Computational optimization for low-carbon and circular pavement management at the network level

Abstract

Pavement management systems (PMS) are essential for guiding road maintenance planning and budget allocation. This study introduces an enhanced PMS framework that integrates machine learning with multi-objective optimization to identify maintenance strategies under varying budget constraints. The framework balances goals including improving pavement condition, prioritizing high-traffic segments, and reducing greenhouse gas (GHG) emissions. Results demonstrate that front-loaded investment- allocating more budget in earlier years-can lead to better long-term pavement conditions, improved cost-effectiveness, and lower life cycle emissions. We also conducted sensitivity analyses to assess the impact of different reclaimed asphalt pavement (RAP) proportions in maintenance treatments. Higher RAP usage was associated with up to a 28 % reduction in GHG emissions, while also improving network-level pavement performance, as measured by a global index integrating skid resistance, evenness, rutting, and cracking. These findings support the integration of RAP and strategic budget phasing into PMS for more sustainable and resilient infrastructure planning.