Urban air mobility (UAM) is presented as a potential solution to urban congestion. By utilising aerial vehicles for tasks like parcel delivery, public transport, and surveillance, pressure on traditional ground-based transportation infrastructure can be alleviated. This is particularly important with the rise of e-commerce and the increasing demand for fast and efficient delivery methods. UAM has the potential to revolutionise urban travel, offering faster commutes and enhancing surveillance capabilities for improved traffic management and emergency response.

The U-space concept, developed within the European Union, provides a framework for the safe integration of drones and small unmanned aircraft systems (sUAS) into urban airspace. It focuses on establishing services, regulations, and procedures to manage UAM operations effectively. An important component of this concept is Type Zu airspace, designated for high-density urban operations. This airspace requires strict regulations and safety-critical services like dynamic capacity management, conflict resolution, and continuous monitoring to ensure safe and efficient U-space operations.

Conflict detection and resolution (CD&R) of air traffic is required to ensure the safety of such operations, and VLL urban airspace presents unique challenges compared to conventional air traffic management. Buildings and other obstacles restrict aircraft movement, making manoeuvring and conflict avoidance more difficult. Unpredictable urban wind patterns further complicate flight planning and trajectory prediction. These factors, combined with the inherent complexity of urban environments, necessitate the development of robust CD&R algorithms and rules specifically tailored to the challenges of VLL urban airspace.

The core research objective of this dissertation is to identify and develop effective CD&R algorithms and rules for safe and efficient UAM operations in VLL urban airspace. This involves evaluating the limitations of existing CD&R methods, designing new algorithms that address the specific challenges of urban environments, and defining clear rules and procedures for aircraft navigation and conflict resolution…
@en

This thesis investigates future air traffic growth projections for an en-route environment and its impact on airspace complexity. The study compares Free Route Airspace, FRA, with the traditional ATS Routes Network, assessing airspace efficiency through various complexity metrics, including flight interactions, air traffic controller workload, and traffic patterns. These complexity metrics present the dependent variables of the study. The research builds a simulation model where the independent variables are the size of airspace, the type of demand, and the operational environment. With help of BlueSky ATM Simulator, the simulation model shows how independent variables can affect the complexity metrics. Additionally to this, the study evaluates the environmental impact by measuring CO2 emissions, which are found to be significantly lower under the FRA due to more direct routing. Also, the findings of this research suggest that FRA offers more efficient traffic distribution, particularly in larger airspace areas. In smaller airspace areas, the controller workload increases due to less predictable flight paths and the more flight interactions under Free Route airspace environment. The study concludes that FRA is advantageous for larger airspace areas, enhancing efficiency and sustainability, but it also introduces challenges in managing air traffic, particularly in smaller or highly concentrated airspace environments.

The advent and rise of low-cost, high-frequency short-haul flights in Europe increasingly necessitates the need of more sustainable travel methods for trips with a distance under 1000 km. Many different proposals and policies have been put in place, including full flight bans for trips under 500 km, but the research space still has not embraced a possible co-existence of major air and ground transport options in this segment.

This research addresses this by developing a reproducible method using openly accessible data to assess air and rail network capacities of three of the busiest air transport routes in Europe. A capacity analysis is conducted and the modelling of travel time, travel cost, change in carbon dioxide emissions and passenger experience is performed, in order to investigate the feasibility and logistics of shifting passengers between air and rail.

The study finds that 30-50% of passengers could shift completely to trains, given sufficient rail network capacity, significantly reducing total carbon dioxide emissions and improving passenger experience throughout.

Predicting aircraft Take-Off Weight (TOW) has been a long-sought task by aviation stakeholders, especially for operational and regulatory bodies involved in flight planning. Unfortunately, TOW being a sensitive parameter to operational trends and cost indices, aircraft operators tend to keep it confidential. In recent years, Machine Learning (ML) algorithms have achieved increased prediction accuracy and capabilities in the field, provided the availability of TOW data. This paper studies the implementation of gradient boosting algorithms as well as Random Forests to better understand which algorithm is best-suited for aircraft TOW prediction (prior to take-off) solely based on Flight PLan (FPL) and Terminal Aerodrome Forecast (TAF) parameters. The study focused on flights at Amsterdam Airport Schiphol (AMS) for training the algorithms, using an 80-20% train-test split. Between Gradient Boosting Decision Trees (GBDTs), LightGBM, XGBoost, and Random Forests, GBDTs achieved the smallest Mean Absolute Percentage Error (MAPE) with 1.71 and 2.17% on the training and testing datasets, respectively. The most influencing feature proved to be the requested cruise speed, followed by great circle distance between airports, and aircraft type. The model was validated on Paris - Charles de Gaulle Airport (CDG) and Brussels South Charleroi Airport (CRL), proving its independence from airport type. However, the distribution of flights in the training dataset, especially that of aircraft and airline types, proved to be an influencing factor for the model's applicability to other airports. Future work includes expanding the training dataset to all flights in the European network, and introducing trajectory-based features such as aircraft speed intent. With a larger training dataset, neural network algorithms could also be explored. Finally, regarding the improvement of trajectory predictions, it was found that better accuracy of TOW predictions does not suffice and that other operational parameters' effect should be investigated, especially speed profiles.

This research investigates the role of time prediction accuracy in optimizing Continuous Descent Operations (CDO) within the aviation sector, with a specific focus on assessing the additional benefits brought forth by the integration of Air-Ground Datalink technologies. Continuous Descent Operations, characterized by uninterrupted and efficient descent profiles, hold promise for reducing fuel consumption, emissions, noise, and overall operational costs. However, the extent to which accurate time predictions contribute to the success of CDO remains a critical yet understudied aspect.

The use of drones in combination with a delivery truck can have a significant impact in improving the efficiency of last-mile delivery. Drones can be dispatched to customers from the truck, allowing the truck to continue delivering packages at the same time. This approach gives rise to the widely researched Traveling Salesman Problem with multiple Drones (TSP-mD). Numerous heuristic models have been developed to solve the problem in a near-optimal manner. However, these optimization strategies do not account for disruptions, which are common in delivery networks and can negatively impact their performance. While existing literature usually considers static models, a more dynamic approach could address these disruptions by adapting to real-time circumstances. To explore this, a dynamic method is developed in this paper for solving the TSP-mD. Its efficiency is compared to an existing static heuristic model from the literature. The comparison is performed in the BlueSky Open Air Traffic simulator, in which disruptions are introduced, such as truck delays and drone speed variations. Experiments in this environment demonstrate that the existing algorithm consistently achieves shorter mission completion times across all uncertainty settings. However, the newly developed method shows a significant improvement in performance under uncertain conditions. Therefore, the use of global optimization for the TSP-mD should be reconsidered.

This paper explores the impact of Automatic Dependent Surveillance - Contract (ADS-C) on air traffic control (ATC) procedures, focusing on operational efficiency and safety margins in lower airspace. Through 64 simulation configurations, the study evaluates how varying airspace density, separation buffer size, and vertical error in ADS-C data influence operational metrics, such as fuel burn, track miles, and flight time. The simulations utilize synthetic ADS-C data with a 100% equipage rate, providing insights into how ADS-C can be applied to manage intersecting flight trajectories. Results indicate that separation buffer size is the most influential factor. Smaller buffers lead to significant reductions in fuel burn, track miles, and flight time compared to the baseline, though this comes at the expense of increased conflict risks. Airspace density demonstrated trends where higher densities showed the greatest fuel savings but more conflicts, highlighting a trade-off between operational efficiency and safety. These findings support the role of ADS-C in increasing predictability and improving trajectory management, both of which are key to Trajectory-Based Operations (TBO). By improving the accuracy of aircraft intent and trajectory data, ADS-C can optimize flight paths and enable more efficient air traffic management. However, carefully considering separation buffers and airspace density is essential to balance efficiency with safety.

The aerospace industry annually provides transport for billions of passengers along trillions of kilometers. The industry is continuously aiming to provide these services in a more efficient and sustainable way. One possibility is to consider improving airside airport operations, both current types and those expected in the near future. Scheduling airport operations requires taking into account flight planning, airport layout, routing requirements and personnel planning. Current operational planning is characterised by application of linear programming tools for strategic planning, and manual adjustment for adaptive planning.

This dissertation aims to develop data-driven optimisation models, to increase the efficiency and sustainability of various airside airport operations, and to apply these models to airport case studies. The focus is first put on external electric taxiing, a new taxiing technique using electric towing vehicles (ETVs) to tow aircraft from gates to runways and vice versa. Many airports are considering to implement this technique, as it offers a large improvement in reducing their greenhouse gas emissions, noise levels and air pollution, which is an improvement for passengers, airport personnel, and local residents.

The first goal is to create a comprehensive overview of the operational aspects of external electric taxiing, by reviewing existing research work and industry sources. This overview includes the expected specifications of ETVs and the future procedures for electric taxiing movement. Electric taxiing introduces a new airside operation to the airport: ETV-to-aircraft scheduling. Studies on this new operation, as well as on vehicle routing, vehicle fleet sizing and battery charging optimisation models, which are needed for electric taxiing, are reviewed. The overview also includes the remaining research challenges to achieve large-scale ETV implementation in the next few decades.

The second goal is to develop an optimisationmodel to performETV-to-aircraft scheduling that takes into account realistic airport circumstances. A more efficient ETV-toaircraft schedule, which allows more aircraft to be towed by an ETV fleet, will reduce airport emissions more. Some studies have already proposed ETV-to-aircraft scheduling models. However, they do not include all elements needed to make the model realistic and comprehensive, such as routing with conflict and collision avoidance, ETV charging and discharging, and airport surface movement specifications. Two more elements are added to this list in this work: airport electricity capacity and achieving a time-efficient model. Two models are developed for full-day ETV-to-aircraft scheduling, a Mixed-Integer Linear Programming (MILP) model and an Adaptive Large Neighbourhood Search (ALNS) model. Both models limit ETV charging to the electricity capacity of the airport. The ALNS model is able to create near-optimal full-day schedules for large fleet sizes within a few hours, for a large airport case study. The ALNS model is tested with various daily electricity capacity profiles, which shows the necessity of night charging and the effects of increasing amounts of charging during the day.

The third goal is to develop an optimisation approach to retain efficiency for electric taxiing in a real-time situation. The models developed for the second goal are applicable for strategic scheduling. During operation, disruptions to the strategic schedule will occur, and adaptive scheduling is required to continue operation. In this dissertation both a strategic and disrupted scheduling model are developed. The disrupted model reassigns delayed aircraft to ETV, aiming to minimize the changes to the original schedule. The model is used to create an adaptive schedule in a large airport case study using historical flight data. At the start of every half hour period, the disruptions due to flight delays of the next period are incorporated in a new schedule. The results show the efficacy of the disrupted model in minimizing schedule changes, which does not come at the expense of emission savings. In addition to electric taxiing, this dissertation focuses on improving the efficiency and robustness of airside operations by predicting airport disruptions, to avoid additional use of resources and to provide a better service. Where the previous part consists of using models to react to flight delays, operations can also be improved by predicting them in advance. In existing works, delays are predicted by classification or as point prediction. In this dissertation, probabilistic prediction is applied to flight delay, using two machine learning algorithms: Mixture Density Networks and Random Forests Regression. In addition, metrics suited to probabilistic prediction are developed and used to evaluate the algorithm performance. In a small airport case study, the algorithms are shown to be able to predict delays within a Continuous Ranked Probability Score (CRPS) of eleven minutes. The probabilistic prediction algorithms generate estimated delay distributions, which include extended uncertainty information. To illustrate the utility of the predictions for airport operations, they are applied in a probabilistic model aimed to increase the robustness of the flight-to-gate assignment problem. The proposed model is shown to reduce the number of gate-conflicted aircraft by up to 74% when compared to a deterministic flight-to-gate assignment model. The robustness of the assignment can be controlled with a model parameter.

Another method for predicting flight delays is binary classification, which is popular in literature. However, when posed as a binary problem, flight delay and also flight cancellation prediction suffer from a large data imbalance. This causes a distorted view when using metrics such as accuracy. This dissertation develops a systematic approach to binary prediction with imbalanced data, by considering a range of sampling ratios and various sampling techniques. Two machine learning algorithms are applied to a small airport historical flight dataset. The results underline the need to investigate the influence of varying data imbalance ratios on the performance of classification algorithms in various metrics.

Throughout this dissertation, the focus has been on improving the sustainability and efficiency of airport operations through data-driven approaches. These approaches include MILP models, heuristics and machine learning models. The developed models provide support for airport planners to improve current and future scheduling tasks. However, it remains future work to apply similar techniques to other airside operations and to further improve the realism and real-time usability of the current models. In addition, airports’ spatial planners, air traffic controllers and ETV developers will play a critical role in the further development and implementation of electric taxiing. Overall, this dissertation forms a starting point for airport planners aiming to use data-driven methods to improve the sustainability and efficiency of airports, to ensure more durable and reliable air transportation services.@en

Charting hyperlocal wind using a drone is a challenge of increased attention as it unlocks potential in a variety of fields. In context of the METeo Sensors In the Sky project, this study proposes a method to estimate the magnitude and direction of wind using a quadcopter in hover and cruise without a dedicated wind sensor. Only on-board sensors are used, with no knowledge of thrust and rpm. A deterministic method models drag experienced by the drone classically as a quadratic function of true airspeed, and estimates wind by deducting the estimated true airspeed with the GPS ground speed. Additionally, a particle filter is implemented and compared to the deterministic method. To validate the proposed methods, a series of verification flights is conducted in which the drone is flown straight into the wind, perpendicular to, and away from the wind. The results show that the proposed method can estimate wind for various ground speeds and altitudes. The root mean square error ranges between 0.3-2.0 m/s and 5-35 degrees in most scenarios with high true airspeeds. In most cases, the particle filter shows a slight improvement over the deterministic method, at the cost of reduced adaptivity to wind changes (gusts).

Air traffic sector demand and capacity balancing is an important process to enable safe and efficient flight execution. In current operations, demand and capacity are determined based on schedules and flight plans. In reality, disruptions to flights create a different situation that may not have been anticipated by the Air Navigation Service Provider (ANSP). Wrong demand forecasts may cause unnecessary network regulations or inefficient flight execution. This research aims to improve air traffic sector demand forecasting, by exploring machine learning based trajectory prediction. In light of the Trajectory Based Operations (TBO) concept that is being developed within Air Traffic Management (ATM) research, a trajectory-based approach is taken to improve demand forecasts. To achieve this, the transformer neural network was identified as a suitable generative model that can predict aircraft trajectories. Using available traffic messages from the Eurocontrol Business-to-Business (B2B) connection, and actual trajectories obtained from the OpenSky ADS-B repository, a successful transformer neural network was built. This trajectory predictor could accurately generate trajectories, outperforming the flight plan and other neural network approaches by a large margin. For demand prediction, the introduction of improved trajectories provided small gains that could potentially lead to more stable predictions.

As aviation recovers to pre-pandemic levels large amounts of Air Traffic Flow Management delay also return, as the traffic at airports and in airspaces reaches their old levels. These delays have a yearly cost of around 500 million euros in the European Civil Aviation Conference area and are detrimental to the experience of passengers. This paper proposes a change in the interaction between the A-CDM process at Schiphol and EUROCONTROL's Network Manager, varying at what point the slot improvement process for regulated flights is stopped; providing more transparency in the network with this change. The resulting change in ATFM delay is investigated by modelling these two systems and freezing the slots at a set time, using historical input data to accurately model the turnaround process. The results generated using the described methods are inconclusive. More data and an additional implementation of using the CTOTs calculated by the model in the simulated turnaround are needed in order to make statistically sound conclusions on whether changing the T-DPI-s horizon has any effect. Nevertheless, this paper still presents insights and a novel framework for continued research into the subject.

In order to enable the safe and efficient integration of Unmanned Aerial Vehicles into very low level airspace, modern day research focuses on the development of new traffic services and procedures. One of these is the geovectoring protocol, which aims to reduce traffic complexity by setting limits on the allowed ground speed, course, and vertical speed. A geovector can be used to increase the capacity of an airspace by lowering the conflict rate. However, problems with priorities emerge when performing conflict resolution maneuvers in geovector airspace, as the limits are ignored in this process. A powerful conflict resolution algorithm is the Modified Voltage Potential (MVP). This research proposes an extension to the MVP ruleset, based on Velocity Obstacle theory. Making use of an alternative conflict resolution maneuver which respects the geovector, five resolution strategies are defined with different priority settings for the separate limits. The performance of these strategies is compared to pure MVP on geovector, safety, and stability measures, making use of fast-time simulations in a corridor airspace. All resolution strategies show improvements on the ability to perform conflict resolution maneuvers within the geovector limits, albeit at the expense of safety and stability. It is recommended to further investigate the performance of the geovector resolution strategies for other types of airspace, to verify whether the observed reduction in conflict rate from the geovectors can be reinforced by the resolution strategies.

To facilitate an increase in air traffic volume and to allow for more flexibility in the flight paths of aircraft, an abundance of decentralized conflict resolution (CR) algorithms have been developed. The efficiency of such algorithms often deteriorates when employed in high traffic densities. Several methods have tried to prioritize certain conflicts to alleviate part of the problems introduced at high traffic densities. However, manually establishing rules for prioritizing intruders is a difficult task due to the complex traffic patterns that emerge in multi-actor conflicts. Reinforcement Learning (RL) has demonstrated its ability to synthesize strategies while approximating the system dynamics. This research shows how RL can be employed to improve conflict prioritization in multi-actor conflicts. We employ the Proximal Policy Optimization algorithm with an actor-critic network. The RL model decides on intruder selection based on the local observations of an aircraft. It was trained on a limited number of conflict geometries in which it was able to significantly reduce the number of intrusions. A conflict prioritization strategy was then formulated based on the decisions taken by the RL model during training. We show that the efficacy of a conflict resolution algorithm that adopts a global solution, the solution space diagram (SSD) in this research, can be improved when utilizing this conflict prioritization strategy. Finally, these results were compared to the performance of a pairwise CR method, the Modified Voltage Potential (MVP). Even though MVP resulted in a smaller number of intrusions compared to SSD with conflict prioritization, the prioritization strategy did reduce the gap between the two CR methods.

Radio frequency fingerprinting has been identified as a method to increase integrity in aircraft surveillance while retaining its openness. One way to uniquely determine transmitting devices is to distill the device its radio frequency (RF) fingerprint by looking at the physical features of the message signal it transmits. This physical layer fingerprint is the unique trace the transmitter leaves in the signals. This research proposes a method to RF fingerprint ADS-B and VDL2 messages to identify the transmitting aircraft using a complex-valued convolutional neural network model. Raw data from ADS-B and VDL2 messages are collected over multiple days using low-cost RTLSDR hardware. Results show that the model can identify ADS-B and VDL2 messages from up to 200 different aircraft based on the raw IQ preamble and bit synchronization samples of both signal protocols. Further analysis of the robustness of the model shows that the model accuracy can be highly affected by changing channel conditions during training and testing. This research shows that testing the RF fingerprinting model’s robustness to channel conditions is necessary since the models are prone to mistakenly considering channel information as transponder RF features.

During the COVID-19 pandemic people living close to the airport got accustomed to less flights, and therefore less noise disturbance. Now the amount of traffic is increasing again and so is the noise disturbance. For this research specifically the optimizing task of distributing of arriving aircraft over the IAF is addressed, as often the shortest transition routes from an IAF towards the runway go over densely populated areas, but flying via another IAF results in longer flying times and thus more CO2 emissions. A tool that is able to quantitatively make a trade-off between noise and emission is required to provide a basis for the distribution of aircraft over the IAF. In this research the feasibility and effects of using an expanded version of the aircraft landing problem to create the IAF Selection Optimization tool is studied, including the effects of different settings for the tool. As a case study Amsterdam Airport Schiphol is used, as it is a busy airport that lies close (11km) to the city center of Amsterdam. In this paper first the methodology of the IAF Selection Optimization tool is explained, and afterwards the working of the tool is discussed by running various scenarios for three different days from 2019 at AAS. For all scenarios an optimal and feasible solution was found by the tool, based on the input variables selected for each scenario. It could therefore be concluded that the IAF Selection Optimization tool provides a means to optimally distribute aircraft based over the IAF based on a quantitative trade-off.

Airspace’s increasing demand is a current concern without a solution. Different research projects aim to expand its available capacity by improving software performance, for example, concerning trajectory prediction and conflict detection methods. This research contributes to this goal by investigating the effect of different look-ahead time values on a state-based conflict detection method’s performance. A parallel analysis is made concerning the traffic density and meteorological conditions’ influence.

The simulations use actual air traffic data, obtained from the OpenSky database. Corrective data processing is implemented to minimize the noise due to data resolution issues, and time shifting techniques are analyzed and implemented to counteract the human bias natural in real recorded data. The chosen air traffic simulator is the open-source BlueSky Simulator, which integrates the state-based method analyzed. The data is selected considering the traffic density (Eurocontrol database) and the meteorological conditions (ERA5 data from Climate Copernicus) since Light, Medium, and High bins are created. The traffic density bins generation makes use of k-clustering, while the meteorological conditions bins go through a more complex process to identify atmospheric cold fronts.

The performance is obtained for different classification approaches, showing the impact more flexible metrics have on the results. For flexible metrics, the performance of the state-based conflict detection method is higher than for stricter metrics. For the first one mentioned, values higher than 120s look-ahead time are not fruitful, while, for the second one, all look-ahead times are not effective in state-based conflict detection. An analysis focusing on the flight phase showed the performance is better for the cruise phase, raising the effective look-ahead times to 300s and 180s for each approach, respectively.

Concerning the secondary independent variables, firstly, a higher traffic density environment translates to a lower conflict detection performance. Secondly, the meteorological conditions bins’ difference is not enough to withdraw conclusions, even though it follows a similar trend to the traffic density values.

The International Air Transport Association (IATA) and the European Commission (EC) have stated their desire for the aviation industry to reach net zero carbon emissions by 2050 and in addition these emissions must be reduced by 45% in 2030. In order to reach these goals, all possible contributions to a reduction in carbon emissions are considered. One of these is the Air Traffic Management (ATM) procedure of Continues Descent Operations (CDO). These operations describe a flight path for the approach where there are minimum level flight segments. This paper investigates the maximum possible impact of this procedure for maximum capacity operations. Four different days have been analysed where the individual components of the procedure are investigated; vertical optimisation, lateral optimisation and the combined case. Using ADS-B data from busy days in august of 2019, these procedures are described and simulated using fast-time ATM simulation software Bluesky using Base of Aircraft Data (BADA) performance data and total-energy model. Compared to current operations, vertical optimisation could possibly safe 20% of fuel, lateral optimisation could theoretically safe 16% fuel and the combined case has the potential to safe up to 27% fuel without negatively impacting capacity.

Testing novel concepts in the allocation and use of aircraft is commonly done in air traffic simulators. Current day simulators rely on proprietary models and often propose questionable solutions. This paper uses BlueSky as simulator, in cooperation with performance models OpenAP and BADA. BlueSky aims to provide the user with full freedom to simulate any scenario. Improving BlueSky and adding functionality further aids in this goal. By expanding logic of the simulator, the user should attain more functionality without compromising the user-friendliness of BlueSky. This paper treats the implementation of thrust setting and flight path angle in BlueSky. This enables continuous descent operations to become part of the possibilities within BlueSky. The challenge was to prepare a set of ADS-B data using Fuzzy logic to validate the new model. Its robustness was then be demonstrated using a large number of flights.

The airspace in western Europe is one of the most complex airspaces globally. With the air space already operating near maximum capacity, innovations are needed to increase airspace efficiency. This research aims to design and test a debunching concept for inbound air traffic to increase the efficiency of the arrival traffic stream. A probabilistic debunching concept is created for the Initial Approach Fix using Probability Density Functions fitted on the errors in predicted arrival times provided by the EUROCONTROL Enhanced Tactical Flow Management System Flight Data messages (EFD). A bunching probability is detected when two or more aircraft have a probability of arriving at the Initial Approach fix simultaneously or within the required Wake Category Separation. A debuncher is created using a Constrained Genetic Algorithm that decreases the bunching probability by imposing en-route delay on arriving air traffic. The results show that the bunching probability increases with shorter prediction horizons as the uncertainty in the arrival estimates decreases. It is shown that with the probabilistic debunching method, it is possible to decrease the delay in the Arrival Manager by imposing delay en-route. However, at prediction ranges before 40 minutes before arrival at the IAF, the decrease in the AMAN delay is not consistent, indicating that the trajectory prediction uncertainty at this range is too high. Furthermore, the decrease in the AMAN delay is often lower than the imposed delay by the debuncher, showing that the decrease in AMAN delay comes at the cost of extra delay en-route. It is concluded that when the uncertainty in the trajectory predictions is decreased, the effectiveness of the debuncher increases and the effect on the Arrival Manager is improved, indicating improved arrival efficiency.

For future operations of unmanned aviation, even higher traffic densities than previously seen in manned aviation are expected. Previous work has shown that a vertically layered airspace design performs best at improving safety metrics such as the total number of conflicts and Losses of Separation (LoSs). Furthermore, it has been shown that machine learning techniques are capable of selecting heading ranges for the vertically stacked layers in non-uniform traffic scenarios, in order to reduce the number of conflicts and LoSs compared to uniform structures. These works, however, set structures in an ‘empty’ airspace and do not take into account the necessary vertical deviations to get from one structure to the next. In this work reinforcement learning (RL) agents are used to select layer heading ranges, while taking into account the previous airspace structure. During this dynamic structuring, several challenges arise. First, it is not clear how to reduce the number of vertical conflicts when aircraft move into a new airspace structure. Second, specific structures should be selected that reduce the necessary vertical deviations from the old structure, while still minimising the cruising conflicts for the new traffic distribution. The present work is divided into three experiments. Experiment I focused on analysing the number of conflicts and LoSs that aircraft suffer during vertically moving towards their layer in the new structure. Experiment II tested whether a RL agent is capable of setting an aircraft structure in function of the expected future traffic scenario. Experiment III aimed to show the capability of a RL agent to select airspace structures, while taking into account the previous airspace structures, in order to decrease the number of vertical conflicts. The results of the research show that RL methods are capable of defining airspace structures appropriate for a given traffic scenario. For dynamic reconfiguration, it proved challenging to simulate traffic scenarios that cause an agent to select different structures to prevent the occurrence of vertical conflicts. Under the experimental conditions employed, analytical methods of structure selection performed better in terms of safety.