Flight Delay Prediction Using Gradient Boosting Machine Learning Classifiers

With the increasing of civil aviation business,flight delay has become a key problem in civil aviation field in recent years,which has brought a considerable economic impact to airlines and related industries.The delay prediction of specific flights is very important for airlines’plan,airport resource allocation,insurance company strategy and personal arrangement.The influence factors of flight delay have high complexity and non-linear relationship.The different situations of various regions and airports,and even the deviation of airport or airline arrangement all have certain influence on flight delay,which makes the prediction more difficult.In view of the limitations of the existing delay prediction models,this paper proposes a flight delay prediction model with more generalization ability and corresponding machine learning classification algorithm.This model fully exploits temporal and spatial characteristics of higher dimensions,such as the influence of preceding flights,the situation of departure and landing airports,and the overall situation of flights on the same route.In the process of machine learning,the model is trained with historical data and tested with the latest actual data.The test result shows that the model and this machine learning algorithm can provide an effective method for the prediction of flight delay.

Short-term train arrival delay prediction:a data-driven approach

Purpose-To optimize train operations,dispatchers currently rely on experience for quick adjustments when delays occur.However,delay predictions often involve imprecise shifts based on known delay times.Real-time and accurate train delay predictions,facilitated by data-driven neural network models,can significantly reduce dispatcher stress and improve adjustment plans.Leveraging current train operation data,these models enable swift and precise predictions,addressing challenges posed by train delays in high-speed rail networks during unforeseen events.Design/methodology/approach-This paper proposes CBLA-net,a neural network architecture for predicting late arrival times.It combines CNN,Bi-LSTM,and attention mechanisms to extract features,handle time series data,and enhance information utilization.Trained on operational data from the Beijing-Tianjin line,it predicts the late arrival time of a target train at the next station using multidimensional input data from the target and preceding trains.Findings-This study evaluates our model’s predictive performance using two data approaches:one considering full data and another focusing only on late arrivals.Results show precise and rapid predictions.Training with full data achieves aMAEof approximately 0.54 minutes and a RMSEof 0.65 minutes,surpassing the model trained solely on delay data(MAE:is about 1.02 min,RMSE:is about 1.52 min).Despite superior overall performance with full data,the model excels at predicting delays exceeding 15 minutes when trained exclusively on late arrivals.For enhanced adaptability to real-world train operations,training with full data is recommended.Originality/value-This paper introduces a novel neural network model,CBLA-net,for predicting train delay times.It innovatively compares and analyzes the model’s performance using both full data and delay data formats.Additionally,the evaluation of the network’s predictive capabilities considers different scenarios,providing a comprehensive demonstration of the model’s predictive performance.

A geographical and operational deep graph convolutional approach for flight delay prediction

Flight delay prediction has attracted great interest in civil aviation community due to its significant role in airline planning,flight scheduling,airport operation,and passenger service.Flight delay is affected by numerous factors and irregularly propagates in air transportation networks owing to flight connectivity,which brings critical challenges to accurate flight delay prediction.In recent years,Graph Convolutional Networks(GCNs)have become popular in flight delay prediction due to the advantage in extracting complicated relationships.However,most of the existing GCN-based methods have failed to effectively capture the spatial-temporal information in flight delay prediction.In this paper,a Geographical and Operational Graph Convolutional Network(GOGCN)is proposed for multi-airport flight delay prediction.The GOGCN is a GCN-based spatial-temporal model that improves node feature representation ability with geographical and operational spatial-temporal interactions in a graph.Specifically,an operational aggregator is designed to extract global operational information based on the graph structure,while a geographical aggregator is developed to capture the similar nature among spatially close airports.Extensive experiments on a real-world dataset demonstrate that the proposed approach outperforms the state-of-the-art methods with a satisfying accuracy improvement.

DTHMM based delay modeling and prediction for networked control systems

In the forward channel of a networked control system （NCS）, by defining the network states as a hidden Markov chain and quantizing the network-induced delays to a discrete sequence distributing over a finite time interval, the relation between the network states and the network-induced delays is modelled as a discrete-time hidden Markov model （DTHMM）. The expectation maximization （EM） algorithm is introduced to derive the maximumlikelihood estimation （MLE） of the parameters of the DTHMM. Based on the derived DTHMM, the Viterbi algorithm is introduced to predict the controller-to-actuator （C-A） delay during the current sampling period. The simulation experiments demonstrate the effectiveness of the modelling and predicting methods proposed.

Multi-factor Comprehensive Prediction of Delay Time through Congested Road Sections

The navigation software uses the positioning system to determine the traffic conditions of the road sections in advance,so as to predict the travel time of the road sections.However,in the case of traffic congestion,the accuracy of its prediction time is low.After empirical analysis,this paper establishes a multi-factor synthesis by studying 7 factors:traffic flow,number of stops,traffic light duration,road network density,average speed,road area,and number of intersections the prediction function achieves the purpose of accurately predicting the transit time of congested road sections.The gray correlation coefficients of the seven factors obtained from the gray correlation analysis are:0.9827,0.9679,0.6747,0.8030,0.9445,0.8759,0.4328.The correlation coefficients of traffic volume,number of stops,average speed,and road congestion delay time were all about 95%,which were the main influencing factors of the study.The prediction needs to be based on functions.This paper fits the main influencing factors to the delay time of congested roads.It is found that the delay time varies parabolically with the traffic flow and the number of stops,and linearly with the average speed.Because the three impact factors have different weights on the delay time of congested roads,demand takes the weight of each factor.Therefore,the gray correlation coefficients occupied by the main influencing factors are normalized to obtain the weights of three of 0.340,0.334,and 0.326.The weighted fitting function is subjected to nonlinear summation processing to obtain a multi-factor comprehensive prediction function.By comparing the original data with the fitting data and calculating the accuracy of the fitting function,it is found that the accuracy of each fitting function is close to 0,the residual error,the relative error is small,and the accuracy is high.