# Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane Graphs

## TL;DR

This paper develops neural attention-based deep learning models to predict traffic dynamics at the lane level, effectively capturing lane interactions and improving prediction accuracy in complex road networks.

## Contribution

It introduces an attention mechanism tailored for lane-to-lane relationships, enhancing traffic prediction models and demonstrating transferability to complex networks.

## Key findings

- Attention improves prediction accuracy by leveraging lane relationships.
- Encoding lane relationship types significantly boosts model performance.
- Transfer learning to complex networks shows performance degradation due to new traffic behaviors.

## Abstract

Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear spatiotemporal physics problem of vehicle traffic dynamics. We consider problems of estimating macroscopic quantities (e.g., the queue at an intersection) at a lane level. First-principles modeling at the lane scale has been a challenge due to complexities in modeling social behaviors like lane changes, and those behaviors' resultant macro-scale effects. Following domain knowledge that upstream/downstream lanes and neighboring lanes affect each others' traffic flows in distinct ways, we apply a form of neural attention that allows the neural network layers to aggregate information from different lanes in different manners. Using a microscopic traffic simulator as a testbed, we obtain results showing that an attentional neural network model can use information from nearby lanes to improve predictions, and, that explicitly encoding the lane-to-lane relationship types significantly improves performance. We also demonstrate the transfer of our learned neural network to a more complex road network, discuss how its performance degradation may be attributable to new traffic behaviors induced by increased topological complexity, and motivate learning dynamics models from many road network topologies.