Research on Flight Delay Prediction Based on Adaptive Kalman Filter and LSTM
LUO Feng'e
GUO Lingyu
DU Yuxin
WEI Changbo
XU Yong
Abstract：This study proposes a flight delay prediction model combining adaptive Kalman filtering(ACKF)and long short-term memory(LSTM)networks to improve prediction accuracy.While LSTM excels in capturing temporal dependencies,it struggles with extreme delay events.To address this,ACKF is incorporated to dynamically adjust predictions,enhancing the model's robustness.Experimental results show that the ACKF-LSTM model outperforms traditional LSTM and other models in metrics such as mean squared error(MSE)and root mean squared error(RMSE),significantly improving the accuracy of flight delay predictions.
Keywords：flight delay predictionKalman filterLSTMtime series analysisdeep learning
Publication Date：2025-01-19
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 43-47 )