cs.LGFeb 22, 2026

Pavement Missing Condition Data Imputation through Collective Learning-Based Graph Neural Networks

Authors: Ke Yu, Lu Gao

Organizations: School of Computing and Information, University of Pittsburgh · Department of Civil & Environmental Engineering, University of Houston

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Pavement condition data is important in providing information regarding the current state of the road network and in determining the needs of maintenance and rehabilitation treatments. However, the condition data is often incomplete due to various reasons such as sensor errors and non-periodic inspection schedules. Missing data, especially data missing systematically, presents loss of information, reduces statistical power, and introduces biased assessment. Existing methods in dealing with missing data usually discard entire data points with missing values or impute through data correlation. In this paper, we used a collective learning-based Graph Convolutional Networks, which integrates both features of adjacent sections and dependencies between observed section conditions to learn missing condition values. Unlike other variants of graph neural networks, the proposed approach is able to capture dependent relationship between the conditions of adjacent pavement sections. In the case study, pavement condition data collected from Texas Department of Transportation Austin District were used. Experiments show that the proposed model was able to produce promising results in imputing the missing data.

Figures & tables

Figure 1: Collective Learning-based GNN framework
VariableDescription
Pavement condition scoreOverall pavement condition (distress and ride quality), ranging from 1 (worst) to 100 (best).
Type of pavement surfacePavement surface type, grouped by similarity of characteristics.
Functional classTexas highway functional classification: groups and sub-groups based on roadway function.
TrafficCurrent 18-kip ESAL for the section; values stored in thousands.
Table 1: Variables used in the analysis.
Figure 2: Condition Score Map in the Case Study Database
Figure 3: Map of Different Pavement Types
Figure 4: Distribution of Different Functional Classes
Figure 5: Map of Traffic Distribution
Figure 6: Masked and Training Data
ModelAccuracy
CLGNN0.773
GCN0.725
GraphSAGE0.721
RF0.712
CART0.654
NN0.556
Table 2: Classification accuracy comparison across models.

Explore similar work

CardsList

  1. When Missingness Follows the Graph: Beyond Feature Propagation for Missing Features

    Oct 13, 2026Enrico Chialà, Francesco Ferrini, Antonio Longa +4Learning with Missing DataGraph Neural Networks

    University of Trento · Fondazione Bruno Kessler · UiT, The Arctic University of Norway +1

  2. Pattern-Aware Graph Neural Networks for Handling Missing Data

    Jul 9, 2026Minett Tran, Taehee JeongGraph Neural NetworksLearning with Missing Data

    San Jose State University

  3. Robust Graph Clustering Network for Multiple Missing Data

    Sep 25, 2026Keyuan Qiu, Renda Han, Zhen Tang +6Graph ClusteringIncomplete Data Imputation

    Northeastern University · University of Chinese Academy of Sciences · Northeast Normal University +2