From micro to macro: multi-scale causal emergent complexity analysis in traffic dynamics

Accurate traffic prediction is essential for modern urban transportation systems. In this paper, we propose a novel multiscale causal modeling framework for traffic prediction, leveraging Emergent Complexity (EC 2.0) analysis to uncover thehierarchical nature of traffic dynamics. Through detailed experiments on real-world datasets (PEMS08, PEMS04, METR-EC)and Beijing Freeway & Rural Scenario datasets, we demonstrate the dominance of spatial dependencies in traffic patternswhile highlighting the complementary role of temporal relationships. Our approach identifies critical nodes and paths withinthe network, revealing congestion-prone areas and informing targeted interventions. Furthermore, we show that our multiscale model outperforms existing methods, achieving state-of-the-art results across all datasets. By analyzing phase transitionsin causal gains (ΔCP) and training dynamics, we provide interpretable insights into the model’s learning process and causalstructure discovery. This work advances the field of traffic prediction by integrating causal reasoning and multi-scale modeling,offering both high accuracy and interpretability.