Qu Jingyi, Xiao Min, Yang Liu, Xie Wenkai
Tianjin Key Laboratory of Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, China.
Entropy (Basel). 2023 May 8;25(5):770. doi: 10.3390/e25050770.
Accurate prediction results can provide an excellent reference value for the prevention of large-scale flight delays. Most of the currently available regression prediction algorithms use a single time series network to extract features, with less consideration of the spatial dimensional information contained in the data. Aiming at the above problem, a flight delay prediction method based on Att-Conv-LSTM is proposed. First, in order to fully extract both temporal and spatial information contained in the dataset, the long short-term memory network is used for getting time characteristics, and a convolutional neural network is adopted for obtaining spatial features. Then, the attention mechanism module is added to improve the iteration efficiency of the network. Experimental results show that the prediction error of the Conv-LSTM model is reduced by 11.41 percent compared with the single LSTM, and the prediction error of the Att-Conv-LSTM model is reduced by 10.83 percent compared with the Conv-LSTM. It is proven that considering spatio-temporal characteristics can obtain more accurate prediction results in the flight delay problem, and the attention mechanism module can also effectively improve the model performance.
准确的预测结果可为大规模航班延误的预防提供极佳的参考价值。当前大多数可用的回归预测算法使用单一时间序列网络来提取特征，较少考虑数据中包含的空间维度信息。针对上述问题，提出了一种基于注意力卷积长短期记忆网络（Att-Conv-LSTM）的航班延误预测方法。首先，为了充分提取数据集中包含的时间和空间信息，使用长短期记忆网络来获取时间特征，并采用卷积神经网络来获取空间特征。然后，添加注意力机制模块以提高网络的迭代效率。实验结果表明，与单一长短期记忆网络相比，卷积长短期记忆网络（Conv-LSTM）模型的预测误差降低了11.41%，与Conv-LSTM相比，注意力卷积长短期记忆网络（Att-Conv-LSTM）模型的预测误差降低了10.83%。事实证明，考虑时空特征可以在航班延误问题中获得更准确的预测结果，并且注意力机制模块也可以有效提高模型性能。
