arXiv subjects

Junzi Sun

Publications and source records attributed to Junzi Sun.

6 recordsLinked to original sources

arXiv2025

Aircraft Fuel Flow Modelling with Ageing Effects: From Parametric Corrections to Neural Networks

Accurate modelling of aircraft fuel-flow is crucial for both operational planning and environmental impact assessment, yet standard parametric models often neglect performance deterioration that occurs as aircraft age. This paper investigates multiple approaches to integrate engine ageing effects into fuel-flow prediction for the Airbus A320-214, using a comprehensive dataset of approximately nineteen thousand Quick Access Recorder flights from nine distinct airframes with varying years in service. We systematically evaluate classical physics-based models, empirical correction coefficients, and data-driven neural network architectures that incorporate age either as an input feature or as an explicit multiplicative bias. Results demonstrate that while baseline models consistently underestimate fuel consumption for older aircraft, the use of age-dependent correction factors and neural models substantially reduces bias and improves prediction accuracy. Nevertheless, limitations arise from the small number of airframes and the lack of detailed maintenance event records, which constrain the representativeness and generalization of age-based corrections. This study emphasizes the importance of accounting for the effects of ageing in parametric and machine learning frameworks to improve the reliability of operational and environmental assessments. The study also highlights the need for more diverse datasets that can capture the complexity of real-world engine deterioration.

cs.LG↗

arXiv2025

OpenSky Report 2025: Improving Crowdsourced Flight Trajectories with ADS-C Data

The OpenSky Network has been collecting and providing crowdsourced air traffic surveillance data since 2013. The network has primarily focused on Automatic Dependent Surveillance--Broadcast (ADS-B) data, which provides high-frequency position updates over terrestrial areas. However, the ADS-B signals are limited over oceans and remote regions, where ground-based receivers are scarce. To address these coverage gaps, the OpenSky Network has begun incorporating data from the Automatic Dependent Surveillance--Contract (ADS-C) system, which uses satellite communication to track aircraft positions over oceanic regions and remote areas. In this paper, we analyze a dataset of over 720,000 ADS-C messages collected in 2024 from around 2,600 unique aircraft via the Alphasat satellite, covering Europe, Africa, and parts of the Atlantic Ocean. We present our approach to combining ADS-B and ADS-C data to construct detailed long-haul flight paths, particularly for transatlantic and African routes. Our findings demonstrate that this integration significantly improves trajectory reconstruction accuracy, allowing for better fuel consumption and emissions estimates. We illustrate how combined data captures flight patterns across previously underrepresented regions across Africa. Despite coverage limitations, this work marks an important advancement in providing open access to global flight trajectory data, enabling new research opportunities in air traffic management, environmental impact assessment, and aviation safety.

cs.SI↗

arXiv2025

Contrail, or not contrail, that is the question: the "feasibility" of climate-optimal routing

The environmental impact of aviation has been a focus of significant research for several decades. While there is a broad consensus among stakeholders on reducing carbon emissions, leading to efforts to improve route efficiency in air traffic management, the impact of non-carbon emissions like contrails has sparked a different debate. Some organizations have already moved to pre-operational trials for contrail avoidance through flight re-routing, with recent industry projects fast-tracking these operational strategies. This paper addresses the practical challenges of implementing contrail-aware routing. Building on our previous research, which enables the generation of wind-optimal 4D trajectories using grid-like cost functions, we utilize the TOP tool and the OpenAP aircraft performance model to analyze the trade-offs between fuel consumption and contrail avoidance. We also examine the impact of weather forecast uncertainty on contrail mitigation, the effects on airspace capacity and network operations, and the implications for aviation regulatory frameworks. To investigate these challenges, we reconstructed a dataset from OpenSky data, encompassing all flight trajectories over Europe on a day with significant contrail potential. Our data-driven analysis highlights the potential difficulties in implementing contrail-optimal routing in practice, particularly concerning uncertainties in weather forecasts, impacts on airspace capacity, and questions of responsibility for optimal routing. Overall, we argue that contrail-optimal routing should be approached with caution, as its implementation may not be as straightforward as some stakeholders suggest.

physics.soc-ph↗

arXiv2024

On the Generalization Properties of Deep Learning for Aircraft Fuel Flow Estimation Models

Accurately estimating aircraft fuel flow is essential for evaluating new procedures, designing next-generation aircraft, and monitoring the environmental impact of current aviation practices. This paper investigates the generalization capabilities of deep learning models in predicting fuel consumption, focusing particularly on their performance for aircraft types absent from the training data. We propose a novel methodology that integrates neural network architectures with domain generalization techniques to enhance robustness and reliability across a wide range of aircraft. A comprehensive dataset containing 101 different aircraft types, separated into training and generalization sets, with each aircraft type set containing 1,000 flights. We employed the base of aircraft data (BADA) model for fuel flow estimates, introduced a pseudo-distance metric to assess aircraft type similarity, and explored various sampling strategies to optimize model performance in data-sparse regions. Our results reveal that for previously unseen aircraft types, the introduction of noise into aircraft and engine parameters improved model generalization. The model is able to generalize with acceptable mean absolute percentage error between 2\% and 10\% for aircraft close to existing aircraft, while performance is below 1\% error for known aircraft in the training set. This study highlights the potential of combining domain-specific insights with advanced machine learning techniques to develop scalable, accurate, and generalizable fuel flow estimation models.

cs.LG↗

arXiv2024

Automatic Control With Human-Like Reasoning: Exploring Language Model Embodied Air Traffic Agents

Recent developments in language models have created new opportunities in air traffic control studies. The current focus is primarily on text and language-based use cases. However, these language models may offer a higher potential impact in the air traffic control domain, thanks to their ability to interact with air traffic environments in an embodied agent form. They also provide a language-like reasoning capability to explain their decisions, which has been a significant roadblock for the implementation of automatic air traffic control. This paper investigates the application of a language model-based agent with function-calling and learning capabilities to resolve air traffic conflicts without human intervention. The main components of this research are foundational large language models, tools that allow the agent to interact with the simulator, and a new concept, the experience library. An innovative part of this research, the experience library, is a vector database that stores synthesized knowledge that agents have learned from interactions with the simulations and language models. To evaluate the performance of our language model-based agent, both open-source and closed-source models were tested. The results of our study reveal significant differences in performance across various configurations of the language model-based agents. The best-performing configuration was able to solve almost all 120 but one imminent conflict scenarios, including up to four aircraft at the same time. Most importantly, the agents are able to provide human-level text explanations on traffic situations and conflict resolution strategies.

cs.AI↗

arXiv2023

Flight Contrail Segmentation via Augmented Transfer Learning with Novel SR Loss Function in Hough Space

Air transport poses significant environmental challenges, particularly regarding the role of flight contrails in climate change due to their potential global warming impact. Traditional computer vision techniques struggle under varying remote sensing image conditions, and conventional machine learning approaches using convolutional neural networks are limited by the scarcity of hand-labeled contrail datasets. To address these issues, we employ few-shot transfer learning to introduce an innovative approach for accurate contrail segmentation with minimal labeled data. Our methodology leverages backbone segmentation models pre-trained on extensive image datasets and fine-tuned using an augmented contrail-specific dataset. We also introduce a novel loss function, termed SR Loss, which enhances contrail line detection by transforming the image space into Hough space. This transformation results in a significant performance improvement over generic image segmentation loss functions. Our approach offers a robust solution to the challenges posed by limited labeled data and significantly advances the state of contrail detection models.

cs.CV↗