Train Delay Prediction Research Articles

Enhancing freight train delay prediction with simulation‐assisted machine learning

AbstractBoosting the rail freight modal share is an ambitious target in Europe and North America. Yards, where freight trains are arranged, can be crucial in realizing this target by reliable dispatching to the network. This paper predicts freight train departures by developing a simulation‐assisted machine learning model with two concepts: general (adding all predictors at once) and step‐wise (adding predictors as they become available in sub‐yard operations) for hump yards with the conventional layout to provide a generalized model for European and North American contexts. The developed model is a decision tree algorithm, validated via 10‐fold cross‐validation. The model's performance on three data sets—a real‐world European yard, a baseline simulation, and an ultimate randomness simulation for a comparable North American yard—shows a respective of 0.90, 0.87, and 0.70. Step‐wise inclusion of the predictors results differently for the real‐world and simulation data. The global feature importance highlights maximum planned length, departure weekday, the number of arriving trains, and minimum arrival deviation as key predictors for the real‐world data. For the simulation data, the most significant predictors are departure yard predictors, the number of arriving trains, and the maximum hump duration. Additionally, utilization rates—except for the receiving yard—enhance the predictions.

Bayesian Spatio-Temporal Graph Convolutional Network for Railway Train Delay Prediction

Bayesian Spatio-Temporal Graph Convolutional Network for Railway Train Delay Prediction

Barzilai Borwein Incremental Grey Polynomial Regression for train delay prediction

AbstractThe swift societal evolution and ceaseless advancement of human value of life have been set forth for reliability as well as rapidity of railway transportation. Latest advances in machine learning approaches as well as surging accessibility of numerous information sources is produced state‐of‐the‐art probabilities for significant, precise train delay identification. In this method called, Barzilai Borwein Incremental Grey Polynomial Regression (BBI‐GPR) is introduced for predicting train arrival/departure delays, which utilized for later delay management in an accurate manner with this method comprised into three sections such as, pre‐processing, feature selection and classification. First, with the raw ETA train delay dataset as input, Barzilai–Borwein Feature Rescaling‐based Pre‐processing is applied to model computationally efficient feature rescaled and normalized values. Second with processed features as input, Incremental Maximum Relevance Minimum Redundant‐based Feature Selection is applied to select error minimized optimal features. Finally, with optimal features selected as input, Grey Polynomial Regression‐based Prediction algorithm is employed to analyse train delay. For confirming proposed BBI‐GPR, as well as analyse its performance, compare standard train delay prediction method with existing machine learning‐based regression method. Results show that new variants outperform existing train delay prediction method by minimizing train delay prediction time, error rate by 25% and 27% respectively, with improved accuracy rate of 7%, therefore paving ways for efficient train delay prediction.

A Novel Hybrid Deep Learning Model for Complex Systems: A Case of Train Delay Prediction

Predicting the status of train delays, a complex and dynamic problem, is crucial for railway enterprises and passengers. This paper proposes a novel hybrid deep learning model composed of convolutional neural networks (CNN) and temporal convolutional networks (TCN), named the CNN + TCN model, for predicting train delays in railway systems. First, we construct 3D data containing the spatiotemporal characteristics of real-world train data. Then, the CNN + TCN model employs a 3D CNN component, which is fed into the constructed 3D data to mine the spatiotemporal characteristics, and a TCN component that captures the temporal characteristics in railway operation data. Furthermore, the characteristic variables corresponding to the two components are selected. Finally, the model is evaluated by leveraging data from two railway lines in the United Kingdom. Numerical results show that the CNN + TCN model has greater accuracy and convergence performance in train delay prediction.

Impact of feature cross in hybrid optimization based convolutional neural networks for train delay prediction

Impact of feature cross in hybrid optimization based convolutional neural networks for train delay prediction

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.

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

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.

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.

A novel deep learning model for short-term train delay prediction

As the density of railway operations increases annually, train delays typically result in a greater degree of economic loss. If we can accurately assess the current evolution of delayed trains, railway authorities will be able to make timely decisions and reduce travel anxiety among passengers. In this paper, a deep learning model integrating wavelet transform (WT), fully connected neural network (FCNN), and long short-term memory (LSTM) network is proposed to address the short-term delay prediction problem for trains. Its predictive performance is enhanced by introducing two front train selection schemes, two methods for converting train operating time features into time-series data, and five commonly used wavelet functions. For validation purposes, the model is tested using real-world operational data from two distinct high-speed railway lines in China, and common machine learning algorithms are compared, including random forest (RF), gradient boosting regression tree (GBRT), XGBoosting (XGB), and support vector regression (SVR). The final experimental results demonstrate that our proposed model outperforms the benchmark models and can be effectively applied to practical prediction problems.

A GTFS data acquisition and processing framework and its application to train delay prediction

With advanced artificial intelligence and deep learning techniques, a growing number of data sources are playing more and more critical roles in planning and operating transportation services. The General Transit Feed Specification (GTFS), with standard open-source data in both static and real-time formats, is being widely used in public transport planning and operation management. However, compared to other extensively studied data sources such as smart card data and GPS trajectory data, the GTFS data lacks proper investigation yet. Utilization of the GTFS data is challenging for both transport planners and researchers due to its difficulty and complexity of understanding, processing, and leveraging the raw data. In this paper, a GTFS data acquisition and processing framework is proposed to offer an efficient and effective benchmark tool for converting and fusing the GTFS data to a ready-to-use format. To validate and test the proposed framework, a multivariate multistep Long Short-Term Memory is developed to predict train delay with minor anomaly in Sydney as a case study. The contribution of this new framework will render great potential for broader applications and deeper research.

An Interpretable Station Delay Prediction Model Based on Graph Community Neural Network and Time-Series Fuzzy Decision Tree

High-speed train delay prediction has always been one of the important research issues in the railway dispatching. Accurate and interpretable delay prediction can enable staff to implement preventive measures and scheduling decisions in advance, and guide relevant departments to cooperate in completing complex transportation tasks, so as to improve rail transit operations, service quality, and the efficiency of train operation. This article proposes a new interpretable model based on graph community neural network and time-series fuzzy decision tree. This model can well capture the influence of spatiotemporal characteristics, train community structure, and multifactor in high-speed train station delay prediction. Besides, the time series fuzzy decision tree based on multiobjective optimization and reduced error pruning can mine potential decision rules to improve the model's interpretability, transparency, and high reliability. Finally, we prove that the prediction effect of the proposed model is superior than the other seven state-of-the-art models and our model is interpretable.

A review of data-driven approaches to predict train delays

Accurate train delay prediction is vital for effective railway traffic planning and management as well as for providing satisfactory passenger service quality. Despite significant advances in data-driven train delay predictions, it lacks of a systematic review of studies and unified modelling development framework. The paper reviews existing studies with an explicit focus on synthesizing a structural framework that could guide effective data-driven train delay prediction model development. The framework consists of three stages including design concept, modelling and evaluation. The study synthesize and discusses six important modules of the framework: (1) Problem scope, (2) Model inputs, (3) Data quality, (4) Methodologies, (5) Model outputs, and (6) Evaluation techniques. For each module, the important problems and techniques reported are synthesized and research gaps are discussed. The review found that most studies focus on developing complex methodologies for the next stop delay predictions that have limited applications in practice. All studies validate the model accuracy, but very few consider other model performance aspects which makes it difficult to assess their usfulness in practical deployment. Future studies need a holistic view on defining the train delay prediction problem considering both application requirements and implementation challenges. Also, the modelling studies should place more attention to data quality and comprehensive model evaluations in representation power, explainability and validity.

A Global Modeling Pruning Ensemble Stacking With Deep Learning and Neural Network Meta-Learner for Passenger Train Delay Prediction

A Global Modeling Pruning Ensemble Stacking With Deep Learning and Neural Network Meta-Learner for Passenger Train Delay Prediction

Enhancing the Understanding of Train Delays With Delay Evolution Pattern Discovery: A Clustering and Bayesian Network Approach

Train delay evolutions exhibit different patterns (i.e., increasing delays, decreasing delays, or unchanged delays), because of the effects of stochastic disturbances and pre-scheduled supplement/recovery times. The dynamics and uncertainty of the train delay evolution make train delay prediction a challenging task. This study presents a hybrid framework, called context-driven Bayesian network (CDBN), composed of a delay evolution pattern discovery model, i.e., a K-Means clustering approach, and a train delay prediction model, i.e., Bayesian network (BN), to address this problem. The clustering algorithm is used to uncover the delay evolution patterns, and classify the data into different categories, based on the delay jumps, i.e., the change of a delay from one station to a consequent station. The BN model, which considers the delays in previous stations to overcome the Markov property assumption, is used as the predictive model of train delays. The data in each category (classified by the clustering model) are used to train and test the BN model separately. We evaluated the BN model, the clustering algorithm, and the CDBN model, by comparing against their counterparts, respectively. The results show that: (1) the proposed BN structure has advantages over the common delay prediction models built on Markov property; (2) the clustering is effective, and it can extensively improve the accuracy of the predictive model; and (3) the CDBN outperforms the existing delay prediction models in wide usability, because of its more profound understanding of the delay evolution patterns.

A multi-output deep learning model based on Bayesian optimization for sequential train delays prediction

ABSTRACT Accurate train arrival delay predictions can provide timely information for passengers and train dispatchers. Previous work mainly focused on predicting the delay of a single train, which is not enough to assist dispatchers, because making more comprehensive decisions considering more trains needs more future delay information of a group of trains. Therefore, this paper proposes a Bayesian optimization-based multi-output deep learning model, which includes a fully connected neural network (FCNN) and two long–short-term memory (LSTM) components, to predict the arrival delays of multiple trains simultaneously. The proposed model is calibrated and validated with the train operation data from the Wuhan–Guangzhou (W-G) high-speed railway. The test results show that the mean absolute error and the root mean square error of the proposed model is 1.379 and 2.021 min, over the four subsequent trains. Moreover, the proposed model outperforms the standard train delay prediction benchmark model.

A Two-Stage Train Delay Prediction Method Based on Data Smoothing and Multimodel Fusion Using Asymmetry Features in Urban Rail Systems

During the operation of urban rail transit trains, train delays have a great negative impact on subway safety and operation management. It is caused by various external environmental disturbances or internal equipment failures. In order to better grasp the situation of train delays, adjust train operation schedules in time, and improve the quality of rail transit command and transportation services, this paper proposes a two-stage train delay prediction method based on data smoothing and multimodel fusion. In the first stage, the Singular Spectrum Analysis (SSA) method is used to smooth the train operation data, and the smoothed components and residual components are extracted. In the second stage, we use different machine learning methods to train the smoothed data and use the K -nearest neighbor (KNN) method to fuse different trainers. Finally, the predicted values of the smoothed and residual components are combined to improve the overall performance of the train delay prediction model, especially under asymmetry features. The research results show that the prediction accuracy of the two-stage train delay prediction method based on KNN multimodel fusion is significantly better than that of the independent machine learning model.

Prediction of train arrival delays considering route conflicts at multi-line stations

Multi-line stations (MLSs) are the intersections of different railway lines; they are crucial for delay propagation in railway networks. Therefore, the precise prediction of train arrival delays at the MLSs can efficiently support train operation rescheduling plans and reduce delay propagation in the railway network. The arrival routes of trains at the MLSs are critical factors for managing train arrival delays, since there may be latent route conflicts with forward arrival/departure trains. However, route conflicts will not occur at single-line stations (SLSs) that are traversed by only one railway line. Existing train delay prediction studies have considered the ways that trains arrive at/depart from stations as black boxes, but have not considered the latent route conflicts from a microscopic view. This study considers the arrival routes of predicted trains and route conflicts with forward trains, for contemplating the gap (not considering the route conflicts from other railway lines) in the existing studies. The influencing factors are separated into three categories according to the data attributes, namely, route-related variables, delay-related variables, and environment-related variables. Then, an architecture called LLCF-net is proposed, with a one-dimensional convolutional neural network (CNN) block for route-related variables, two long short-term memory (LSTM) networks for delay-related variables, and a fully connected neural network (FCNN) block for environment-related variables. Compared with the methods in exiting studies, this architecture showed the best performance for both two MLSs—GuangzhouSouth(GZS) and ChangshaSouth (CSS)—on the Chinese high-speed railway network, regardless of the consideration of route-related variables. In addition, LLCF-net is proven to have a strong predictive effectiveness and a robust performance for different delay lengths.

Train Time Delay Prediction for High-Speed Train Dispatching Based on Spatio-Temporal Graph Convolutional Network

Train delay prediction can improve the quality of train dispatching, which helps the dispatcher to estimate the running state of the train more accurately and make reasonable dispatching decision. The delay of one train is affected by many factors, such as passenger flow, fault, extreme weather, dispatching strategy. The departure time of one train is generally determined by dispatchers, which is limited by their strategy and knowledge. The existing train delay prediction methods cannot comprehensively consider the temporal and spatial dependence between the multiple trains and routes. In this paper, we don’t try to predict the specific delay time of one train, but predict the collective cumulative effect of train delay over a certain period, which is represented by the total number of arrival delays in one station. We propose a deep learning framework, train spatio-temporal graph convolutional network (TSTGCN), to predict the collective cumulative effect of train delay in one station for train dispatching and emergency plans. The proposed model is mainly composed of the recent, daily and weekly components. Each component contains two parts: spatio-temporal attention mechanism and spatio-temporal convolution, which can effectively capture spatio-temporal characteristics. The weighted fusion of the three components produces the final prediction result. The experiments on the train operation data from China Railway Passenger Ticket System demonstrate that TSTGCN clearly outperforms the existing advanced baselines in train delay prediction.

The Bounds of Improvements Toward Real-Time Forecast of Multi-Scenario Train Delays

Different from the existing train delay studies that had strived to explore sophisticated algorithms, this paper focuses on finding the bound of improvements on predicting multi-scenario train delays with different machine learning methods. Motivated by the observation of deep learning methods failing to improve the prediction performance if the delay occurs rarely, we present a novel augmented machine learning approach to improve the overall prediction accuracy further. Our solution proposes a rule-driven automation (RDA) method, including a delay status labeling (DSL) algorithm, and the resilience of section (RSE) and resilience of station (RST) indicators to generate the forecast for train delays. The experiment results demonstrate that the Random Forest based implementation of our RDA method (RF-RDA) can significantly improve the generalization ability of multivariate multi-step forecast models for multi-scenario train delay prediction. The proposed solution surpasses state-of-art baselines based on real-world traffic datasets, which treat various real-time delays differently. Even when the predictability of conventional deep learning methods decreases, the performance of our method is still acceptable for practical use to provide accurate forecasts.