Dataset for Network-wide Traffic Forecasting
The data is collected by the inductive loop detectors deployed on freeways in Seattle area. The freeways contains I-5, I-405, I-90, and SR-520, shown in the above picture. This dataset contains spatio-temporal speed information of the freeway system. In the picture, each blue icon demonstrates loop detectors at a milepost. The speed information at a milepost is averaged from multiple loop detectors on the mainlanes in a same direction at the specific milepost. The time interval of the dataset is 5-minute.
speed_matrix_2015: Loop Speed Matrix, which is a pickled file that can be read by pandas or other python packages.Loop_Seattle_2015_A.npy: Loop Adjacency Matrix, which is a numpy matrix to describe the traffic network structure as a graph.Loop_Seattle_2015_reachability_free_flow_Xmin.npy: Loop Free-flow Reachability Matrix during X minites' drive.nodes_loop_mp_list.csv: List of loop detectors' milepost, with the same order of that in the Loop Speed Matrix.
A demo of the speed_matrix_2015 is shown as the following figure. The horizontal header denotes the milepost and the vertical header indicates the timestamps.
The name of each milepost header contains 11 characters:
- 1 char: 'd' or 'i', i.e. decreasing direction or increasing direction.
- 2-4 chars: route name, e.g. '405' demonstrates the route I-405.
- 5-6 chars: 'es' has no meanings here.
- 7-11 chars: milepost, e.g. '15036' demonstrates the 150.36 milepost.
Three Seattle loop detector datasets (pickled files) are added to the download link. The formats of the three files is similar to the speed matrix file.
volume_avg_matrix_2015: containing the averaged volume over all lanes of a road segment (a set of loop detectors)volume_total_matrix_2015: containing the total volume information (total volume = averaged volume * lane number)occupancy_avg_matrix_2015: containning the averaged occupancy information.
Data Download Link: Seattle Loop Dataset
Cui, Z., Ke, R., & Wang, Y. (2018). Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction. arXiv preprint arXiv:1801.02143.Cui, Z., Henrickson, K., Ke, R., & Wang, Y. (2019). Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting. IEEE Transactions on Intelligent Transportation Systems.
@article{cui2018deep,
title={Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction},
author={Cui, Zhiyong and Ke, Ruimin and Wang, Yinhai},
journal={arXiv preprint arXiv:1801.02143},
year={2018}
} ,
@article{cui2019traffic,
title={Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting},
author={Cui, Zhiyong and Henrickson, Kristian and Ke, Ruimin and Wang, Yinhai},
journal={IEEE Transactions on Intelligent Transportation Systems},
year={2019},
publisher={IEEE}
}