Seeing the Forest for the Trees: Road-Level Insights Assisted Lane-Level Traffic Prediction

Lane-level traffic prediction is crucial for refined smart city applications, yet the scarcity and quality issues of datasets hinder its development. To overcome these challenges, this study introduces a novel <u> M </u>ulti-<u> c </u>hannel <u> g </u>raph-structured <u> V </u>ariational <u> A </u>uto<u> E </u>ncoder model, McgVAE. This model integrates road-level information to provide a global perspective for lane prediction and performs integrated tasks through three interconnected channels: the road-level channel ensures accurate prediction of road traffic states and communicates closely with the data quality channel to share historical and predicted road information; the data quality channel leverages road-level information to identify and correct missing and noisy data; and finally, the lane channel uses the aforementioned information for lane-level traffic prediction. After extensive experimental comparisons with multiple baseline models across three datasets, the McgVAE model demonstrated outstanding predictive performance and the ability to handle data missingness and noise