Missing Pavement Performance Data Imputation Using Graph Neural Networks

Abstract

Pavement condition data is important for providing information on the current state of the network and determining the needs of preventive maintenance or rehabilitation treatments. However, the condition data set is often incomplete for various reasons such as measurement errors and non-periodic inspection intervals. Missing data, especially when missing systematically, presents loss of information, reduces statistical power, and introduces biased assessment. Existing practices in pavement management systems (PMS) usually discard entire cases with missing data or impute it through data correlation. This paper proposes a graph-based deep learning framework, convolutional graph neural networks, to tackle the missing data problem in PMS. Unlike other variants of neural networks, the proposed approach is able to capture the spatio-temporal relationship in data and to learn and reconstruct the missing data by combining information among neighboring sections. In the case study, pavement condition data from 4,446 sections managed by Texas Department of Transportation were used. Experiments show that the proposed model was able to outperform standard machine learning models when imputing the missing data.

Considering the Spatial Structure of the Road Network in Pavement Deterioration Modeling

“…Zhou et al ( 12 ) also applied the LSTM model to predict an asphalt concrete (AC) pavement international roughness index (IRI), utilizing datasets extracted from the Long-Term Pavement Performance (LTPP) database. Gao et al ( 13 ) introduced a convolutional graph neural network (GNN) for imputing missing pavement condition data in pavement management systems, outperforming standard machine learning models.…”