Urban Vibrancy Embedding and Application on Traffic Prediction

TL;DR

This paper introduces a novel method that uses urban vibrancy embeddings derived from floating population data, combined with deep learning models, to significantly improve traffic prediction accuracy and responsiveness.

Contribution

It presents a new approach integrating VAE and LSTM to forecast urban vibrancy embeddings, enhancing traffic prediction models with interpretability of temporal patterns.

Findings

Improved traffic prediction accuracy across multiple models.

Revealed temporal patterns such as weekday/weekend and seasonal variations.

Enhanced responsiveness of traffic forecasting to dynamic urban changes.

Abstract

Urban vibrancy reflects the dynamic human activity within urban spaces and is often measured using mobile data that captures floating population trends. This study proposes a novel approach to derive Urban Vibrancy embeddings from real-time floating population data to enhance traffic prediction models. Specifically, we utilize variational autoencoders (VAE) to compress this data into actionable embeddings, which are then integrated with long short-term memory (LSTM) networks to predict future embeddings. These are subsequently applied in a sequence-to-sequence framework for traffic forecasting. Our contributions are threefold: (1) We use principal component analysis (PCA) to interpret the embeddings, revealing temporal patterns such as weekday versus weekend distinctions and seasonal patterns; (2) We propose a method that combines VAE and LSTM, enabling forecasting dynamic urban knowledge embedding; and (3) Our approach improves accuracy and responsiveness in traffic prediction models, including RNN, DCRNN, GTS, and GMAN. This study demonstrates the potential of Urban Vibrancy embeddings to advance traffic prediction and offer a more nuanced analysis of urban mobility.