ST-ResGAT: Explainable Spatio-Temporal Graph Neural Network for Road Condition Prediction and Priority-Driven Maintenance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Topu, Mohsin Mahmud, Wasi, Azmine Toushik, Anik, Mahfuz Ahmed, Ahsan, MD Manjurul
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915999671910400
author Topu, Mohsin Mahmud
Wasi, Azmine Toushik
Anik, Mahfuz Ahmed
Ahsan, MD Manjurul
author_facet Topu, Mohsin Mahmud
Wasi, Azmine Toushik
Anik, Mahfuz Ahmed
Ahsan, MD Manjurul
contents Climate-vulnerable road networks require a paradigm shift from reactive, fix-on-failure repairs to predictive, decision-ready maintenance. This paper introduces ST-ResGAT, a novel Spatio-Temporal Residual Graph Attention Network that fuses residual graph-attention encoding with GRU temporal aggregation to forecast pavement deterioration. Engineered for resource-constrained deployment, the framework translates continuous Pavement Condition Index (PCI) forecasts directly into the American Society for Testing and Materials (ASTM)-compliant maintenance priorities. Using a real-world inspection dataset of 750 segments in Sylhet, Bangladesh (2021-2024), ST-ResGAT significantly outperforms traditional non-spatial machine learning baselines, achieving exceptional predictive fidelity (R2 = 0.93, RMSE = 2.72). Crucially, ablation testing confirmed the mathematical necessity of modeling topological neighbor effects, proving that structural decay acts as a spatial contagion. Uniquely, we integrate GNNExplainer to unbox the model, demonstrating that its learned priorities align perfectly with established physical engineering theory. Furthermore, we quantify classification safety: achieving 85.5% exact ASTM class agreement and 100% adjacent-class containment, ensuring bounded, engineer-safe predictions. To connect model outputs to policy, we generate localized longitudinal maintenance profiles, perform climate stress-testing, and derive Pareto sustainability frontiers. ST-ResGAT therefore offers a practical, explainable, and sustainable blueprint for intelligent infrastructure management in high-risk, low-resource geological settings.
format Preprint
id arxiv_https___arxiv_org_abs_2603_14107
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ST-ResGAT: Explainable Spatio-Temporal Graph Neural Network for Road Condition Prediction and Priority-Driven Maintenance
Topu, Mohsin Mahmud
Wasi, Azmine Toushik
Anik, Mahfuz Ahmed
Ahsan, MD Manjurul
Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Emerging Technologies
Neural and Evolutionary Computing
Climate-vulnerable road networks require a paradigm shift from reactive, fix-on-failure repairs to predictive, decision-ready maintenance. This paper introduces ST-ResGAT, a novel Spatio-Temporal Residual Graph Attention Network that fuses residual graph-attention encoding with GRU temporal aggregation to forecast pavement deterioration. Engineered for resource-constrained deployment, the framework translates continuous Pavement Condition Index (PCI) forecasts directly into the American Society for Testing and Materials (ASTM)-compliant maintenance priorities. Using a real-world inspection dataset of 750 segments in Sylhet, Bangladesh (2021-2024), ST-ResGAT significantly outperforms traditional non-spatial machine learning baselines, achieving exceptional predictive fidelity (R2 = 0.93, RMSE = 2.72). Crucially, ablation testing confirmed the mathematical necessity of modeling topological neighbor effects, proving that structural decay acts as a spatial contagion. Uniquely, we integrate GNNExplainer to unbox the model, demonstrating that its learned priorities align perfectly with established physical engineering theory. Furthermore, we quantify classification safety: achieving 85.5% exact ASTM class agreement and 100% adjacent-class containment, ensuring bounded, engineer-safe predictions. To connect model outputs to policy, we generate localized longitudinal maintenance profiles, perform climate stress-testing, and derive Pareto sustainability frontiers. ST-ResGAT therefore offers a practical, explainable, and sustainable blueprint for intelligent infrastructure management in high-risk, low-resource geological settings.
title ST-ResGAT: Explainable Spatio-Temporal Graph Neural Network for Road Condition Prediction and Priority-Driven Maintenance
topic Machine Learning
Artificial Intelligence
Computational Engineering, Finance, and Science
Emerging Technologies
Neural and Evolutionary Computing
url https://arxiv.org/abs/2603.14107