BikeVAE-GNN: A Variational Autoencoder-Augmented Hybrid Graph Neural Network for Sparse Bicycle Volume Estimation

TL;DR

BikeVAE-GNN introduces a hybrid graph neural network combined with a variational autoencoder to improve bicycle volume estimation in extremely sparse urban networks, demonstrating superior accuracy and robustness.

Contribution

The paper presents a novel dual-task framework that integrates VAE with hybrid GNNs to effectively estimate bicycle volumes in sparse networks, advancing urban transportation modeling.

Findings

Outperforms baseline GNN models in MAE, accuracy, and F1-score

Effectively handles 99% data sparsity in bicycle count data

Ablation studies confirm the importance of VAE and hybrid GNN components

Abstract

Accurate link-level bicycle volume estimation is essential for informed urban and transport planning but it is challenged by extremely sparse count data in urban bicycling networks worldwide. We propose BikeVAE-GNN, a novel dual-task framework augmenting a Hybrid Graph Neural Network (GNN) with Variational Autoencoder (VAE) to estimate Average Daily Bicycle (ADB) counts, addressing sparse bicycle networks. The Hybrid-GNN combines Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and GraphSAGE to effectively model intricate spatial relationships in sparse networks while VAE generates synthetic nodes and edges to enrich the graph structure and enhance the estimation performance. BikeVAE-GNN simultaneously performs - regression for bicycling volume estimation and classification for bicycling traffic level categorization. We demonstrate the effectiveness of BikeVAE-GNN using OpenStreetMap data and publicly available bicycle count data within the City of Melbourne - where only 141 of 15,933 road segments have labeled counts (resulting in 99% count data sparsity). Our experiments show that BikeVAE-GNN outperforms machine learning and baseline GNN models, achieving a mean absolute error (MAE) of 30.82 bicycles per day, accuracy of 99% and F1-score of 0.99. Ablation studies further validate the effective role of Hybrid-GNN and VAE components. Our research advances bicycling volume estimation in sparse networks using novel and state-of-the-art approaches, providing insights for sustainable bicycling infrastructures.