TraffNet: Learning Causality of Traffic Generation for What-if Prediction

TL;DR

TraffNet is a deep learning framework that models traffic generation mechanisms using causal features like OD demands, enabling accurate what-if traffic predictions from vehicle trajectory data.

Contribution

TraffNet introduces a novel method to learn traffic causality from trajectory data, enhancing what-if traffic prediction capabilities beyond correlation-based models.

Findings

Effective in synthetic datasets

Incorporates causal features like OD demands

Models traffic generation mechanisms

Abstract

Real-time what-if traffic prediction is crucial for decision making in intelligent traffic management and control. Although current deep learning methods demonstrate significant advantages in traffic prediction, they are powerless in what-if traffic prediction due to their nature of correla-tion-based. Here, we present a simple deep learning framework called TraffNet that learns the mechanisms of traffic generation for what-if pre-diction from vehicle trajectory data. First, we use a heterogeneous graph to represent the road network, allowing the model to incorporate causal features of traffic flows, such as Origin-Destination (OD) demands and routes. Next, we propose a method for learning segment representations, which models the process of assigning OD demands onto the road network. The learned segment represen-tations effectively encapsulate the intricate causes of traffic generation, facilitating downstream what-if traffic prediction. Finally, we conduct experiments on synthetic datasets to evaluate the effectiveness of TraffNet. The code and datasets of TraffNet is available at https://github.com/iCityLab/TraffNet.