Geospatial learning for large-scale transport infrastructure depth prediction

Transportation infrastructure supports the smooth mobility of humans, commodities, and services. Pavement depth measures the quality of road infrastructure through representing the thickness of road surfaces, and influences various aspects of construction projects. However, accurately modeling and predicting pavement depth has been a critical challenge due to diverse and complex factors, such as weather dynamics, traffic patterns, maintenance interventions, and environmental fluctuations. This study develops a second-dimension spatial learning (SDSL) model that integrates geospatial models and machine learning for large-scale pavement depth prediction. SDSL models are implemented in pavement prediction for eight distinct regions in Western Australia, and they are validated using the observation of pavement depth through cross-validation. Results demonstrate that the proposed SDSL models can more accurately predict large-scale pavement depth than the existing first-dimension spatial learning (FDSL) models, with 17.3% to 37.6% increase of R² values, 1.46% to 16.5% reduction of RMSE, 1.7% to 31.1% reduction of MAE and 21.0% reduction of prediction uncertainty. SDSL models enhance effective infrastructure management by accurately predicting pavement depth, essential for maintaining large-scale transportation infrastructure. The study significantly contributes to the efficient management of sustainable infrastructure assets, saving time and money.