Quanevac
Quantum-enhanced evacuation routing system integrating PyTorch LSTM flood prediction, Qiskit QAOA / IBM Quantum hardware, and OSRM real road mapping.
Why it exists
Severe coastal cyclones disrupt critical transit networks within hours. Classical heuristic routers struggle to assign congestion-free escape routes when storm surges submerge arterial highways. Quanevac couples temporal deep learning flood forecasts with quantum combinatorial optimization.
How it works
- Implements a PyTorch LSTM risk model predicting road segment inundation probabilities across 3 timesteps ($T=0\text{h}$, $T+12\text{h}$, $T+24\text{h}$).
- Formulates congestion-aware route assignment into a Quadratic Unconstrained Binary Optimization (QUBO) problem.
- Executes variational circuits using QAOA via Qiskit Aer simulators or real IBM Quantum hardware via `qiskit-ibm-runtime`.
- Traces real driving geometry via OSRM and visualizes evacuation corridors on dark-mode interactive maps with live storm track manipulation.
What happened
Expanded from an early hackathon prototype into a full end-to-end framework featuring real highway polylines, classical baseline fallbacks, and real QPU dispatch. Handling quantum execution latency while keeping the map interactive required careful asynchronous worker queuing.
What I'd change
I'd ingest live Doppler radar weather telemetry directly into the LSTM tensor pipeline to trigger automatic dynamic re-routing during active storm landfall.