Causal conditional hidden Markov model for multimodal traffic prediction

TL;DR

This paper introduces a Causal Conditional Hidden Markov Model (CCHMM) that incorporates physical causal concepts to improve the prediction of multimodal traffic flow, addressing the instability of spatio-temporal correlations.

Contribution

The paper proposes a novel CCHMM that models causal relationships in traffic data, enhancing interpretability and prediction accuracy over existing correlation-based methods.

Findings

CCHMM effectively disentangles causal representations of traffic concepts.

The model accurately predicts multimodal traffic flow on real datasets.

CCHMM identifies causality in traffic data, improving robustness.

Abstract

Multimodal traffic flow can reflect the health of the transportation system, and its prediction is crucial to urban traffic management. Recent works overemphasize spatio-temporal correlations of traffic flow, ignoring the physical concepts that lead to the generation of observations and their causal relationship. Spatio-temporal correlations are considered unstable under the influence of different conditions, and spurious correlations may exist in observations. In this paper, we analyze the physical concepts affecting the generation of multimode traffic flow from the perspective of the observation generation principle and propose a Causal Conditional Hidden Markov Model (CCHMM) to predict multimodal traffic flow. In the latent variables inference stage, a posterior network disentangles the causal representations of the concepts of interest from conditional information and observations, and a causal propagation module mines their causal relationship. In the data generation stage, a prior network samples the causal latent variables from the prior distribution and feeds them into the generator to generate multimodal traffic flow. We use a mutually supervised training method for the prior and posterior to enhance the identifiability of the model. Experiments on real-world datasets show that CCHMM can effectively disentangle causal representations of concepts of interest and identify causality, and accurately predict multimodal traffic flow.