Traffic prediction is the task of predicting traffic volumes, utilising historical speed and volume data.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain.
SOTA for Traffic Prediction on METR-LA
However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence.
Predicting traffic conditions from online route queries is a challenging task as there are many complicated interactions over the roads and crowds involved.
Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i. e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical.
The visualization of graph convolution weights shows that the proposed framework can accurately recognize the most influential roadway segments in real-world traffic networks.
A GPU-based stochastic projected gradient descent method is proposed to efficiently solve the multi-year 24/7 DODE problem.