Freeway Inductive Loop Detector Dataset for Network-wide Traffic Speed Prediction

The data is collected by the inductive loop detectors deployed on freeways in Seattle area. The freeways contain I-5, I-405, I-90, and SR-520. This data set contains spatiotemporal speed information of the freeway system. At each milepost, the speed information collected from main lane loop detectors in the same direction are averaged and integrated into 5 minutes interval speed data. The raw data is provided by Washington Start Department of Transportation (WSDOT) and processed by the STAR Lab in the University of Washington according to data quality control and data imputation procedures [1][2].  

The data file is a pickle file that can be easily read using the read_pickle() function in the Pandas package. The data forms as a matrix and each cell of the matrix is speed value for the specific milepost and time period. The horizontal header of the data set denotes the milepost and the vertical header indicates the timestamps. For more information on the definition of milepost, please refer to this website.

This data set been used for traffic prediction tasks in several research studies [3][4]. For more detailed information about the data set, you can also refer to this link.

References:

[1]. Henrickson, K., Zou, Y., & Wang, Y. (2015). Flexible and robust method for missing loop detector data imputation. Transportation Research Record, 2527(1), 29-36.

[2]. Wang, Y., Zhang, W., Henrickson, K., Ke, R., & Cui, Z. (2016). Digital roadway interactive visualization and evaluation network applications to WSDOT operational data usage (No. WA-RD 854.1). Washington (State). Dept. of Transportation.

[3]. 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.

[4]. Cui, Z., Henrickson, K., Ke, R., & Wang, Y. (2018). Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting. arXiv preprint arXiv:1802.07007.