Alumni

Schiphol’s current Departure Manager (DMAN) system, built around Target Off-Block Times (TOBT) and fixed 10-minute bins, offers operational stability but lacks the granularity needed to efficiently sequence departures in a high-density environment. This research investigates the integration of the Predicted End of Ground Handling Time (PEGT) into the DMAN. This new PEGT is a machine learning-based estimate developed by Schiphol Aviation Solutions’ Deep Turnaround project. PEGT leverages image-based machine learning algorithms to monitor over 70 unique turnaround events in real-time, generating predictive insights from over 150,000 historical turnarounds. These predictions enable early delay detection (up to 40 minutes in advance), supporting more precise TOBT estimates and improved gate and runway slot usage. Building on previous work and aligned with SESAR’s integrated DMAN-AMAN vision, this study also questions the effectiveness of rigid 10-minute departure bins. Using historical PEGT & TOBT data together with simulation models inspired by traffic flow constraints, this project evaluates dynamic bin sizing and delay damping mechanisms. The goal is to find a balance between operational stability and responsiveness in pre-departure sequencing. By combining turnaround predictions with more flexible pre-departure scheduling, this research aims to improve DMAN’s ability to manage departure flows efficiently, reduce last-minute gate conflicts, and enhance overall airport throughput at complex hub airports like Schiphol.

The integration of artificial intelligence (AI) in air traffic management (ATM) is expected to play a key role in improving efficiency, prediction, and safety. International programs such as SESAR and NextGen outline recurring domains where AI could add value, including trajectory prediction, conflict detection, speech recognition, anomaly detection, and human–machine teaming. For LVNL, however, it is not yet clear which of these applications are both relevant and feasible in daily operations.

My thesis focuses on identifying and evaluating AI applications that can realistically be adopted within the Dutch ATM context in the short term. The research begins by reviewing international frameworks and academic studies to determine which applications are sufficiently mature to be considered within the coming five years. These applications are then linked to LVNL’s organizational functions and assessed against three feasibility dimensions: operational fit, compliance with safety and cybersecurity requirements, and acceptance by air traffic controllers. The outcome of the study will be a prioritized set of AI opportunities that combine potential benefits with practical feasibility. In this way, the research provides LVNL with a concrete basis for deciding which AI applications to explore further, supporting both operational efficiency and the continued modernization of Dutch air traffic management.

Currently the workload of the executive operating in sector 3 is relatively high compared to other sectors within the Dutch airspace. An explanation one could give for the relative high workload is the fact that the diversity of the traffic passing through the sector is high, the traffic consists out of inbound and outbound traffic for EHAM, regional traffic from EHRD and EHEH and finally transit flights passing over the sector. In order to make such sectors more manageable for the executive a decision support tool for the planner for decision support in such sectors will be developed. Due to the higher fidelity of information available in the future through ADS-C data, new possibilities with regards to planning become possible. The tool that will be developed will make use of this ADS-C data in order to provide new insights to the planner, which allow for better planning that might reduce the complexity of the airspace. Due to this reduced complexity of the airspace, the workload of the executive will be reduced.

The Deep Turnaround (DT) integration project investigates how AI-driven video recognition of aircraft turnaround activities can be securely connected to LVNL’s technical infrastructure. Originally developed at Amsterdam Airport Schiphol, DT uses multi-camera monitoring and historical datasets to capture, interpret, and distribute real-time information on A-CDM milestones and turnaround events. By providing a verified stream of operational data, DT has the potential to improve sequencing, resource planning, and situational awareness across airport stakeholders. At present, however, DT functions largely in isolation, with limited sharing of milestone data between the Knowledge Development Center (KDC) partners. This research examines how interoperability can be achieved by addressing technological requirements, regulatory compliance frameworks, and organizational barriers. The ultimate goal is to enable collaborative decision-making and reduce fragmented situational awareness. In doing so, the study aims to unlock efficiency gains, support more sustainable operations, and contribute directly to SESAR objectives for a predictable, integrated European air traffic management network.

To regulate and mitigate noise impact of an airport on the surrounding communities, aircraft noise models are used to assess the impact. For these models, flights are modelled based on standard procedures of consecutive steps of speed and altitude changes and their corresponding delivered thrust. Under these procedures, however, lie a number of assumptions that could significantly alter the actual flown trajectory and thus noise pollution. Using real world data including data from the Aircraft Condition and Monitoring System (ACMS) and measurement data from the Noise Monitoring System (NOMOS), a comparison can be made between the estimated and real flight profiles.

The field of Air Traffic Management (ATM) is evolving to meet the growing complexities of air travel, yet traditional systems like Air Traffic Flow Management (ATFM) and Arrival Management (AMAN) still rely heavily on deterministic inputs. This reliance leads to inefficiencies, especially in long-haul operations such as transatlantic flights, where uncertainties in weather, demand, and capacity often disrupt planning. Despite recent advances in machine learning and delay prediction models, integrating uncertainty quantification into ATM systems remains underexplored, limiting their adaptability in dynamic environments. This research seeks to address these challenges by integrating uncertainty quantification into an Extended AMAN and LR-ATFM framework, with a focus on transatlantic operations. The goal is to develop a dynamic speed management system that adjusts flight speeds based on real-time uncertainty predictions. By enhancing predictability and optimizing sequencing, the approach aims to reduce fuel consumption, minimize delays, and improve overall efficiency. This is especially relevant as the aviation industry faces increasing pressures to manage growing air traffic sustainably and reduce carbon emissions.

Air traffic management is complex and requires tight coordination between procedures, controllers, and flight crews. Instrument approach procedures aim to ensure predictability and smooth transitions to landing, with stabilised approaches at their core—where aircraft follow a defined path at the correct speed and configuration. This reduces workload and supports efficient sequencing.

Despite these procedures, deviations still occur. These can be Non-Compliant Approaches (NCA), where procedural rules aren’t fully met, or Non-Stabilised Approaches (NSA), where trajectory or configuration can’t be maintained. NCAs often lead to NSAs, increasing workload and reducing predictability.
This study investigates whether the final approach routes to runways 18R and 18C at Schiphol allow aircraft to meet published requirements at the Final Approach Fix. Using historical trajectory data, it explores whether atypical approaches result from route design limitations or operational factors. The goal is to identify root causes and offer insights to improve safety and efficiency.

Despite regulatory efforts at harmonizing and enhancing ATM performance, ANSPs still utilize indicators based on extra distance and time flown, such as Horizontal Flight Efficiency (HFE) to periodically report on their performance. However, additional distance and time flown may not necessarily correlate with increased fuel consumption particularly if the flight operates under more favourable conditions for fuel burn, such as optimal wind conditions, speed, and altitude. In certain cases, there is a negative correlation between horizontal efficiency and total fuel efficiency. Nonetheless, fuel-based metrics are not enforced as their complexity remain a limiting factor in their implementation. Given these metrics offer a more accurate representation of a flight’s environmental efficiency, this study will focus on fuel-based performance indicators and will utilize an open-source aircraft performance model (OpenAP) to reconstruct historical and flight plan trajectories, generate reference optimal trajectories and calculate each flight’s fuel consumption. The discrepancy in the fuel consumption of this set of trajectories will allow the identification of strategic, tactical, horizontal and vertical efficiencies in LVNL’s airspace.

Established on RNP AR APCH (EoR) is a navigation technique built upon Required Navigation Performance Authorization Required approaches, which use self-monitoring capabilities to achieve a high navigation accuracy. This allows aircraft to be established on complex (curved) approach paths and be released from standard radar separation requirements, which brings benefits in terms of reduced level segments, more predictable ground tracks and reduced track miles. Since not all operators at Schiphol Airport are equipped for EoR, the air traffic controller will have to handle a mix of traffic. Evaluations from previous implementations of EoR highly recommend offering a support tool to the approach controller. This research focuses on designing and evaluating a Decision Support Tool (DST) to enable merging EoR traffic with vectored ILS traffic on final approach for a single runway. The design will follow principles from Ecological Interface Design to create an effective and accepted tool. A simulation will be used to evaluate the DST in terms of controller workload, traffic capacity and ability to robustly handle different traffic mixes.

Many TBO techniques for Trajectory Management for arrivals involve either speed management by ATC or time management by the aircraft. However, in high density operations, both speed management and time management exhibit too many uncertainties, making them incompatible with high-density arrival operations. In previous research, the benefits of an alternative method of managing trajectories in a speed managed environment, have been demonstrated. In this alternative method, geometric descents are employed. Using these fixed angle descents, many uncertainties are eliminated. However, since such descents are flown off-idle, a different balance between capacity and flight efficiency is created. On the other hand, opportunities exist to allow aircraft to fly idle descents, when higher uncertainties can be permitted due to specific operational circumstances. This study will research the uncertainties associated with idle descents and off-idle geometric descents within the CTA related to EHAM. A model demonstrating the dynamic application of both descent techniques in a 24H operation will be developed based on determined criteria, and compared to static applications of the descent techniques.