基于时效信息和深度学习的离港航班延误预测

针对离港航班延误预测问题,利用深度神经网络模型,结合时效航班信息数据和时效气象数据,提出了一种基于时效信息和深度学习的离港航班延误预测模型。利用真实数据开展数值试验,结果表明了所构建的延误预测模型可以在较短时间内获得较高的航班延误预测精度,并且具有较大的航班延误预测时效；同时随着延误时间阈值的增加,预测精度不断提高,损失值不断降低；尤其以60分钟为阈值时,模型的预测精度可以达到91.26%,说明了模型的有效性。

The Departure Flight Delay Prediction Research Based on Timely Information and Deep Learning

For the problem of departure delay prediction, the departure flight delay prediction model based on timely information and deep learning is proposed by deep neural network model, combined with timely flight information data and meteorological data . The results of numerical experiments with real data show that the prediction accuracy of the model can be improved in a short period of time, and it has a large time effectiveness of flight delay prediction; at the same time, with the increase of threshold value, the prediction accuracy of the model is continuously improved, and the loss value of the model is constantly reduced; especially when the threshold value is 60 minutes, the prediction accuracy of the model can reach 91.26% , which shows the validity of the model.