A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Forecasting Freeway Traffic Volumes with Adverse Weather via a CNN-BiLSTM-Attention Model
https://orcid.org/0000-0002-4985-458X
https://orcid.org/0000-0001-8812-6350
Forecasting traffic volumes under adverse weather in advance contributes to allocating traffic resources for traffic managers and formulating optimal travel strategies for travelers, which assists in preventing and offsetting the impact of adverse weather on traffic. Consequently, the accurate prediction of traffic volume is vital. This paper proposes an adverse weather traffic volume prediction model combining convolution neural networks, bidirectional long short-term memory (BiLSTM), and the attention mechanism. Convolutional neural networks extract the spatial features of the traffic volume data and learn the connection between the traffic volume data and the data of each adverse weather impact factor; BiLSTM extracts the temporal features of the traffic volume data; and the attention mechanism captures the inhomogeneity of spatial-temporal features so that the model can pay more attention to the key features during the training process. The 5-min highway traffic volume data from December 1, 2021, to March 13, 2022, in Minnesota, United States, and the weather data in the same period provided by MesoWest were used as the experimental data. The proposed model was compared with three single prediction models, two validated hybrid models, and the model itself without integrating adverse weather impact factors. The experiments show that the prediction accuracy of the proposed model is higher than other comparison models.
Forecasting Freeway Traffic Volumes with Adverse Weather via a CNN-BiLSTM-Attention Model
https://orcid.org/0000-0002-4985-458X
https://orcid.org/0000-0001-8812-6350
Forecasting traffic volumes under adverse weather in advance contributes to allocating traffic resources for traffic managers and formulating optimal travel strategies for travelers, which assists in preventing and offsetting the impact of adverse weather on traffic. Consequently, the accurate prediction of traffic volume is vital. This paper proposes an adverse weather traffic volume prediction model combining convolution neural networks, bidirectional long short-term memory (BiLSTM), and the attention mechanism. Convolutional neural networks extract the spatial features of the traffic volume data and learn the connection between the traffic volume data and the data of each adverse weather impact factor; BiLSTM extracts the temporal features of the traffic volume data; and the attention mechanism captures the inhomogeneity of spatial-temporal features so that the model can pay more attention to the key features during the training process. The 5-min highway traffic volume data from December 1, 2021, to March 13, 2022, in Minnesota, United States, and the weather data in the same period provided by MesoWest were used as the experimental data. The proposed model was compared with three single prediction models, two validated hybrid models, and the model itself without integrating adverse weather impact factors. The experiments show that the prediction accuracy of the proposed model is higher than other comparison models.
Forecasting Freeway Traffic Volumes with Adverse Weather via a CNN-BiLSTM-Attention Model
https://orcid.org/0000-0002-4985-458X
https://orcid.org/0000-0001-8812-6350
Forecasting traffic volumes under adverse weather in advance contributes to allocating traffic resources for traffic managers and formulating optimal travel strategies for travelers, which assists in preventing and offsetting the impact of adverse weather on traffic. Consequently, the accurate prediction of traffic volume is vital. This paper proposes an adverse weather traffic volume prediction model combining convolution neural networks, bidirectional long short-term memory (BiLSTM), and the attention mechanism. Convolutional neural networks extract the spatial features of the traffic volume data and learn the connection between the traffic volume data and the data of each adverse weather impact factor; BiLSTM extracts the temporal features of the traffic volume data; and the attention mechanism captures the inhomogeneity of spatial-temporal features so that the model can pay more attention to the key features during the training process. The 5-min highway traffic volume data from December 1, 2021, to March 13, 2022, in Minnesota, United States, and the weather data in the same period provided by MesoWest were used as the experimental data. The proposed model was compared with three single prediction models, two validated hybrid models, and the model itself without integrating adverse weather impact factors. The experiments show that the prediction accuracy of the proposed model is higher than other comparison models.
Forecasting Freeway Traffic Volumes with Adverse Weather via a CNN-BiLSTM-Attention Model
J. Transp. Eng., Part A: Systems
Ci, Yusheng (author) / Gao, Xueyi (author) / Li, Haowen (author) / Yuen, Kum Fai (author) / Wu, Lina (author)
2025-02-01
Article (Journal)
Electronic Resource
English
Generalized Visibility of Freeway in Adverse Weather Conditions
| British Library Conference Proceedings | 2010
Multiple-Interval Freeway Traffic Flow Forecasting
| British Library Online Contents | 1996
Inclement Weather Impacts on Freeway Traffic Stream Behavior
| British Library Online Contents | 2008
Effect of weather conditions to traffic flow on freeway
| Springer Verlag | 2002