Bridging Stochastic, Robust, and Neutrosophic Paradigms for Hurricane Evacuation Under Compound Uncertainty: A Six–Layer Methodological Synthesis

Hurricane evacuation planning under uncertainty requires integrating decisions across multiple spatial and temporal scales, yet the literature addresses demand stochasticity, temporal robustness, and computational tractability largely in isolation. This paper develops a unified optimization framework organized around six progressive layers: meteorological scenario generation, deterministic and stochastic network flow planning, vehicle scheduling with origin-based decomposition, classical robust temporal protection, neutrosophic adaptive robust optimization with scenario-anchored uncertainty sets, and computational complexity characterization. An integrated critical review of 337 Scopus-indexed publications (2022–2026) identifies persistent methodological gaps that motivate each architectural layer. The framework couples two-stage stochastic programming with budget-constrained robust optimization, affine decision rules, and neutrosophic indeterminacy calibration within a single operational pipeline. Validation on a georeferenced Caribbean network demonstrates a 94% reduction in binary variables through origin-based decomposition and end-to-end execution in under four minutes, with a sensitivity analysis showing that neutrosophic budget calibration reduces the price of robustness from 24.8% to 2.8%.