Q-RESTORE: quantum-driven framework for resilient and equitable transportation network restoration

Post-disaster transportation network restoration is essential for maintaining mobility, accessibility, and equitable access to critical services following infrastructure disruptions; however, existing restoration approaches either rely on simplified linear approximations that fail to capture nonlinear traffic interactions or require computationally expensive nonlinear optimization methods unsuitable for rapid decision-making. To address this gap, this study proposes Q-RESTORE, a hybrid quantum optimization framework that integrates constrained quadratic modeling (CQM), user-equilibrium traffic assignment, accessibility-based resilience metrics, and equity-sensitive restoration objectives within a unified restoration framework. Comparative analyses against a linearized Gurobi benchmark and a nonlinear Genetic Algorithm (GA) demonstrate that the proposed hybrid quantum framework consistently produces substantially better nonlinear recovery performance than the linearized benchmark while maintaining runtimes of approximately 1–2 seconds, compared to more than 60 seconds for the GA. The results further show that preserving nonlinear restoration interactions significantly improves recovery deficiency reduction and accessibility equity under realistic transportation network conditions. These findings demonstrate the feasibility and potential of hybrid quantum optimization for computationally efficient, equity-aware, and resilient post-disaster transportation recovery planning.