Classical approaches for modelling aircraft taxi-speed assume constant speed or use a turning rate function to approximate taxi-timings for taxiing aircraft. However, those approaches cannot predict spatio-temporal component of aircraft-taxi trajectory due to a lack of consideration of the complexity and stochasticity of airport-airside movements and interactions. This research adopts the Generative Adversarial Imitation Learning (GAIL) algorithm for aircraft taxi-speed modelling, while considering multiple operational factors including surrounding traffic on the ground and target take-off time. The proposed model can learn and reproduce the ground movement patterns in a real-world dataset under different circumstances. In addition, the characteristics of the taxi-speed model are also analyzed, especially focusing on handling conflict scenarios with surrounding traffic. Finally, the travel-time of the aircraft from starting to target positions are compared with baseline models and actual taxiing data. The proposed model outperforms all the baseline models with a significant margin. In terms of spatial completion (SC), it achieves up to 97.1% for arrivals and 88.3% for departures. The results also show significantly high performance for temporal completion. The model achieves a stable performance with low Root Mean Square Error (RMSE) (16.8 seconds for arrivals, 32.4 seconds for departures) and Mean Absolute Percentage Error (MAPE) (4.4% for arrivals and 7.6% for departures). Our model’s errors are 72% lower for arrivals and 48% lower for departures when compared to other baseline models.

Recent advancements have significantly improved the efficiency and effectiveness of deep learning methods for image-based remote sensing tasks. However, the requirement for large amounts of labeled data can limit the applicability of deep neural networks to existing remote sensing datasets. To overcome this challenge, few-shot learning has emerged as a valuable approach for enabling learning with limited data. While previous research has evaluated the effectiveness of few-shot learning methods on satellite-based datasets, little attention has been paid to exploring the applications of these methods to datasets obtained from Unmanned Aerial Vehicles (UAVs), which are increasingly used in remote sensing studies. In this review, we provide an up-to-date overview of both existing and newly proposed few-shot classification techniques, along with appropriate datasets that are used for both satellite-based and UAV-based data. We demonstrate few-shot learning can effectively handle the diverse perspectives in remote sensing data. As an example application, we evaluate state-of-the-art approaches on a UAV disaster scene dataset, yielding promising results. Furthermore, we highlight the significance of incorporating explainable AI (XAI) techniques into few-shot models. In remote sensing, where decisions based on model predictions can have significant consequences, such as in natural disaster response or environmental monitoring, the transparency provided by XAI is crucial. Techniques like attention maps and prototype analysis can help clarify the decision-making processes of these complex models, enhancing their reliability. We identify key challenges including developing flexible few-shot methods to handle diverse remote sensing data effectively. This review aims to equip researchers with an improved understanding of few-shot learning’s capabilities and limitations in remote sensing, while pointing out open issues to guide progress in efficient, reliable and interpretable data-efficient techniques.

Incorporating deep learning (DL) classification models into unmanned aerial vehicles (UAVs) can significantly augment search-and-rescue operations and disaster management efforts. In such critical situations, the UAV’s ability to promptly comprehend the crisis and optimally utilize its limited power and processing resources to narrow down search areas is crucial. Therefore, developing an efficient and lightweight method for scene classification is of utmost importance. However, current approaches tend to prioritize accuracy on benchmark datasets at the expense of computational efficiency. To address this shortcoming, we introduce the Wider ATTENTION EfficientNet (WATT-EffNet), a novel method that achieves higher accuracy with a more lightweight architecture compared to the baseline EfficientNet. The WATT-EffNet leverages width-wise incremental feature modules and attention mechanisms over width-wise features to ensure the network structure remains lightweight. We evaluate our method on a UAV-based aerial disaster image classification dataset and demonstrate that it outperforms the baseline by up to 15 times in terms of classification accuracy and 38.3% in terms of computing efficiency as measured by Floating Point Operations per second (FLOPs). Additionally, we conduct an ablation study to investigate the effect of varying the width of WATT-EffNet on accuracy and computational efficiency.

Air traffic is operated in an air traffic network (ATN) environment. It is pertinent to improve the robustness of ATNs as they are frequently exposed to manifold uncertainties which can break down their functioning components. Existing studies improve the robustness of an ATN by either rewiring its links or adding more ones. In this paper we discover the robustness paradox phenomenon in ATNs. Specifically, we claim to improve the robustness of an ATN by removing its links. In order to determine the links whose removal can improve an ATN's robustness, we develop a bi-objective optimization model with one objective maximizing the network's robustness and the other one minimizing the number of links to be removed. We further apply and modify a non-dominated sorting genetic algorithm (NSGA-II) to optimize the developed model. We then carry out experiments on nine real-world ATNs to validate the effectiveness of the proposed idea. We also compare the modified NSGA-II algorithm against NSGA-III, and MODPSO, which are famous and efficient multiobjective evolutionary algorithms. Experiments indicate that NSGA-II outperforms the compared algorithms and that robustness paradox phenomenon does exist in ATNs. This work provides a new perspective for aviation decision makers to better design and manage ATNs.

We provide a concept of operations and a corresponding implementation of a long-range air traffic flow management in the Asia-Pacific region. This management will provide an appropriate demand-capacity balancing considering both aircraft sequencing by local arrival management procedures and flow optimization to prevent over-demand in the approach area around the airport. Thus, coordination of long-range international flights demands collaboration between different flight information regions and local regulations. As Singapore Changi Airport is a central element of the Asia-Pacific flow management high share of long-haul air traffic, we use this airport to demonstrate our approach. To derive the operational conditions and actual traffic patterns at the airport, ADS-B messages and flight plan information are processed. The data are cleaned, analyzed, and filtered to provide information about arrival flows within given distances to the airport. We provide an efficacy analysis of the long-range air traffic flow management using two approaches. First, we applied a mixed-integer optimization of time shifts of normal distributed flight times. Here, the regulation of long-range flights by time shifts (e.g., achieved by speed advisories) shows a significant relief from periods of over-demand at the airport approach sector. Second, we implement a reference and a test case scenario in an agent-based simulation environment including the local arrival management procedures. Here, the number of holdings and the associated holding time could be reduced by at least 26%.