Bridge-Centered Metapath Classification Using R-GCN-VGAE for Disaster-Resilient Maintenance Decisions

TL;DR

This paper introduces a novel graph neural network approach using R-GCN-VGAE to classify bridges' disaster-preparedness roles, aiding maintenance decisions with open data from Japanese cities.

Contribution

It presents a new methodology for constructing urban heterogeneous graphs from open data and redefines bridge roles for disaster scenarios using metapath-based classification.

Findings

Validated on three Japanese cities with 1,103 bridges.

Demonstrated the effectiveness of R-GCN-VGAE in classifying bridge roles.

Showed UMAP's superiority over t-SNE/PCA in visualization tasks.

Abstract

Daily infrastructure management in preparation for disasters is critical for urban resilience. When bridges remain resilient against disaster-induced external forces, access to hospitals, shops, and residences via metapaths can be sustained, maintaining essential urban functions. However, prioritizing bridge maintenance under limited budgets requires quantifying the multi-dimensional roles that bridges play in disaster scenarios -- a challenge that existing single-indicator approaches fail to address. We focus on metapaths from national highways through bridges to buildings (hospitals, shops, residences), constructing a heterogeneous graph with road, bridge, and building layers. A Relation-centric Graph Convolutional Network Variational Autoencoder (R-GCN-VGAE) learns metapath-based feature representations, enabling classification of bridges into disaster-preparedness categories: Supply Chain (commercial logistics), Medical Access (emergency healthcare), and Residential Protection (preventing isolation). Using OSMnx and open data, we validate our methodology on three diverse cities in Ibaraki Prefecture, Japan: Mito (697 bridges), Chikusei (258 bridges), and Moriya (148 bridges), totaling 1,103 bridges. The heterogeneous graph construction from open data enables redefining bridge roles for disaster scenarios, supporting maintenance budget decision-making. We contributed that (1) Open-data methodology for constructing urban heterogeneous graphs. (2) Redefinition of bridge roles for disaster scenarios via metapath-based classification. (3) Establishment of maintenance budget decision support methodology. (4) k-NN tuning strategy validated across diverse city scales. (5) Empirical demonstration of UMAP superiority over t-SNE/PCA for multi-role bridge visualization.