Abstract

Wildfires cause unpredictable spread and panic-driven congestion, posing severe challenges to evacuation planning. We present RESCUE (Routing under Evolving Stochastic Congestion and Uncertain Spread in Wildfire Emergencies), a dynamic, risk-aware framework that models the road network as a time-varying weighted graph. RESCUE operates in two stages: (i) a preprocessing phase integrating fire forecasts, traffic density, and distance to assign edge weights, and (ii) a real-time routing phase that adaptively updates paths using a multi-granular strategy distinguishing macro-level disruptions (e.g., rapid spread) from micro-level changes (e.g., local congestion). Two stochastic edge-cost functions are introduced: the Edge-Fire Risk Function (EFRF), estimating road inaccessibility from the fire's rate-of-spread, and a Beta cumulative distribution modeling evacuee speed under stress, combined with the Bureau of Public Roads (BPR) model for delay estimation. Formulated as a multi-objective shortest-path problem, on real-world networks, RESCUE reduces travel distance, fire risk, and congestion delay by, and over A∗-based routing. Compared to D∗, it achieves, and reductions in these metrics.

Department(s)

Computer Science

Publication Status

Free Access

Comments

National Science Foundation, Grant OAC-2104078

Keywords and Phrases

congestion modeling; dynamic graphs; emergency response; multi-objective optimization; stochastic routing; Wildfire evacuation

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2026 Association for Computing Machinery, All rights reserved.

Publication Date

05 Jan 2026

Download

Full Text Link

Share

 
COinS