Event-Aware Multimodal Mobility Nowcasting

TL;DR

This paper introduces EAST-Net, a novel spatio-temporal model that explicitly captures intermodal mobility interactions and adapts to societal events for improved crowd movement nowcasting.

Contribution

It proposes a heterogeneous mobility information network and a memory-augmented dynamic filter generator to enhance predictive accuracy during societal events.

Findings

EAST-Net outperforms state-of-the-art baselines on real-world datasets.

The model effectively captures event-driven mobility deviations.

Experimental results demonstrate improved prediction accuracy and adaptability.

Abstract

As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal predictive modeling for crowd movements is a challenging task particularly considering scenarios where societal events drive mobility behavior deviated from the normality. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods are neither aware of the dynamic interactions among multiple transport modes nor adaptive to unprecedented volatility brought by potential societal events. In this paper, we are therefore motivated to improve the canonical spatio-temporal network (ST-Net) from two perspectives: (1) design a heterogeneous mobility information network (HMIN) to explicitly represent intermodality in multimodal mobility; (2) propose a memory-augmented dynamic filter generator (MDFG) to generate sequence-specific parameters in an on-the-fly fashion for various scenarios. The enhanced event-aware spatio-temporal network, namely EAST-Net, is evaluated on several real-world datasets with a wide variety and coverage of societal events. Both quantitative and qualitative experimental results verify the superiority of our approach compared with the state-of-the-art baselines. Code and data are published on https://github.com/underdoc-wang/EAST-Net.