Flight Delay Prediction Using Deep Convolutional Neural Network Based on Fusion of Meteorological Data
- PDF / 847,398 Bytes
- 24 Pages / 439.37 x 666.142 pts Page_size
- 25 Downloads / 259 Views
Flight Delay Prediction Using Deep Convolutional Neural Network Based on Fusion of Meteorological Data Jingyi Qu1
· Ting Zhao1 · Meng Ye1 · Jiayi Li2 · Chao Liu1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Nowadays, the civil aviation industry has a high precision demand of flight delay prediction. To make full use of the characteristics of flight data and meteorological data, two flight delay prediction models using deep convolution neural network based on fusion of meteorological data are proposed in this paper. One is DCNN (Dual-channel Convolutional Neural Network), which refers to the ResNet network structure. The other is SE-DenseNet (Squeeze and Excitation-Densely Connected Convolutional Network), combining the advantages of DenseNet and SENet. Firstly, flight data and meteorological data are fused in the model. Then, both DCNN and SE-DenseNet models are used to extract feature automatically based on the fused flight data set. Finally, the softmax classifier is adopted to predict the flight delay level. For proposed DCNN model, both straight channel and convolution channel are designed to guarantee the lossless transmission of the feature matrix and enhance the patency of the deep network. For proposed SE-DenseNet model, a SE module is added after the convolution layer of each DenseNet block, which can not only enhance the transmission of deep information but also achieve feature recalibration in the feature extraction process. The research results indicate that after considering characteristics of meteorological information, the accuracy of the model can be improved 1% compared with only considering the flight information. The two deep convolutional neural networks proposed in this paper, DCNN and SE-DenseNet, can both effectively improve the prediction accuracies, reaching to 92.1% and 93.19%, respectively. Keywords Flight delay prediction · DCNN · SE-DenseNet · Data fusion
B
Jingyi Qu [email protected]
1
Tianjin Key Laboratory of Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, China
2
Qingdao Air Traffic Management Station of Civil Aviation of China, East China Air Traffic Control Bureau, Qingdao 266000, China
123
J. Qu et al.
1 Introduction Due to the development of the national economy, the increase of air traffic flow and the deficiencies in airspace, ground and manpower support, the problem of flight delay is becoming more and more serious in China’s Civil Aviation. Since flight delays will not only bring pernicious inconvenience to passengers, but also cause malignant group events, it is really important to give a fast and accurate prediction about flight delays [1–3]. Aimed at solving the problem of flight delay prediction, a lot of research has been carried out by domestic and foreign scholars. Traditional machine learning algorithms, such as Bayesian network, decision tree, support vector machine, stochastic forest, artificial neural network and so on, have been mostly adopted in current research [4–19]. Cao et al. [11]
Data Loading...
