Delay Prediction Research Articles

Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction

Accurate and interpretable delay predictions are vital for decision-making in the aviation industry. However, effectively incorporating spatiotemporal dependencies and external factors related to delay propagation remains a challenge. To address this challenge, we propose the SpatioTemporal Propagation Network (STPN), a novel space-time separable graph convolutional network that models delay propagation by considering both spatial and temporal factors. STPN uses a multi-graph convolution model that considers both geographic proximity and airline schedules from a spatial perspective, while employing a multi-head self-attention mechanism that can be learned end-to-end and explicitly accounts for various types of temporal dependencies in delay time series from a temporal perspective. Experiments on two real-world delay datasets show that STPN outperforms state-of-the-art methods for multi-step ahead arrival and departure delay prediction in large-scale airport networks. Additionally, the counterfactuals generated by STPN provide evidence of its ability to learn explainable delay propagation patterns. Comprehensive experiments also demonstrate that STPN sets a robust benchmark for general spatiotemporal forecasting. The code for STPN is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Kaimaoge/STPN</uri> .

XGBoost in Public Transportation for Multi-Attribute Data: Delay Prediction in Railway Systems in Real-Time

XGBoost in Public Transportation for Multi-Attribute Data: Delay Prediction in Railway Systems in Real-Time

Delay Prediction for Managing Multiclass Service Systems: An Investigation of Queueing Theory and Machine Learning Approaches

Delay Prediction for Managing Multiclass Service Systems: An Investigation of Queueing Theory and Machine Learning Approaches

Comparative study of ensemble machine learning techniques for airline delay prediction

Comparative study of ensemble machine learning techniques for airline delay prediction

Ground Handling Process Optimization Model Linked to Flight Delay Prediction Results

Ground Handling Process Optimization Model Linked to Flight Delay Prediction Results

Hybrid Approach to Train Delay Prediction: An Integration of Analytical Model and Deep Learning Techniques

Hybrid Approach to Train Delay Prediction: An Integration of Analytical Model and Deep Learning Techniques

How Complex Systems Sometimes Follow Murphy’s Law: Train Delay Prediction at a Station Using Delays at Previous Stops as the Features

Prediction or estimation of the delay of a train is essential to analyze customer behavior. In case of longer delays, there is a high probability that the customer will abort their travel or change the mode/time of travel. The delay propagation from previous stations to the next station creates a chain of these types of customer reactions. Thus, using delays at the previous station to predict the next station’s delay is a good approach to align with customer behavior. The present research attempts to predict the delays at a station using the delays at previous stations. The previous delays at stations are generated by creating lags in the original delays and creating them as one of the prediction features. The present research uses the delay data acquired from Bane NOR from 1 January 2021 to 28 February 2023. This data contains the scheduled and actual departure and arrival times of different trains between Oslo and Trondheim (up and down the line) in the specified period. The machine learning models based on neural networks were used on the data in the present research. Different prediction algorithms, i.e., recurrent neural network (RNN), gated recurrent unit (GRU), and long short-term memory (LSTM), were used. The prediction results are compared to look at the insights of the train delays in the given period. In conclusion, this study highlights how extreme feature engineering can negatively affect the output of a model.

FLIGHT DELAY PREDICTION BASED ON AVIATION BIG DATA AND MACHINE LEARNING

Accurate flight delay prediction is fundamental to establish the more efficient airline business. Recent studies have been focused on applying machine learning methods to predict the flight delay. Most of the previous prediction methods are conducted in a single route or airport. This paper explores a broader scope of factors which may potentially influence the flight delay, and compares several machine learning-based models in designed generalized flight delay prediction tasks. To build a dataset for the proposed scheme, automatic dependent surveillance broadcast (ADS-B) messages are received, pre-processed, and integrated with other information such as weather condition, flight schedule, and airport information. The designed prediction tasks contain different classification tasks and a regression task. Experimental results show that long short-term memory (LSTM) is capable of handling the obtained aviation sequence data, but over fitting problem occurs in our limited dataset. Compared with the previous schemes, the proposed random forest-based model can obtain higher prediction accuracy (90.2% for the binary classification) and can overcome the over fitting problem. KEYWORDS: Automatic Dependent Surveillance-Broadcast (ADS-B), Air Traffic Flow Management (ATFM) , Random Forest (RF), K-nearest Neighbors (K-NN)

A novel intelligent approach for flight delay prediction

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.

Intelligent algorithms applied to the prediction of air freight transportation delays

PurposeThe objective of this paper is to evaluate whether the data from consignors, logistics service providers (LSPs) and consignees contribute to the prediction of air transport shipment delays in a machine learning application.Design/methodology/approachThe research database contained 2,244 air freight intercontinental shipments to 4 automotive production plants in Latin America. Different algorithm classes were tested in the knowledge discovery in databases (KDD) process: support vector machine (SVM), random forest (RF), artificial neural networks (ANN) and k-nearest neighbors (KNN).FindingsShipper, consignee and LSP data attribute selection achieved 86% accuracy through the RF algorithm in a cross-validation scenario after a combined class balancing procedure.Originality/valueThese findings expand the current literature on machine learning applied to air freight delay management, which has mostly focused on weather, airport structure, flight schedule, ground delay and congestion as explanatory attributes.

Assessment of biomass ignition potential and behavior using a cost-effective CFD approach

This paper utilizes a CFD approach to study the ignition of pulverized biomass particles. Ignition is a critical parameter in a reactor’s design and process efficiency, and a reliable and relatively quick method of its determination is a necessity. CFD is a well-established tool that has already proved credible in many combustion/gasification applications, and for that reason, its application in ignition-related studies should be paramount. In this research, an Eulerian-Lagrangian approach is used where key stages during biomass combustion such as inert heating, evaporation, devolatilization, gas-phase kinetics, char conversion, particle transport, and radiative transport are considered. The predictions of the model are verified against experimentally measured ignition data from the literature and are found to be in good agreement. The ignition delay is determined by monitoring the concentrations of OH (hydroxyl) and CH (methyl) radicals. It is concluded that using OH species as ignition indicator allowed reproducing the delay better for lower temperatures, whereas, for temperatures above 1600 K, CH species was found to be more accurate. The CFD approach was eventually found reasonable and relatively fast in ignition delay predictions enabling its wider use in industrial applications.

Ignition characteristics of the high-velocity pulverized coal jet in MILD combustion mode: Experiments and prediction improvements

The influence of high jet velocity on the ignition characteristics of pulverized coal is very important for the Moderate or Intense Low-oxygen Dilution (MILD) combustion technology of pulverized coal. This paper conducts experimental and numerical simulation research on the ignition characteristics of the pulverized coal jet in a high-temperature environment based on the Hencken-type flat flame burner. The results show that when the ambient temperature is 1873 K and the ambient oxygen mole fraction is 5 %, the ignition delay distance of the pulverized coal jet decreases as the jet velocity increases from 15 m/s to 100 m/s for the formation of MILD combustion. The adoption of the turbulent particle heat transfer model and the non-spherical particle motion model effectively improves the prediction of particle dispersion, ignition delay, and reaction zone in the high-velocity coal jet flame. The enhancement of gas–solid heat transfer by turbulent fluctuation plays a dominant role in advancing the coal ignition in the high-velocity jet, while the non-spherical shape of coal particles mainly improves the uniformity of reaction distribution. The influence of ignition characteristics in the high-velocity jet on the MILD combustion formation of pulverized coal has been also analyzed in detail.

A graph multi-attention network for predicting airport delays

Predicting airport delays is of great importance for aviation operations, from the development of effective air traffic management strategies to the reallocation of airline resources. In this paper, the long-term prediction of the next 24 h of network-wide delays is investigated. The sensitivity to error propagation over long time periods as well as dynamic spatial correlations and non-linear temporal correlations of the aviation network are considered. An external impact modeling module is introduced to account for the influence of weather on flight delay patterns. A Spatial-Temporal Gated Multi-Attention Graph Network (STGMAGNet) considering external impact to predict airport delays is then developed. We validate our model on a flight delays dataset collected from the Bureau of Transportation Statistics of US, covering January 1, 2019, to December 31, 2019. In long-term (input-24-predict-24 setting) forecasting, STGMAGNet provides state-of-the-art accuracy, with a MAE reduction of at least 21% averaged in arrival delay prediction, 18% averaged MAE reduction in departure delay prediction compared to MLP, LSTM, Seq2Seq and Transformer. Our model can enable aviation management to shift from a reactive to proactive approach, thus enhancing its operational efficiency and overall performance.

Data‐driven train delay prediction incorporating dispatching commands: An XGBoost‐metaheuristic framework

AbstractTrain delays can significantly impact the punctuality and service quality of high‐speed trains, which also play a crucial role in affecting dispatchers with their decision‐making. In this study, a data‐driven train delay prediction framework was proposed and strengthened by considering the impact of dispatching commands and the mechanisms of train delay propagation using XGBoost. Four metaheuristic algorithms were utilized to fine‐tune its hyperparameters. A vast dataset comprising 1.9 million records spanning 38 months of train operation data was utilized for feature extraction and model training. The model's accuracy was evaluated using three statistical metrics, and a comparison of the four tuning frameworks was performed. To emphasize the model's interpretability and its practical guidance for train rescheduling, the relationship of dispatching commands, delay propagation and delay prediction was validated by combining the theory and practical results, and a SHAP (SHapley Additive exPlanations) analysis was used for a clearer model explanation. The results revealed that distinct XGBoost‐Metaheuristic models exhibit unique effects in different criteria, yet they all demonstrated high accuracy and low prediction errors, thereby revealing the potential of using machine learning for train delay prediction, which is valuable for decision‐making and rescheduling.

Transport causality knowledge-guided GCN for propagated delay prediction in airport delay propagation networks

Flight delays pose a worldwide challenge that significantly affect the safety and efficiency of air transportation systems. However, propagated delay prediction, as well as its causality among airport delay propagation networks, has not considered some crucial issues regarding spatiotemporal dependence and propagation relationships. Thus, this study proposes a transport causality knowledge-guided extended graph convolutional network (GCN) framework to tackle these issues. In particular, a causality knowledge-guided airport delay propagation network (ADPN) is developed using the second modified transfer entropy (SMTE) principle. Furthermore, a causality-embedded adjacency matrix is utilized by an extended GCN for propagated delay prediction. Comprehensive validations and results indicate that the proposed method benefits significantly from the causality knowledge, and increases the prediction performances up to 15.51%. Thus, transport causality is significant and efficient for understanding propagated delay features and airport delay propagation network characteristics.

Prediction of departure delays at original stations using deep learning approaches: A combination of route conflicts and rolling stock connections

Rolling stock connections and route conflicts of trains at terminal stations are critical to train delay propagation and prediction on the railway networks. Previous studies primarily focused on delay prediction/propagation from a macro perspective, without considering the two factors. To address this problem, a hybrid neural network architecture, called TLF-net, is proposed to predict departure delays at original stations (DDOSs), considering the rolling-stock connection and potential route conflicts in the railway network. TLF-net consists of a transformer, a long short-term memory (LSTM), and a fully-connected neural network (FCNN) block, to separately address variables with different characteristics. Based on the real-world data from two terminal stations in China, the experimental results show that the consideration of the potential route conflicts from the network can considerably improve TLF-net's prediction performance over the model that only considering train interactions on a single railway line. Also, it is proven that arrival/departure routes of consecutive trains are crucial for delay prediction, while using the transformer block can efficiently reveal the route conflict severity between arrival/departure routes. The sensitivity analysis to influence factors demonstrates the significance of considering the rolling stock connection and potential route conflicts. Finally, to support real-time railway traffic management, a train arrival delay prediction model from our previous study is integrated to predict the input of TLF-net (i.e., train arrival delays), enabling the proposed model to dynamically predict the DDOSs. This dynamic updating lengthens the prediction horizon (the prediction time ahead), making it better support real-time train traffic control and management.

Gaussian Noise Data Augmentation-Based Delay Prediction for High-Speed Railways

Accurately predicting delays for high-speed railways (HSRs) is a challenging yet significant task. The historical operation data of the HSRs, implicating delay derivation rules under the dispatchers’ rescheduling strategies, have sparsity characteristics, resulting in heterogeneous prediction performances under different scenarios. This article proposes a Gaussian noise data augmentation-based delay prediction method to cope with the sparsity. Specifically, the Gaussian noise is added to the original data based on the train operation data characteristics. Then, the delay data rather than the full-state dataset are selected as the training data for different designed machine learning prediction models. Numerous studies based on real HSR operational data from the Beijing Railway Bureau show that the proposed method could significantly improve the prediction accuracy under different scenarios with different machine learning models, verifying the effectiveness of the performance improvement. The relevant results could be significantly helpful for real-time train rescheduling and passenger management, thus improving the emergency response capabilities of HSRs.

Dynamic Switching Control of Power-Split Hybrid Electric Vehicles Based on Time Delay Prediction and Interference Compensation

The deterioration of vehicle dynamics caused by the simultaneous action of time delay and interference is a key issue for the switching control system in a power-split hybrid electric vehicle (PS-HEV). This paper presents an innovative compound control method based on extended state observer (ESO) incorporating time delay during the mode transition process. First, the coupling effect of time-varying delay and external disturbance during the typical mode switching process is analyzed in depth, and the double deterioration mechanism of the two coupling effects on vehicle dynamics and ride comfort is revealed. To accurately estimate the system disturbance under the influence of time delay, an unconventional ESO is designed further by adopting the Markov chain time delay prediction model, and the main tool for interference observation is selected by comparing the practicability, reachable bandwidth and observation accuracy. Moreover, the stable mode switching performance and interference suppression are thoroughly investigated, and the smooth transmission of multi-power is realized through the multi-module fusion design of the compound coordinated controller. Finally, the hardware-in-the-loop test is implemented to validate the effectiveness of the control strategy, which also provides a novel idea and lays a theoretical foundation for the optimal design of the PS-HEV controller.

Ionospheric TEC modeling using COSMIC-2 GNSS radio occultation and artificial neural networks over Egypt

Abstract The ionospheric delay significantly impacts GNSS positioning accuracy. To address this, an Artificial Neural Network (ANN) was developed using the high-quality COSMIC-2 ionospheric profile dataset to predict the Total Electron Content (TEC). ANNs are adept at addressing both linear and nonlinear challenges. For this research, eight distinct ANNs were cultivated. These ANNs were designed with the following inputs Year, Month, Day, Hour, Latitude, and Longitude. Along with solar and geomagnetic parameters such as the F10.7 solar radio flux index, the Sunspot Number (SSN), the Kp index, and the ap index. The goal was to discern the most influential parameters on ionosphere prediction. After pinpointing these key parameters, an enhanced model utilizing a pioneering technique of a secondary ANN was employed with the main ANN to predict TEC values for events in 2023. The study’s findings indicate that solar parameters markedly enhance the model’s accuracy. Notably, the augmented model featuring a prelude secondary network achieved a stellar correlation coefficient of 0.99. Distributionally, 41 % of predictions aligned within the (−1≤ ΔTEC ≤1) TECU spectrum, 28 % nestled within the (1&lt; ΔTEC ≤2) and (−2≤ ΔTEC &lt;−1) TECU ambit, while a substantial 30 % spanned the broader (2&lt; ΔTEC ≤5) and (−5≤ ΔTEC &lt;−2) TECU range. In essence, this research underscores the potential of incorporating solar parameters and advanced neural network techniques to refine ionospheric delay predictions, thus boosting GNSS positioning precision.

Delay prediction with spatial–temporal bi-directional LSTM in railway network

Train delay prediction is a vital part of railway system, but due to uncertain factors such as the complexity of the railway system and spatial–temporal features, it is often difficult to predict train delay in practice. In this paper, we propose a Spatial–Temporal and Bi-directional Long Short-Term Memory (ST-BiLSTM) model to deal with the train delay prediction problem. The model contains spatial–temporal blocks to capture spatial and temporal features and a bi-directional Long Short-Term Memory (LSTM) block to introduce bi-directional information through an attention mechanism. Experiments demonstrate that ST-BiLSTM outperforms the existing baselines in two evaluation metrics.