Listening to the city, attentively: A Spatio-Temporal Attention Boosted Autoencoder for the Short-Term Flow Prediction Problem

TL;DR

This paper introduces STREED-Net, a deep learning model with spatio-temporal attention, that improves short-term urban mobility flow prediction by capturing complex patterns, aiding transportation planning especially during pandemic conditions.

Contribution

The paper presents a novel multi-attention deep learning architecture, STREED-Net, specifically designed for accurate short-term urban mobility flow prediction.

Findings

STREED-Net outperforms existing models on real-world data.

The multi-attention mechanism effectively captures complex spatial-temporal dependencies.

Experimental results demonstrate significant accuracy improvements.

Abstract

In recent years, studying and predicting alternative mobility (e.g., sharing services) patterns in urban environments has become increasingly important as accurate and timely information on current and future vehicle flows can successfully increase the quality and availability of transportation services. This need is aggravated during the current pandemic crisis, which pushes policymakers and private citizens to seek social-distancing compliant urban mobility services, such as electric bikes and scooter sharing offerings. However, predicting the number of incoming and outgoing vehicles for different city areas is challenging due to the nonlinear spatial and temporal dependencies typical of urban mobility patterns. In this work, we propose STREED-Net, a novel deep learning network with a multi-attention (spatial and temporal) mechanism that effectively captures and exploits complex spatial and temporal patterns in mobility data. The results of a thorough experimental analysis using real-life data are reported, indicating that the proposed model improves the state-of-the-art for this task.