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

Mohsin Mahmud Topu; Azmine Toushik Wasi; Mahfuz Ahmed Anik; MD Manjurul Ahsan

cs.LGMar 14, 2026

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

Authors: Mohsin Mahmud Topu, Azmine Toushik Wasi, Mahfuz Ahmed Anik, MD Manjurul Ahsan

Organizations: Shahjalal University of Science and Technology, Sylhet, Bangladesh · University of Oklahoma, Norman, OK, United States

Abstract

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.

Figures & tables

Figure 1: Graphical Abstract. Overview of ST-ResGAT development and evaluation.

Abbreviation	Full Form
AADT	Annual Average Daily Traffic
AdaBoost	Adaptive Boosting
AI	Artificial Intelligence
ANN	Artificial Neural Networks
ASTM	American Society for Testing and Materials
CatBoost	Categorical Boosting

Table 1: Abbreviations and Acronyms

Author / Year (Model)	Application	Gaps	ST-ResGAT Contribution
Gao et al. (2024) (GraphSAGE)	GNN applied on road-network topology to model pavement deterioration using PMIS data.	Neighbour effects modeled implicitly; limited interpretability for infrastructure decisions.	Graph attention with residual projection quantifies neighbour influence and provides explainable spatial learning.
Zhou and Al-Qadi (2024) (FE-GNN surrogate)	Graph neural surrogate trained on 3D finite-element pavement response simulations.	Focuses on structural response prediction rather than network-level PCI forecasting.	Extends graph learning toward segment-level PCI prediction with temporal modeling.
Tong et al. (2025) (STGAN)	Spatio-temporal graph autoregression combining graph attention and temporal autoregressive prediction.	Feature mixing during message passing; limited interpretability for practitioners.	Residual spatial representation stabilizes feature propagation with explainable node influence.
Dang et al. (2022) (g-SDDL)	GNN + convolutional stack operating directly on raw vibration signals; stacked models for multi-damage detection without hand-engineered features.	Focused on classification/damage detection from vibration data; not designed for network-level continuous PCI forecasting or long-horizon deterioration.	Inspires raw-sensor→node feature pipeline in ST-ResGAT (use raw time-series as node inputs) and ensemble/stacking strategies for robust multi-damage segment modelling while preserving ST-ResGAT’s temporal forecasting and explainability.
Djenouri et al. (2022) (Intelligent GCN crack detection)	Image-to-graph conversion with GCN for road crack detection.	Patch-level detection; ignores network topology and temporal deterioration.	Segment-level graph representation capturing spatial propagation of pavement conditions.
Feng et al. (2023) (SCL-GCN)	Contrastive-learning enhanced GCN for LiDAR-based crack detection.	Detection-focused; lacks temporal forecasting and maintenance decision mapping.	Combines spatial GAT with temporal GRU to enable deterioration forecasting.

Table 2: Graph-based infrastructure prediction models: overview, research gaps, and how ST-ResGAT addresses them.

Figure 2: Construction of the spatio-temporal graph representation used in ST-ResGAT . Pavement inspection records collected across multiple years are first organized as node features for each road segment. THe road network topology defines adjacency relationships among segments, forming a graph structure. Each year corresponds to a graph snapshot with identical topology but updated node attributes. A temporal window of historical snapshots is then combined to create a spatio-temporal feature sequence that serves as input to the proposed ST-ResGAT model for future pavement condition prediction.

Symbol	Description
$G$	Graph representation of the road network $(V,E)$
$V$	Set of pavement segments (graph nodes)
$E$	Set of adjacency relationships between segments (edges)
$N$	Total number of pavement segments in the network
$T$	Total number of temporal observations (years)
$F$	Number of node features describing pavement properties

Table 3: Notations.

Figure 3: Architecture of the proposed Spatio-Temporal Residual Graph Attention Network (ST-ResGAT) for pavement condition prediction . The model receives temporal node features and the road network graph as input. Spatial dependencies among adjacent pavement segments are learned through multi-head Graph Attention Network (GAT) layer with residual connections to preserve original structural attributes. The resulting spatial embeddings across multiple time steps are aggregated using a Gated Recurrent Unit (GRU) to capture temporal deterioration patterns. The final spatio-temporal representation is passed through a regression head to estimate the Pavement Condition Index (PCI) for each segment, which can subsequently be used for maintenance prioritization.

PCI	Severity Rank	Recommended Action	Physical Implication
86–100	1 (Very low)	Routine monitoring	Structurally sound, No immediate action
71–85	2 (Low)	Preventive	Noticeable wear, Crack sealing required
56–70	3 (Moderate)	Corrective	Significant distress, Patching required
41–55	4 (High)	Major overlay	Severe distress, Potential base failure
0–40	5 (Critical)	Full reconstruction	Structural failure, High safety hazard

Table 4: Pavement condition index (PCI) severity and recommendations according to ASTM International (2023)

Feature	Unique	Min	Max	Mean	Std
Material	2	0	1	0.74	0.44
Agg_Type	2	0	1	0.87	0.34
Flood_Risk	3	0	2	0.93	0.86
Proximity_Quarry	2	0	1	0.26	0.44
Age_Yrs	10	2	11	6.56	2.28
Traffic_AADT	2505	5004	19977	9481.24	4039.14

Table 5: Descriptive statistics of the dataset.

Property	Value
Road segments (nodes)	750
Temporal observations	3000
Edges (adjacent connections)	1498
Time span	2021–2024
Connection type	Adjacent

Table 6: Graph structure of the road network dataset.

Type	Model	MSE ( $\downarrow$ )	RMSE ( $\downarrow$ )	MAE ( $\downarrow$ )	R 2 ( $\uparrow$ )
ML	RandomForest	19.9238	4.4636	3.4266	0.8177
	XGBoost	15.0562	3.8802	2.9291	0.8622
	AdaBoost	16.5347	4.0663	3.1908	0.8487
	CatBoost	12.1068	3.4795	2.6313	0.8892
Neural Network	MLP	12.2046	3.4935	2.6632	0.8883
Proposed model	ST-ResGAT	7.4096	2.7221	2.0886	0.9322

Table 7: Performance metrics comparison on test set

Figure 4: Actual vs. Predicted PCI scatter plot for all comparative models. The ResGAT model shows the tightest clustering along the diagonal identity line.

Panel of Figure 5 — Figure 5: (a) REC curve, further validating the high error tolerance and robustness of the ST-ResGAT predictions, (b) Taylor Diagram illustrating the standard deviation, root mean square error (RMSE), and correlation coefficient of the models relative to the ground truth observation point.

Figure 6: Longitudinal Profile of the maintenance interventions for all 750 segements (2024), illustrating the ST-ResGAT predicted spatial degradation trends against actual conditions, overlaid with ASTM D6433 action thresholds.

Figure 7: Confusion matrix of actual vs. predicted maintenance categories.

Panel of Figure 8 — Figure 8: (a) Local feature importance (Node 2), (b) Global feature importance.

Model Architecture	MSE ( $\downarrow$ )	RMSE ( $\downarrow$ )	MAE ( $\downarrow$ )	R 2 ( $\uparrow$ )
ST-ResGAT (Proposed)	5.4321	2.3307	2.0954	0.9388
ResGAT (Spatial Only)	8.9645	2.9941	2.7823	0.9184
ST-GAT (Non-Residual)	11.8453	3.4420	3.1265	0.8916
Vanilla GAT (Baseline)	14.2762	3.7784	3.4587	0.8642

Table 8: Influence of different architecture

Feature Set	MSE ( $\downarrow$ )	RMSE ( $\downarrow$ )	MAE ( $\downarrow$ )	R 2 ( $\uparrow$ )
Full Model (All Features)	5.4321	2.3307	2.0954	0.9388
No Structural Factors	10.7324	3.2760	3.0416	0.8879
No Traffic Load Data	7.8569	2.8030	2.6248	0.9211
No Condition History	11.2947	3.3603	3.1125	0.8963

Table 9: Impact of different feature categories

Category	Setting	MSE	RMSE	MAE	R 2
Temporal Window ( $T_{0}$ )	1 Year	5.6000	2.3664	2.2164	0.9288
Temporal Window ( $T_{0}$ )	2 Years	5.4321	2.3307	2.1807	0.9388
Attention Heads	1	5.5500	2.3558	2.2058	0.9298
	2	5.5000	2.3452	2.1952	0.9308
	4	5.4321	2.3307	2.1807	0.9388
	8	5.5800	2.3622	2.2122	0.9292

Table 10: Influence of various hyperparameters on ST-ResGAT

Predictive Maintenance

Predictive maintenance uses data and models to detect equipment faults, estimate degradation and remaining life, and plan timely repairs.

See all 120 papers

GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting
Oct 27, 2026Joseph Natter, Long Vu, Yifan Zhang +3Traffic Forecasting Spatiotemporal Forecasting
Kennesaw State University · Missouri State University
Efficient Traffic State Prediction With Dynamic Joint Spatio-Temporal Relation Inference
Apr 10, 2025Zhifeng Hao, Kai Hu, Juncai Zhang +2Temporal Convolutional Networks Dynamic Graph Learning
School of Cyberspace Security, Hainan University, Haikou, China
Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
May 28, 2026Amirhossein Ghaffari, Saeid Sheikhi, Ekaterina GilmanAdaptive Model Routing Mixture-of-Experts Models
Future Computing Group, University of Oulu

Oct 27, 2026J/K move · Enter open · S save

GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting

Joseph Natter, Long Vu, Yifan Zhang, Bobin Deng+2

Kennesaw State University · Missouri State University

Traffic Forecasting Spatiotemporal Forecasting Zero-Shot Time Series Forecasting Prior-Data Fitted Networks Spatiotemporal Transformers

Open paper AskPDF arXiv

Traffic forecasting requires modeling complex temporal dynamics and the spatial dependencies imposed by road topology. Supervised graph-based models achieve strong performance, but are often trained for a particular dataset and sensor graph, making deployment to new or evolving networks costly. Prior-Data Fitted Networks (PFNs) offer a zero-shot alternative by learning in-context inference from synthetic task priors, which provide an explicit mechanism for encoding domain-specific assumptions. Existing forecasting PFNs, however, do not explicitly represent the graph-structured dependencies governing traffic dynamics. To combine graph-aware traffic modeling with zero-shot adaptation, we introduce the Graph-Aware Spatiotemporal Prior-Data Fitted Network (GAS-PFN). GAS-PFN incorporates sampled road topology into its synthetic task prior through random-walk diffusion, teaching the model to learn graph-coupled dynamics during pretraining. Its co-designed inference architecture uses two mask-conditioned passes through a shared Transformer backbone to separately model sensor-specific temporal dynamics and spatiotemporal interactions among neighboring sensors before integrating their representations for prediction. This design enables GAS-PFN to use target-network structure and context without parameter updates. Across six benchmarks at the 90-minute horizon, GAS-PFN reduces MSE by 34.0% on average relative to TimePFN, its closest PFN-based predecessor. It also reduces MSE by 27.7% on average relative to four recent industry-developed general-purpose zero-shot forecasters. In this comparison, all models receive 90 minutes of contiguous recent history, and any additional context is drawn from each dataset's chronological training split. These results indicate that aligning PFN priors and inference architectures with graph structure improves in-context learning for zero-shot traffic forecasting.

Abstract

Predictive Maintenance

Explore similar work

GAS-PFN: Graph-Aware Spatiotemporal Prior-Data Fitted Networks for Zero-Shot Traffic Forecasting

Efficient Traffic State Prediction With Dynamic Joint Spatio-Temporal Relation Inference

Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting