Adaptive AHP and Monte Carlo Simulation for Risk-Informed High-Speed Rail Route Decision-Making Operations

Deciding on the routes for the HSR involves complex trade-offs within and across the environmental, financial, and social dimensions, all within uncertain and dynamic settings. Whenever traditional decision-making models, such as static Multi-Criteria Decision-Making (MCDM) frameworks, cannot track real-time data or adjust to the ever-changing views of the stakeholders, a new, detailed gap appears. To satisfy this need, the paper proposes a Predictive Multi-Criteria Decision-Making (PMCDM) model, which combines Analytical Hierarchy Process (AHP), Monte Carlo Simulation, and Fuzzy Logic, and presents an adaptive framework. The PMCDM model updates the weights of decisions dynamically based on real-time feedback of IoT sensors and from financial data, and models future possibilities and uncertainties through probabilistic simulations and the fuzzy inference would evolve with changing stakeholder perceptions. Our model, applied to the Californian HSR context, increased route rank by 3.5% better performance alignment margin over exclusive reach in financial risk variance by 6. These findings underscore that PMCDM may be involved in risk-informed adaptive infrastructure decision-making.