Indoor positioning in aircraft cabins presents fundamental challenges arising from severe multipath propagation, non-line-of-sight conditions, and metallic fuselage geometry that degrade radio-based positioning methods. This study validates a residual neural network (ResNet) based deep learning approach for aircraft cabin localization through real-world measurements in an A320 cabin mockup. The methodology employs dual-technology ranging measurements from Ultra-Wideband and Bluetooth Low Energy, transforming range observations into spatial likelihood representations processed by a ResNet. Experimental validation encompasses 19 distributed measurement positions, evaluated against three baseline methods: iterative least squares, robust least squares with Huber loss, and Bayesian grid filtering. ResNet achieved an overall median positioning error of 0.177 m, achieving lower positioning errors than all three baseline methods. Results confirm that likelihood-based neural network positioning is viable for operational aircraft cabin deployment while identifying performance dependencies on anchor visibility, measurement height, and propagation conditions. The original data is openly available.

Dynamic, demand-focused airspace management must reduce sector-specific traffic complexity to support air traffic controller operations. The flow-centric concept contributes through the homogenization of aircraft trajectories, and we extend it by grouping aircraft as elements of a granular flow and introducing dynamic handover times between adjacent sectors. The idea of granular flow reflects the view of aircraft as locally dense particles within a collective stream, where interactions are not purely individual but are shaped by density, coupling strength, and available capacity. This perspective captures phenomena such as local congestion in sectors, delay waves, and the propagation of capacity bottlenecks.We create granular cells that group flights with similar characteristics. Within each cell, aircraft follow comparable patterns and therefore receive similar instructions from controllers, thereby reducing their taskload. As in granular flow, cells may differ in size, and controllers manage several cells, down to those containing only a single aircraft. Dynamic handover times, derived from airspace boundary parameterization and the direct optimization of handover locations, enable workload-based early or late transfers between adjacent sectors while preserving the legally defined responsibilities of controllers. To assess the impact of modeling air traffic as granular flows, an operational concept is developed and applied to en-route traffic within Singapore’s upper airspace at peak times. Traffic complexity is assessed using 25 parameters encompassing aircraft-, conflict-, and airspace-related aspects.Granular cells substantially reduce intra-sector complexity, with reductions averaging 17% and reaching up to 50%, while also propagating moderate benefits to adjacent sectors. Dynamic handover times decrease inter-sector complexity by 2% on average, with maximum reductions of 6%. When combined with granular cells, both concepts consistently reduce complexity across all evaluated cases, with an average reduction of 3% and a maximum reduction of 7%. Although the effects of both concepts are not strictly additive, they can overlap.

Regional Air Mobility (RAM) is an emerging passenger transport concept that extends Urban Air Mobility (UAM) beyond metropolitan areas by using electric Vertical Take-Off and Landing (eVTOL) aircraft to connect urban, peri-urban, and regional locations. Since the deployment of RAM requires long-term infrastructure decisions under uncertain demand and operational conditions, strategic network design is a central planning problem. This paper develops a robust hybrid hub-and-spoke and point-to-point network design model for RAM. The proposed formulation is based on a single-allocation p-hub location problem with range-constrained direct links. The model is applied to a case study of Bavaria, Germany, using 86 candidate vertiplaces across 53 cities selected from existing aviation and mobility infrastructure. Passenger demand is estimated from census and mobility data using mode-specific switching rates, and five demand levels are evaluated: low, medium-low, medium, medium-high, and high. For each demand level, nine operational scenarios are generated by combining three point-to-point connectivity grades and three eVTOL flight ranges. A scenario-based robust optimization model is then used to identify network designs that remain effective across uncertain operating conditions. In the revised scenario structure, probabilities are conditioned on the demand level, and a probability sensitivity analysis is performed for the nominal medium-demand case. The results show that low-demand networks are mainly hub-oriented, while higher demand levels increasingly support direct point-to-point connections. The price of robustness remains between 2.40% and 3.73% across all demand levels, indicating that robust network designs can provide protection against scenario uncertainty with a moderate nominal cost increase. The findings demonstrate that robust hybrid network design can support strategic RAM infrastructure planning under uncertain demand, range, and connectivity assumptions.

Air traffic complexity is a key driver of controller workload and fundamentally constrains air traffic growth. While air traffic complexity metrics provide quantitative indicators of workload, they are typically calibrated for specific sectors or traffic scenarios, limiting their generalizability. This underscores the need for flexible, context-sensitive support for situation assessment. Accordingly, this study investigates whether GenLLMs can assess the complexity of air traffic situations. A survey among air traffic controllers is conducted to establish a human ground truth. These ratings serve as a benchmark for a systematic evaluation of several GenLLMs. The models are assessed using progressively structured prompting strategies, ranging from zero-shot prompting to multi-role reasoning and in-prompt learning. The results show that several models achieve an average deviation of less than one rating level from the controller benchmark. Assessment performance is strongly model-dependent, with larger models exhibiting closer agreement with human judgments. The effect of prompting strategies is not universal and is primarily observed for suitable models in the present application. Overall, the findings demonstrate the feasibility of GenLLM–based air traffic complexity assessment and highlight its potential for situation assessment support and future co-controller concepts.

The recent advancements in Artificial Intelligence (AI) have paved the way for Human-AI Hybrid (HAH) systems, which integrate human and AI capabilities to augment human ingenuity rather than replace it. However, the application of HAH in Safety-Critical Systems (SCS), such as Air Traffic Management (ATM), remains limited due to the high stakes involved and the challenges presented by AI's unpredictable behavior and limitations in complex reasoning tasks. This paper provides an extensive review of the emerging domain of HAH in ATM, defining HAH and examining the fundamental pillars of effective HAH in ATM, including collaboration, adaptation, and trust. By synthesizing interdisciplinary research, this review explores the interaction between humans and AI, identifies obstacles, and recommends strategies for developing effective HAH systems in ATM. Furthermore, by examining real-world ATM applications, this study bridges the gap between theoretical recommendations and practical implementation, offering valuable insights for future efforts in similar contexts.

Accurate and high precision of the indoor positioning is as important as ensuring reliable navigation in outdoor environments. Using the state-of-the-art deep learning models provides better reliability and accuracy to navigate and monitor the accurate positions in the aircraft cabin environment. We utilize the simulated aircraft cabin environment measurements and propose a residual neural network (ResNet) model to predict the accurate positions inside the cabin. The measurements include the ranges and angles between a tag and the anchors points which are then mapped onto a grid as range and angle residuals. These residual maps are then transformed into the likelihood grid maps where each cell of the grid shows the likelihood of being a true location. These grid maps along with the true positions are then passed as inputs to train the ResNet model. Since any deep learning model involve numerous parameter settings, hyperparameter optimization is performed to get the optimal parameters for training the model effectively with the highest accuracy. Once we get the best hyperparameters settings of the model, it is then trained to predict the positions which provides a centimeter-level accuracy of the localization.

Our map represents the first successful large-area fusion of OpenStreetMap and Copernicus data at a spatial resolution of 10 m or finer and can be applied globally. We addressed varying label noise and feature space quality, utilizing artificial intelligence and advanced computing. Our method relies solely on openly available data streams and methods, eliminating training data acquisition or the need for additional expert knowledge for such purpose. We extracted land use labels from OpenStreetMap and remote sensing data to create a contiguous land use map of the European Union as of March 2020. OpenStreetMap tags were translated into land use labels, directly mapping 61.8% of the Union’s area. These labels served as training data for a classification model, predicting land use in remaining areas. Country-specific deep learning convolutional neural networks and Sentinel-2 feature space composites of 2020 at 10 m resolution were employed. The overall map accuracy is 89%, with class-specific accuracies ranging from 77% to 99%. The data set is available for download from https://doi.org/10.11588/data/IUTCDN and visualization at https://osmlanduse.org .

This study introduces a novel approach to optimizing air traffic complexity within moving sectors, a concept designed for flow-centric air traffic management. Moving sectors dynamically allocate controller workload by grouping aircraft with similar trajectories and interactions. A trajectory adjustment method is proposed, incorporating Grey Wolf Optimization, to reduce traffic complexity through minor lateral path modifications. This approach maintains operational constraints, such as handover times, while ensuring minimal disruption to aircraft trajectories. Two case studies demonstrate significant improvements, with reductions in average traffic complexity of up to 27% and peak complexity loads of up to 30%. These findings highlight the potential of flow-centric procedures to enhance airspace capacity, ensuring safety and efficiency in future air traffic management systems.

This paper presents a two-stage optimization method improving drone route network efficiency above cities, with a specific focus on balancing delivery performance with noise exposure. The improvement is assessed by three indicators: the mean delivery distance, which reflects travel efficiency and energy use; the number of trajectory intersections, which relates to airspace deconfliction complexity; and the estimated number of highly annoyed individuals due to noise exposure. A twostage approach tackles the trade-off between the three indicators. This approach is based on a Probabilistic Roadmap (PRM) combined with a Simulated Annealing (SA) to improve graph point locations. The combination of the two algorithms iteratively improves the objective function. Our approach is validated through a real-world case study in Paris, France, focusing on medical sample delivery between hospitals and clinics.

Air transportation is frequently disrupted by factors such as weather and air traffic control, making it difficult for flights to strictly adhere to schedules, leading to frequent early arrivals or delays. These disruptions pose challenges to airport operations management, particularly in gate assignments, where potential conflicts and adjustments are often required. Unlike traditional methods that focus on enhancing robustness to reduce conflicts, this study adopts a Predict-then-Optimize (PO) framework, using predicted flight arrival times for gate assignments to avoid the need for robustness-related objectives. In the prediction phase, a CNN-LSTM-Attention deep learning model is developed to predict flight arrival times based on the historical data of a single airport, enhancing data availability and model practicality. In the optimization phase, a bi-objective gate assignment model is constructed, using predicted arrival times instead of scheduled times as input. An epsilon-constrained branch-and-price algorithm is developed to obtain non-dominated Pareto optimal solutions. Analysis using actual operational data from Beijing Capital International Airport shows that the prediction model achieves an accuracy of 93.27% for early arrivals and 83.6% for on-time flights. The epsilon-constrained branch-and-price algorithm outperforms heuristic algorithms in both the quantity and quality of Pareto solutions. Notably, the gate assignment strategy based on predicted arrival times significantly reduces potential conflicts, with a maximum reduction of 25.33% compared to the schedule-based strategy. This study demonstrates that the proposed gate assignment method, based on flight arrival time prediction, effectively mitigates the impact of arrival time uncertainty on gate assignments, providing a new approach to reducing potential conflicts without relying on robustness.

Urban air mobility is an innovative mode of transportation in which electric vertical takeoff and landing (eVTOL) vehicles operate between nodes called vertiports. We outline a self-organized vertiport arrival system based on deep reinforcement learning. The airspace around the vertiport is assumed to be circular, and the vehicles can freely operate inside. Each aircraft is considered an individual agent and follows a shared policy, resulting in decentralized actions that are based on local information. We investigate the development of the reinforcement learning policy during training and illustrate how the algorithm moves from suboptimal local holding patterns to a safe and efficient final policy. The latter is validated in simulation-based scenarios, including robustness analyses against sensor noise and a changing distribution of inbound traffic. Lastly, we deploy the final policy on small-scale unmanned aerial vehicles to showcase its real-world usability.

We systematically study cornerstones that must be solved to define an air traffic control benchmarking system based on a Data Envelopment Analysis. Primarily, we examine the appropriate decision-making units, what to consider and what to avoid when choosing inputs and outputs in the case that several countries are included, and how we can identify and deal with outliers, like the Maastricht Service Provider. We argue that Air Navigation Service Providers would be a good choice of decision units within the European context. Based on that, we discuss candidates for DEA inputs and outputs and emphasize that monetary values should be excluded. We, further suggest to use super-efficiency DEA for eliminating outliers. In this context, we compare different DEA approaches and find that standard DEA is performing well.

Moving sectors are a crucial element of efficient flow-centric air traffic flow management, enabling the efficient integration of prioritized flights and providing dynamic flow structures. This study establishes a foundation for determining the complexity of air traffic within moving sectors. Present air traffic flow management depends on sector-based approaches, with air traffic controller workload being a primary limitation on airspace capacity. Air traffic complexity, airspace design, and operational concepts affect controller workload. Introducing moving sectors for prioritized traffic flows challenges existing complexity assessment metrics. A comprehensive analysis of available metrics revealed that only a limited number could be reproduced and adapted to assess the complexity of moving sectors. Twenty-five significant factors were identified and aggregated into five complexity metrics. Six moving sector configurations were derived using air traffic scenarios in the Singapore flight information region. The absence of an operational concept for the prioritized traffic flows prevented human-in-the-loop experiments from assessing controller workload and taskload. However, fifteen air traffic controllers provided expert evaluations of the air traffic scenarios, which were subsequently compared with the computed complexity metrics. Mitigation strategies, such as adjusted arrival times and adapted traffic flows, are implemented to align the traffic within moving sectors and reduce air the traffic within moving sectors complexity. The findings reveal variability in complexity metrics and controller assessments, demonstrating a modest linear correlation (R $2 =0.18$ ). The five introduced metrics capture certain aspects of complexity, which will be validated in upcoming validation experiments applying the operational concept of moving sectors.

With regard to the demanding aircraft cabin environment, this paper delves into the rising use of location-aware radio communication systems to streamline operational processes. We propose a hybrid deterministic and stochastic simulation approach, incorporating model-based ray-tracing and empirical residual simulation. The methodology presented allows for the evaluation of localization methods based on geometric relations, serving as both a data generation and validation tool. We elaborate how different radio properties and propagation phenomena influence these geometric relations and the localization process. This paper includes a publicly available dataset derived from the simulation approach, facilitating transparency and further analysis in the field of aircraft cabin radio localization systems.

Free route airspace allows airspace users to freely plan a route in en-route airspaces within certain restrictions. It is anticipated to offer the benefit of fuel saving and operational flexibility. Regarding its efficient implementation into the ASEAN airspace, the key challenge would be reducing hotspots with clusters of potential conflicts. This paper designed a time-varying queuing network model, which contributed to untangle trajectory complexity in the most congested hotspot area. A series of fast-time simulation experiments were conducted to identify hotspots in en-route airspace in Singapore FIR. The application of departure time control using time-varying queuing networks successfully reduced up to 45% of potential conflicts. This was achieved within an average delay of 30 min by controlling time of less than 60% of candidate flights. The original contribution of this paper is to develop a novel modeling and simulation framework for composing ideal air traffic patterns. Lastly, we discussed the extension of this study toward a generalized application of the proposed approach in future air traffic management.

The potential of citizens as a source of geographical information has been recognized for many years. Such activity has grown recently due to the proliferation of inexpensive location aware devices and an ability to share data over the internet. Recently, a series of major projects, often cast as citizen observatories, have helped explore and develop this potential for a wide range of applications. Here, some of the experiences and learnings gained from part of one such project, which aimed to further the role of citizen science within Earth observation and help address environmental challenges, LandSense, are shared. The key focus is on quality assurance of citizen generated data on land use and land cover especially to support analyses of remotely sensed data and products. Particular focus is directed to quality assurance checks on photographic image quality, privacy, polygon overlap, positional accuracy and offset, contributor agreement, and categorical accuracy. The discussion aims to provide good practice advice to aid future studies and help fulfil the full potential of citizens as a source of volunteered geographical information (VGI).

Spatially explicit information on carbon fluxes related to land use and land cover change (LULCC) is of value for the implementation of local climate change mitigation strategies. However, estimates of these carbon fluxes are often aggregated to larger areas. We estimated committed gross carbon fluxes related to LULCC in Baden-Württemberg, Germany, using different emission factors. In doing so, we compared four different data sources regarding their suitability for estimating the fluxes: (a) a land cover dataset derived from OpenStreetMap (OSMlanduse); (b) OSMlanduse with removal of sliver polygons (OSMlanduse cleaned), (c) OSMlanduse enhanced with a remote sensing time series analysis (OSMlanduse+); (d) the LULCC product of Landschaftsveränderungsdienst (LaVerDi) from the German Federal Agency of Cartography and Geodesy. We produced a high range of carbon flux estimates, mostly caused by differences in the area of the LULCC detected by the different change methods. Except for the OSMlanduse change method, all LULCC methods achieved results that are comparable to other gross emission estimates. The carbon flux estimates of the most plausible change methods, OSMlanduse cleaned and OSMlanduse+, were 291,710 Mg C yr -1 and 93,591 Mg C yr -1 , respectively. Uncertainties were mainly caused by incomplete spatial coverage of OSMlanduse, false positive LULCC due to changes and corrections made in OpenStreetMap during the study period, and a high number of sliver polygons in the OSMlanduse changes. Overall, the results showed that OSM can be successfully used to estimate LULCC carbon fluxes if data preprocessing is performed with the suggested methods.

Industrial contaminants accumulated in Arctic permafrost regions have been largely neglected in existing climate impact analyses. Here we identify about 4500 industrial sites where potentially hazardous substances are actively handled or stored in the permafrost-dominated regions of the Arctic. Furthermore, we estimate that between 13,000 and 20,000 contaminated sites are related to these industrial sites. Ongoing climate warming will increase the risk of contamination and mobilization of toxic substances since about 1100 industrial sites and 3500 to 5200 contaminated sites located in regions of stable permafrost will start to thaw before the end of this century. This poses a serious environmental threat, which is exacerbated by climate change in the near future. To avoid future environmental hazards, reliable long-term planning strategies for industrial and contaminated sites are needed that take into account the impacts of cimate change.