Physics Informed Temporal Multimodal Multivariate Learning for Short-Term Traffic State Prediction

EasyChair Preprint no. 11010

Abstract

Estimating multimodal distributions of travel times (TT) from real-world data is critical for understanding and managing congestion. Mixture models can estimate the overall distribution when distinct peaks exist in the probability density function, but no transfer of mixture information under epistemic uncertainty across different spatiotemporal scales has been considered for capturing unobserved heterogeneity. In this paper, a physics-informed and -regularized (PIR) prediction model is developed that shares observations across similarly distributed network segments over time and space. By grouping similar mixture models, the model uses a particular sample distribution at distant non-contiguous unexplored locations and improves TT prediction. The model includes hierarchical Kalman filtering (KF) updates using the traffic fundamental diagram to regulate any spurious correlation and estimates the mixture of TT distributions from observations at the current location and time sampled from the multimodal and multivariate TT distributions at other locations and times. In order to overcome the limitations of KF, this study developed dynamic graph neural network (GCN) model which uses time evolving spatial correlations. The KF model with PIR predicts traffic state with 19% more accuracy than TMML model in Park et al.(2022) and GCN model will further reduce the uncertainty in prediction. This study uses information gain from explored correlated links to obtain accurate predictions for unexplored ones.

Keyphrases: Dynamic adjacent graphs, Graph Neural Network, Kalman filter, Physics Informed Regularization, Traffic State Prediction

@Booklet{EasyChair:11010,
  author = {Niharika Deshpande and Justice Darko and Hyoshin Park and Gyugeun Yoon and Venktesh Pandey},
  title = {Physics Informed Temporal Multimodal Multivariate Learning for Short-Term Traffic State Prediction},
  howpublished = {EasyChair Preprint no. 11010},

  year = {EasyChair, 2023}}