关键词: 短时交通流预测, 交通流时空特征提取, 残差结构, Transformer, 组合模型

Abstract: The prediction of urban highway traffic flow is influenced by historical traffic flow and neighboring lane traffic flow, involving complex spatio-temporal features. In order to address the insufficient feature extraction, feature confusion, and feature information loss caused by not separating the spatio-temporal features in the traditional traffic flow prediction model Convolutional Long Short-Term Memory (ConvLSTM), improvements are made to the ConvLSTM model. Firstly, the short-term temporal features and spatial features of the traffic flow data at each sampling moment were extracted, and the short-term spatio-temporal features of the traffic flow were fused in specific dimensions. Secondly, residual mapping was performed. Finally, the mapped short-term spatio-temporal features were captured by the Transformer model to capture the long-term spatio-temporal features of the traffic flow data, and based on the captured long-term features, the traffic flow at each sampling point in the future moment was predicted. The model is validated using California urban freeway data, and in the ablation experiment, when the Mean Absolute Error (MAE) is used as the model evaluation metric, the proposed model has the prediction accuarcy improved by 18% compared to the Conv-Transformer model, validating the effectiveness of the proposed model.

Key words: short-term traffic flow prediction, spatio-temporal feature extraction of traffic flow, residual structure, Transformer, combined model