Prediction of Flight Delays at Beijing Capital International Airport Based on Ensemble Methods

Wang, Xu-Nuo; Wang, Zhan; Wan, Lili; Tian, Yong

doi:10.3390/app122010621

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A review of different approaches to flight delay prediction and how this problem is addressed is presented in [20]. They compare the prediction models used, such as operational research [21], machine learning [22], Bayesian network approach [23], probabilistic models, statistical analysis, a super statistical approach [24] and ensemble methods and select representative algorithms [25]. A novel predictive model applying graphs to sequence learning architecture is studied in [26].…”

Section: State Of the Artmentioning

confidence: 99%

Estimating the Volatility of Flights and Risk of Saturation of Airspaces in the European Core Area: A Methodological Proposal

Galarraga,

Abadie,

Standfuss

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Despite having some fluctuations and the impact of the COVID-19 crisis, the demand for flights had a general growing trend for the past years. As the airspace is limited, efforts to better manage the total number of flights are noteworthy. In addition, volatility (i.e., unpredicted changes) in the number of flights has been observed to be increasing. Efforts to improve flight forecasting are thus necessary to improve air traffic efficiency and reduce costs. In this study, volatility in the number of flights is estimated based on past trends, and the outcomes are used to project future levels. This enables risk situations such as having to manage unexpectedly high numbers of flights to be predicted. The methodological approach analyses the Functional Airspace Block of Central Europe (FABEC). Based on the number of flights for 2015–2019, the following are calculated: historic mean, variance, volatility, 95th percentile, flights per hour and flights per day of the week in different time zones in six countries. Due to the nature of air traffic and the overdispersion observed, this study uses counting data models such as negative binomial regressions. This makes it possible to calculate risk measures including expected shortfall (ES) and value at risk (VaR), showing for each hour that the number of flights can exceed planned levels by a certain number. The study finds that in Germany and Belgium at 13:00 h there is a 5% worst-case possibility of having averages of 683 and 246 flights, respectively. The method proposed is useful for planning under uncertainties. It is conducive to efficient airspace management, so risk indicators help Air Navigation Service Providers (ANSPs) to plan for low-probability situations in which there may be large numbers of flights.

show abstract

Section: State Of the Artmentioning

confidence: 99%

Estimating the Volatility of Flights and Risk of Saturation of Airspaces in the European Core Area: A Methodological Proposal

Galarraga,

Abadie,

Standfuss

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

Air Temperature for Sustainable Airport Infrastructure and Environment

Rahutomo,

Hidayat,

Isnan

et al. 2024

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Understanding the patterns of air temperature in the local area is essential to mitigate potential destructive impacts and develop strategies for climate-resilient infrastructure. The pilot study focuses on the analysis of air temperature at Soekarno Hatta International Airport (SHIA), Indonesia. The study utilizes air temperature data collected over a 30-month period, grouped into six-month intervals. To assess the significance of means and distributions of air temperature points, independent t-tests are employed. Data visualizations are provided to clarify the air temperature patterns during the observation period. The findings reveal that SHIA has experienced warm and stable air temperatures over the last 30 months. However, to comprehensively study the various impacts from climatology and meteorology perspectives on airport infrastructure and operations, it is essential for future research to address limitations related to access to certain variables and consider employing multivariable forecasting techniques. By addressing these aspects, further investigations are able to provide deeper insights into the implications of air temperature on airport operations and contribute to formulate a strategy for developing a climate-resilient airport infrastructure.

show abstract

A novel intelligent approach for flight delay prediction

Mamdouh,

Ezzat,

A.Hefny

2023

J Big Data

View full text Add to dashboard Cite

Flight delay prediction is one of the most significant components of intelligent aviation systems that may spread throughout the whole aviation network and cause multi-billion-dollar losses faced by airlines and airports, it is quickly becoming an important research issue to improve airport and airline performance. Thus this paper proposed an effective algorithm called Flight Delay Path Previous-based Machine Learning (FDPP-ML) capable of improved prediction of individual flight delay minutes using regression models to an up level of accuracy. As aviation system connectivity presents complex spatial–temporal correlations, machine learning approaches have addressed flight delay prediction by using complex flight or weather features, or private information for specific airports and airlines that are hard to obtain, In contrast, the proposed FDPP-ML improved prediction based only on basic flight schedule features even with wide flight networks. The FDPP-ML consists of a novel algorithm with a supervised learning model, which works on reshaping datasets and creates two new features the main feature is previous flight delay (PFD) for flight paths, there is a strong relationship between departure and arrival delay, and vice versa for the same flight path, which increases the strength of the training model based on historical data. For target future flights, the algorithm works on inheriting the predicted flight delay to the next flight on the same flight path and repeats this process to end the prediction forecast horizon. The proving of approach effectiveness by using a wide network of US flight arrival and departure flights containing 366 airports and 10 airlines with various metrics accuracies of regression, and explanatory the impacts on various forecast horizons 2, 6, and 12 h for future flights. The FDPP-ML outperforms traditional training models by using machine and deep learning models and improving model accuracy in 10 models with an average of up to 39% in MAE, and 42% in MSE in a forecast horizon of 2 h. Finally, providing airport and airline analysis further reveals that can improve prediction than traditional training models for the individual busiest airports "Core 30" with an average of 35% in MAE and 42% in MSE respectively, and for the busiest 10 airlines with an average of 36% in MAE and 47% in MSE respectively. The findings of this study may offer informative recommendations to airport regulators and aviation authorities for developing successful air traffic control systems for enhanced flight delay prediction to flight operational effectiveness, not only over the US flight network but with wide worldwide flight networks if a dataset of flights existed.

show abstract

Prediction of Flight Delays at Beijing Capital International Airport Based on Ensemble Methods

Cited by 4 publications

References 27 publications

Estimating the Volatility of Flights and Risk of Saturation of Airspaces in the European Core Area: A Methodological Proposal

Estimating the Volatility of Flights and Risk of Saturation of Airspaces in the European Core Area: A Methodological Proposal

Air Temperature for Sustainable Airport Infrastructure and Environment

A novel intelligent approach for flight delay prediction

Contact Info

Product

Resources

About