dimensional flight trajectories attempted to identify the impacts of various flight trajectories and maneuver parameters on air traffic management efficiency and aviation safety. The previous studies attempted to cluster trajectories based on spatial scales. However, these might require converting the flight trajectories to equal lengths for sequence-based clustering. This paper proposes a novel trajectory three-channel image representation and Gaussian mixture model clustering based on several image-processing methodologies. The aircraft’s latitude, longitude, flight level, and ground speed are represented as corresponding pixel information of the image followed by image-based flight trajectory representation and clustering methods (including deep convolutional autoencoder (DCAE), principal component analysis (PCA) image dimensionality reduction, and image feature points extraction) using a half-year of automatic dependent surveillance-broadcast flight trajectory data in the Hong Kong flight information region. The computational results indicate that the image-based trajectory representation produces more insights for trajectory processing, such as the application of convolutional neural networks and image-processing algorithms. In addition, the DCAE model has better performance and robustness for trajectory feature extraction and similarity analysis than PCA, which will provide ideas for multiparameter trajectory similarity analysis and prediction.

TA-LSTM: A Time and Attribute Aware LSTM for Deep Flight Track Clustering

The rapid development of civil aviation imposes an urgent need for efficient air traffic management. Flight track clustering is the premise and foundation of air traffic control. Flight track points compose time-series data with non-identical point- to-point intervals, and the effective latent representation of track data is key to the flight trajectory clustering. Long Short-Term Memory (LSTM) is an important and popular method to extract the features of trajectory time-series data. However, LSTM ignores the irregular time intervals between track points and fails to effectively distinguish the importance of different attributes at each track point during feature extraction. In addition, the existing methods based on LSTM either ignore the distinct impacts of different attributes at each track point or simply assume that the influences of the previous track points on the subsequent ones decrease with time. In this paper, we propose a flight trajectory feature extraction unit called TA-LSTM (Time and Attribute Aware Long Short- Term Memory) and a flight track clustering model based on TA- LSTM. The flight track clustering model consists of a feature extraction layer and a clustering layer. The feature extraction layer adopts TA-LSTM to obtain the latent representation of flight tracks, which adds a time control gate and an attribute control gate to the standard LSTM unit. The time control gate manipulates the action of each track point on subsequent points to obtain the characteristics of irregular time intervals. The attribute control gat enables LSTM to capture the impact of different attributes on the flight track features at various points. The clustering layer takes the latent representation of flight tracks as the input to obtain the clustering results. The clustering model updates the parameters of TA-LSTM and the cluster centers by minimizing the Kullback-Leibler (K-L) divergence. We conduct experiments using Automatic Dependent Surveillance-Broadcast track data provided by VariFlight. In comparison with popular and state-of-the-art methods, the proposed method obtains superior pe formance in three widely used evaluation metrics, i.e., Silhouette Coefficient, Calinski-Harabaz index and Davies-Bouldin index.

Airborne flight time: A comparative analysis between the U.S. and China

Actual airborne time (AAT) is the time between actual wheels-off and actual wheels-on of a flight. Given the ever-growing demand for air travel and growing flight delays, understanding the behavior of AAT is increasingly important for on time performance and delay propagation. Of particular interest is the comparison on AAT in different countries with varying air route structures, air traffic management systems, weather, and geography. This paper performs the first comparative empirical analysis of AAT behavior, focusing on the U.S. and China. The focus is on how AAT is affected by origin-destination (OD) distance, the possible pressure to reduce AAT from other parts of flight operations, hub status of departure/arrival airports, enroute and terminal traffic conditions, and convective weather. Econometric models are developed to quantify the impacts of factors on AAT behavior in China and the U.S., separately. The estimation results show that in both countries AAT is highly correlated with OD distance. Flight time in China is longer than that in the U.S. given the same OD distance which indicates a low effective speed may be the result of a low aircraft speed, or due to the flight experiencing metering, rerouting, holding or vectoring in Chinese airspace. In addition, we find that a flight has limited capability to make up for pre-departure delay. Sensitivity analysis of AAT to flight length and aircraft utilization is further conducted. Given the more abundant civil airspace, flexible routing networks, and efficient air traffic flow management (ATFM) procedures, we performed a counterfactual analysis to investigate how Chinese AATs would change if they were governed by the U.S. model. We find that this would result in significant efficiency gains for the Chinese air traffic system. On average, 13 min of AAT per flight would be saved. Systemwide fuel saving would amount to 326 million gallons with CO2 emission reduction of 2.7 million tons and direct airline operating cost saving of over $1.3 billion in 2016.

Evaluation of the performance of the multi-objective scalarization methods for the aircraft sequencing and scheduling problem using multi-criteria decision-making

PurposeThis study aims to evaluate the performance of the most popular multi-objective programming scalarization methods in the literature for the aircraft sequencing and scheduling problem (ASSP). These methods are the weighted sum method, weighted goal programming, the ε-constraint method, the elastic constraint method, weighted Tchebycheff and augmented weighted Tchebycheff.Design/methodology/approachFirst, the ASSP for a single runway case was modeled using mixed-integer programming considering the safety and operational constraints and the objectives of the minimization of total delay and total flight time for a sample airport. The objectives were then combined by using the multi-objective programming scalarization methods and various expected times of arrival–departure samples were run for the mathematical models. Finally, the methods were evaluated in terms of the number of nondominated solutions, superior nondominated solution and the average solution time using the Measurement of Alternatives and Ranking according to Compromise Solution method, which is a popular multi-criteria decision-making method.FindingsAugmented Weighted Tchebycheff was found to be the most effective approach to ASSP in terms of the evaluation criteria followed by Weighted Tchebycheff and then weighted sum method.Practical implicationsThe methodology presented in this study could provide more efficient air traffic management in terminal maneuvering areas when multiple objectives need to be optimized.Originality/valueAlthough there are studies including the comparison of several scalarization methods for other problems, the comparison of the methods for ASSP has not yet been handled in the literature. As there are several stakeholders in the air traffic system, ASSP includes several objectives, and as a result, this problem can benefit from analyses using this comparison.

Adaptive conflict resolution for multi-UAV 4D routes optimization using stochastic fractal search algorithm

The increasing unmanned aircraft system (UAS) applications in urban environments pose challenges for safe and efficient low altitude air traffic management. As an essential enabler to meet these challenges, pre-flight 4D routes optimization is required to conduct conflict detection and resolution (CD&R) and to generate conflict-free flight routes before departure. Existing studies on strategic deconfliction cover several types of strategies such as scheduling or rerouting. However, a single type of strategy used to solve different types of conflicts may lead to an unsafe and inefficient way of conflict resolution. This paper proposes an adaptive decision-making framework to optimize the resolution strategies used for different types of conflicts with explainable mechanisms. The proposed framework is formulated as a double-layer optimization problem with the considerations of scheduling, speed adjustment, and rerouting strategies for conflict resolution. The first layer of the framework is established as a probabilistic selection model to make decisions on which strategy should be selected for what type of conflict. The second layer is developed as a mixed-integer nonlinear programming (MINLP) model to optimize the decision variables of the strategies selected by the first layer. To solve the proposed double-layer optimization problem, we introduce and improve a novel meta-heuristic stochastic fractal search (SFS) algorithm with two major improvements of a penalty-guided fitness function and an exploitation-exploration balancing scheme. Simulation results demonstrate that the proposed adaptive conflict resolution framework successfully optimizes the strategies used for each type of flight conflict, which subsequently optimizes the 4D routes with significant reductions in total operational cost, number of flight conflicts, and flight delays. The improved stochastic fractal search (ISFS) algorithm is also proved effective and reliable in solving the proposed optimization problem in different traffic density scenarios.

ATMChain: Blockchain-Based Security Framework for Cyber-Physics System in Air Traffic Management

The air traffic management (ATM) system is an intelligent system that integrates the ground computer network, the airborne network, and the space satellite (communication and navigation) network. It has remarkable characteristics of cyber-physical system (CPS). The development of ATM system is inseparable from the application of new technologies. This paper proposes a security framework based on blockchain for CPS in the ATM system. Through the research on the characteristics of blockchain and CPS, this paper analyzes the necessity of integrating them into the research of the ATM system, demonstrates the feasibility of combining them, and then constructs the ATMChain framework mechanism to realize the in-depth integration of blockchain and CPS in ATM. On this basis, this paper gives the overall design architecture and implementation steps of the scheme. In addition, this paper also makes a series of analysis and demonstration from the perspective of scheme security. The research scheme will help to improve the security, reliability, and scalability of ATM services and provide a new reference for establishing a more security and efficient ATM system.

위성기반보정시스템(SBAS) APV-Ⅰ 계기접근절차에 관한 실증 연구

Along with the remarkable advances in GNSS technology, SBAS further enhances the accuracy and integrity of GNSS location information and derives improvement in the safety and efficiency of air traffic management from reducing GNSS location errors, induced by passing through the ionosphere and atmosphere, to less than three meters. In this regard, ICAO specifies the standards of SBAS signals and recommends every party to phase in by 2025; and it is foreseeable that SBAS APV-I and CAT-I will be provided in South Korea by its undertaking the development of KASS, a Korean SBAS. The purpose of the study is to design SBAS APV-I procedure on the basis of the runway 15L of Incheon International Airport and conduct obstacle assessment according to PAN-OPS Doc. 8168, focusing on the usability and usefulness of SBAS APV-I. The results show that SBAS APV-I will provide better decision height compared to other PBN RNP approach procedures such as LNAV and Baro-VNAV at the Incheon International Airport.

Identifying Operational Benefits of the Arrival Management System – A KPI-Based Experimental Method by Evaluating Radar Trajectories

The arrival management (AMAN) system is a decision support tool for air traffic controllers to establish and maintain the landing sequence for arrival aircraft. The original intention of designing the AMAN system is to improve the efficiency of air traffic management (ATM), but few studies are investigating the operational benefits of this system based on key performance indicators (KPIs) and evaluating actual data in a real-time environment. The main purpose of this paper is to propose a KPI based transferable comparative analysis method for identifying the operational benefits of the AMAN through radar trajectories. Firstly, six KPIs are established from a joint study of the mainstream ATM performance frameworks worldwide. Secondly, appropriate evaluation technique approaches are determined according to the characteristics of each KPI. Finally, a Chinese metropolitan airport is taken for the case study, and three periods are defined to form data samples with high similarity for comparative experiments. The results validate the feasibility of the proposed method and find comprehensive performance improvements in arrival operations under the effects of the AMAN system.

An explainable machine learning approach to improve take-off time predictions

Accurate aircraft trajectory predictions are necessary to compute exact traffic demand figures, which are crucial for an efficient and effective air traffic flow and capacity management. At present, the uncertainty of the take-off time is one of the major contributions to the loss of trajectory predictability. In the EUROCONTROL Maastricht Upper Area Control Centre, the predicted take-off time for each individual flight relies on the information received from the Enhanced Traffic Flow Management System. However, aircraft do not always take-off at the times reported by this system due to several factors, which effects and interactions are too complex to be expressed with hard-coded rules. Previous work proposed a machine learning model that, based on historical data, was able to predict the take-off time of individual flights from a set of input features that effectively captures some of these elements. The model demonstrated to reduce by 30% the take-off time prediction errors of the current system one hour before the time that flight is scheduled to depart from the parking position. This paper presents an extension of the model, which overcomes this look-ahead time constraint and allows to improve take-off time predictions as early as the initial flight plan is received. In addition, a subset of the original set of input features has been meticulously selected to facilitate the implementation of the solution in an operational air traffic flow and capacity management system, while minimising the loss of predictive power. Finally, the importance and interactions of the input features are thoroughly analysed with additive feature attribution methods.

Modeling Arrival Flight Times within the Terminal Airspace

Air traffic management efficiency in the descent phase of flights is a key area of interest in aviation research for the United States, Europe, and recently other parts of the world. The efficiency of arrival travel times within the terminal airspace is one of nineteen key performance indicators defined by the Federal Aviation Administration (FAA) and the International Civil Aviation Organization, typically within 100 nmi of arrival airports. This study models the relationship between travel time within the terminal airspace and contributing factors using a multivariate log-linear model to quantify the impact that these factors have on the total travel time within the last 100 nmi. The results were compared with the baseline set of variables that are currently used for benchmarking at the FAA. The analyzed data included flight and weather data from January 1, 2018 to March 31, 2018 for five airports in the United States: Chicago O’Hare International Airport, Hartsfield-Jackson Atlanta International, San Francisco International Airport, John F. Kennedy International Airport, and LaGuardia Airport. The modeling results showed that there is a significant improvement in prediction accuracy of travel times compared with the baseline methodology when additional factors, such as wind, meteorological conditions, demand and capacity, ground delay programs, market distance, time of day, and day of week, are included. Root mean squared error values from out-of-sample testing were used to measure the accuracy of the estimated models.

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.

A Practical Approach to Monitor Capacity under the CDM Approach

The operations of take-off and landing at hub airports are often subject to a wide variety of delays; the effects of these delays impact not only the related stakeholders, such as aircraft operators, air-traffic control unity and ground handlers but as part of the European network, delays are propagated through the network. As a result, Airport Collaborative Decision Making (A-CDM) is being employed as a methodology for increasing the efficiency of Air Traffic Management (ATM), through the involvement of partners within the airports. Under CDM, there are some strategic common objectives regardless the airport or the partner specific interest to improve operational efficiency, predictability and punctuality to the ATM network and airport stakeholders. Monitoring and controlling some strategic areas such as, Efficiency, Capacity, Safety and Environment is needed to achieve the benefits. Therefore, the present work aims to provide a framework to monitor the accuracy of capacity in the three main flight phases. It aims to provide a comprehensible and practical approach to monitoring capacity by identifying and proposing Key Performance Indicators (KPIs) based on the A-CDM Milestone Approach to optimise the use of available capacity. To illustrate our approach, Amsterdam Airport Schiphol is used as case study as a full A-CDM airport.

Machine Learning Aided Air Traffic Flow Analysis Based on Aviation Big Data

Timely and efficient air traffic flow management (ATFM) is a key issue in future dense air traffic. The emerging demands for unmanned aerial vehicles and general aviation aircraft aggravate the burden of the ATFM. Thanks to the advanced automatic dependent surveillance-broadcast (ADS-B) technique, the aerial vehicles can be tracked and monitored in a real-time and accurate manner, providing possibility for establishing a more intelligent ATFM architecture. In this article, we first form an aviation Big Data platform by using the distributed ADS-B ground stations and the obtained ADS-B messages. By exploring the constructed dataset and mapping the extracted information to the routes, the air traffic flow between different cities can be counted and predicted, where the prediction task is implemented on the basis of two machine learning methods, respectively. The experimental results based on real-world data demonstrate that the proposed traffic flow prediction model adopting long short-term memory (LSTM) can achieve better performance, especially when abnormal factors in traffic control are considered.

Feasibility Study on Improvement of Cruise Flight Time Prediction via Aircraft Mass Estimation during Climb Trajectory

A precise and accurate trajectory prediction is indispensable for efficient air traffic management with a large traffic throughput achieved by four-dimensional trajectory prediction. Recent aircraft are able to fly along their optimum trajectories. The configurations of these optimum trajectories also depend on aircraft mass. However, information on aircraft mass are generally unavailable for air traffic controllers; they are seldom applied for actual operations. To overcome such inconvenience, recent studies demonstrated aircraft mass estimation from their flight trajectories. This study further aims at applying the mass estimation for the prediction of cruise flight time. Aircraft mass are estimated from actual climb trajectory data, and the correlation between the estimated mass and flight time error are confirmed. The regression and correction has revealed that the presented methodology is able to reduce the mean square error of the flight time prediction by half.

Service assurance packet-scheduling algorithm for a future aeronautical mobile communication system

In recent years, realizing safe and efficient air traffic management (ATM) has become one of the most important social issues because of the rapid increase in air traffic volume. To realize safe and efficient ATM, it is necessary for related stakeholders to share aeronautical big data by connecting to aircrafts and ground systems efficiently and globally. However, the current aeronautical communication systems are not adapted to be used in support of global collaborative decision making (CDM) through information exchange. In order to accelerate the implementation of information collaborative environment and improve operational awareness in the aeronautical domain, this study focuses on an information platform for sharing aeronautical big data, and a communication medium for achieving Internet of aeronautical things. This paper proposes a new packet-scheduling algorithm for a next-generation aeronautical mobile communication system that includes various types of services and devices. The algorithm balances service assurance and service fairness using strict priorities for real-time services and loose priorities for non-real-time services. Performance evaluations were conducted using a network simulator to confirm the effectiveness of the proposed algorithm. First, a simple single-device scenario was utilized to confirm the effectiveness of the quality of service function for an aeronautical mobile communication system. Second, a multiple-device scenario was employed to evaluate the performance of the proposed scheduler. Finally, an airport scenario was used to demonstrate the effectiveness of our algorithm in a more practical situation. Furthermore, we show that the airport scenario is useful for evaluating the overall performance of a new aeronautical mobile communication system in the system introduction phase or cell design phase.

ECONOMIC AND FINANCIAL ASPECTS OF AIR TRAFFIC MANAGEMENT IN POLISH AIRSPACE

The article discusses selected provisions of EU aviation law concerning economic issues of air traffic management. This process in European airspace is carried out by air navigation service providers, which, unlike airport operators and air carriers, have a monopolistic position and do not operate under market conditions. Consequently, the lack of competition between air navigation service providers replaces the common charging system for airspace users established by European Union law. In order to increase the cost-effectiveness of the services provided while maintaining a high level of safety of air operations, the navigation charges system was linked to the parallel implementation of the Single European Sky performance scheme for air navigation services in 2010. In 2019, the rules governing both systems were consolidated into a single legal act. The study also looks at the basic indicators of economic efficiency of air traffic management based on the example of the Polish Air Navigation Agency.

Interdependent Uncertainty Handling in Trajectory Prediction

The concept of 4D trajectory management relies on the prediction of aircraft trajectories in time and space. Due to changes in atmospheric conditions and complexity of the air traffic itself, the reliable prediction of system states is an ongoing challenge. The emerging uncertainties have to be modeled properly and considered in decision support tools for efficient air traffic flow management. Therefore, the subjacent causes for uncertainties, their effects on the aircraft trajectory and their dependencies to each other must be understood in detail. Besides the atmospheric conditions as the main external cause, the aircraft itself induces uncertainties to its trajectory. In this study, a cause-and-effect model is introduced, which deals with multiple interdependent uncertainties with different stochastic behavior and their impact on trajectory prediction. The approach is applied to typical uncertainties in trajectory prediction, such as the actual take-off mass, non-constant true air speeds, and uncertain weather conditions. The continuous climb profiles of those disturbed trajectories are successfully predicted. In general, our approach is applicable to all sources of quantifiable interdependent uncertainties. Therewith, ground-based trajectory prediction can be improved and a successful implementation of trajectory-based operations in the European air traffic system can be advanced.

Impact of optimised trajectories on air traffic flow management

ABSTRACTMulticriteria trajectory optimisation is expected to increase aviation safety, efficiency and environmental compatibility, although neither the theoretical calculation of such optimised trajectories nor their implementation into today’s already safe and efficient air traffic flow management reaches a satisfying level of fidelity. The calibration of the underlying objective functions leading to the virtually best available solution is complicated and hard to identify, since the participating stakeholders are very competitive. Furthermore, operational uncertainties hamper the robust identification of an optimised trajectory. These uncertainties may arise from severe weather conditions or operational changes in the airport management. In this study, the impact of multicriteria optimised free route trajectories on the air traffic flow management is analysed and compared with a validated reference scenario which consists of real flown trajectories during a peak hour of Europe’s complete air traffic in the upper airspace. Therefore, the TOolchain for Multicriteria Aircraft Trajectory Optimisation (TOMATO) is used for both the multicriteria optimisation of txrajectories and the calculation of the reference scenario. First, this paper gives evidence for the validity of the simulation environment TOMATO, by comparison of the integrated reference results with those of the commercial fast-time air traffic optimiser (AirTOp). Second, TOMATO is used for the multicriteria trajectory optimisation, the assessment of the trajectories and the calculation of their integrated impact on the air traffic flow management, which in turn is compared with the reference scenario. Thereby, significant differences between the reference scenario and the optimised scenario can be identified, especially considering the taskload due to frequent altitude changes and rescinded constraints given by waypoints in the reference scenario. The latter and the strong impact of wind direction and wind speed cause wide differences in the patterns of the lateral trajectories in the airspace with significant influence on the airspace capacity and controller’s taskload. With this study, the possibility of a successful 4D free route implementation into Europe’s upper airspace is proven even over central Europe during peak hours, when capacity constraints are already reaching their limits.