 This paper proposes a novel hybrid model for long-term traffic flow forecasting. The model uses variational mode decomposition, VMD, to decompose the data into intrinsic mode functions with different frequencies, allowing the model to extract the internal features of the data and better capture the changes of traffic flow data over time. Additionally, a convolutional layer is added to improve the residual structure and a correction module is used to further enhance the accuracy of the model. Finally, the model is tested on a dataset of taxi departures from Beijing Capital International Airport and achieves the best results in terms of mean-squared error and mean-absolute error when compared to the baseline model. This article was authored by Kai Senghua, Xinyu, Gao Xianglu, and others.