Probabilistic Flight Delay Predictions Using Machine Learning and Applications to the Flight-to-Gate Assignment Problem

Zoutendijk, Mike; Mitici, Mihaela

doi:10.3390/aerospace8060152

Cited by 30 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CRPS has been used to evaluate probabilistic predictions for applications such as flight delays (Zoutendijk & Mitici, 2021), sea level pressure and surface temperature (Gneiting, Raftery, Westveld III, & Goldman, 2005) and electricity prices (Nowotarski & Weron, 2018). However, to the best of our knowledge, this metric has not yet been used to evaluate probabilistic RUL prognostics.…”

Section: Novel Metrics To Evaluate Probabilistic Rul Prognosticsmentioning

confidence: 99%

Novel Metrics to Evaluate Probabilistic Remaining Useful Life Prognostics with Applications to Turbofan Engines

Pater

Mitici

2022

PHME_CONF

Self Cite

View full text Add to dashboard Cite

Well-established metrics such as the Root Mean Square Error or the Mean Absolute Error are not suitable to evaluate estimated distributions of the Remaining Useful Life (i.e., probabilistic prognostics). We therefore propose novel metrics to evaluate the quality of probabilistic Remaining Useful Life prognostics. We estimate the distribution of the Remaining Useful Life of turbofan engines using a Convolutional Neural Network with Monte Carlo dropout. The accuracy and sharpness of the obtained probabilistic prognostics are evaluated using the Continuous Ranked Probability Score (CRPS) and weighted CRPS. The reliability of the obtained probabilistic prognostics is evaluated using the α-Coverage and the Reliability Score. The results show that the estimated distributions of the Remaining Useful Life of turbofan engines are accurate, reliable and sharp when using a Convolutional Neural Network with Monte Carlo dropout. In general, the proposed metrics are suitable to evaluate the accuracy, sharpness and reliability of probabilistic Remaining Useful Life prognostics.

show abstract

Section: Novel Metrics To Evaluate Probabilistic Rul Prognosticsmentioning

confidence: 99%

Novel Metrics to Evaluate Probabilistic Remaining Useful Life Prognostics with Applications to Turbofan Engines

Pater

Mitici

2022

PHME_CONF

Self Cite

View full text Add to dashboard Cite

show abstract

“…Different from the CNN and RNN, BDNN owns the following characteristics: Firstly, its multi-layer structure characteristic together with more information processing units results in a strong learning and fitting ability for complex and nonlinear models under multidimensional space, and the process does not depend on the accurate mathematical model. Also, it allows input samples with larger dispersion [12], [13]. Secondly, BDNN learns one hidden layer feature representation each time through greedy learning.…”

Section: Introductionmentioning

confidence: 99%

A Capability Fitting and Data Reconstruction Model Based on Particle Swarm Optimization-Bidirectional Deep Neural Network for Search and Rescue System of Systems

Gao

Liu

Niu³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Search and rescue (SAR) is an important part of joint operations and a key support for combat effectiveness. Because of the complex composition of the SAR system of systems (SoS), sensitivity analysis method is usually used to carry out sensitivity analysis of SoS capability, so as to determine the main design indicators affecting SoS capability. Reliable sensitivity analysis results are often based on the analysis for sufficient data. However, the SAR SoS capability is affected by many factors and there are numerous design indicators. Even if a small number of design points are selected for each design indicator, tens of thousands of test schemes will be formed, and carrying out all simulation tests will bring huge workload and time cost. To solve this contradiction, this paper introduces a bidirectional deep neural network (BDNN), and takes advantage of its better self-learning and adaptive features and unique structure to train the existing test data, Through strong feature extraction ability of BDNN, the network model between the design indicator and capability indicator is formed, namely, the capability fitting and data reconstruction (CFDR) model, so that the implicit relationship between the two is fixed into the model. In the training process, the number of hidden layers and neurons in each hidden layer, and the amount of training data are explored according to the training effect, so as to obtain a better parameter combination. In order to avoid introducing large cumulative errors accumulated during BDNN pre-training into DNN, particle swarm optimization (PSO) was introduced to optimize weight parameters and avoid large training errors being transmitted to deep neural network (DNN). Meanwhile, three basic functions were used to verify the strong global optimization and convergence abilities of the BDNN after optimized by the PSO (PSO-BDNN). Finally, the new test scheme is applied to the CFDR model to obtain the SoS capability value. The reconstructed data obtained from the CFDR model based on BDNN and PSO-BDNN respectively were compared with the simulation test data.The results show that the reconstruction accuracy of the CFDR model based on the PSO-BDNN is greatly improved than that of the BDNN. And the feasibility of this model as a reconstruction data generation model and the effectiveness of this model as an analysis data extension method applied to the sensitivity analysis of insufficient data to obtain reliable analysis results are verified.INDEX TERMS Capability fitting and data reconstruction model, bidirectional deep neural network, particle swarm optimization, search and rescue, SoS capability sensitivity analysis.The associate editor coordinating the review of this manuscript and approving it for publication was Mitra Mirhassani .

show abstract

“…Earliness is a measure of finishing operations before due time, and tardiness is a measure of a delay in executing certain operations. Tardiness is considered the primary cause behind delays in production and delivery to all downstream customers, and earliness induces additional storage and handling costs (Metzger, Leitner, Ivanovi, et al, 2015) and (Zoutendijk, 2021). Disruption risk in transportation is often considered the extreme risk, which is more than 48-hour delays or more than 24 hours earliness, severely impacting the customers' operations and the freight forwarders.…”

Section: Introductionmentioning

confidence: 99%

A hybrid ensemble learning-based prediction model to minimise delay in air cargo transport using bagging and stacking

Sahoo

Pasayat

Bhowmick

et al. 2021

International Journal of Production Research

View full text Add to dashboard Cite

Manufacturing productivity is inextricably linked to air freight handling for the global delivery of finished and semi-finished goods. In this article, our focus is to capture the transport risk associated with air freight which is the difference between the actual and the planned time of arrival of a shipment. To mitigate the time-related uncertainties, it is essential to predict the delays with adequate precision. Initially data from a case study in the transportation and logistics sector were pre-processed and divided into categories based on the duration of the delays in various legs. Existing datasets are transformed into a series of features, followed by extracting important features using a decision tree-based algorithm. To predict the delay with maximum accuracy, we used an improved hybrid ensemble learning-based prediction model with bagging and stacking enabled by characteristics like time, flight schedule, and transport legs. We also calculated the dependency of accuracy on the point in time during business process execution is examined while predicting. Our results show all predictive methods consistently have a precision of at least 70 percent, provided a lead-time of half the duration of the process. Consistently, the proposed model provides strategic and sustainable insights to decision-makers for cargo handling.

show abstract

Probabilistic Flight Delay Predictions Using Machine Learning and Applications to the Flight-to-Gate Assignment Problem

Cited by 30 publications

References 35 publications

Novel Metrics to Evaluate Probabilistic Remaining Useful Life Prognostics with Applications to Turbofan Engines

Novel Metrics to Evaluate Probabilistic Remaining Useful Life Prognostics with Applications to Turbofan Engines

A Capability Fitting and Data Reconstruction Model Based on Particle Swarm Optimization-Bidirectional Deep Neural Network for Search and Rescue System of Systems

A hybrid ensemble learning-based prediction model to minimise delay in air cargo transport using bagging and stacking

Contact Info

Product

Resources

About