QuantumVision: Intelligent Disaster Navigation and Emergency Evacuation Management

Author

Dr. V. Srinadh, S. Sri Kavya, V. Sai, V. Guna Sekhar Reddy, K. Nandhu, G. Ganesh


Abstract

 Floods are among the most damaging hazards in coastal India. Timely estimates of rainfall, inundation and road accessibility can determine whether people reach safety. This paper presents QuantumVision, a decision-support framework integrating remote sensing, rainfall forecasting, classical and quantum machine learning, GIS analysis and flood-aware routing for Srikakulam district, Andhra Pradesh. Sentinel-1 radar backscatter, Copernicus DEM variables, multi-year station rainfall and reference flood records form the feature dataset for a 24-hour rainfall forecaster and binary flood classifier. Random Forest and XGBoost are compared with four-qubit Variational Quantum Classifier (VQC) and Quantum Neural Network (QNN) circuits using a PennyLane state-vector simulator. On a spatially separated test set of 982 samples, both tree ensembles achieved 99.80% accuracy and ROC-AUC above 0.999; VQC and QNN achieved 89.61% and 90.12% accuracy, with ROC-AUC values of 0.973 and 0.955. XGBoost gave the lowest rainfall error (MAE 4.115 mm; RMSE 8.552 mm). Predicted risk is overlaid on an OpenStreetMap road graph, where Dijkstra and A* use distance, flood and accessibility penalties. A QUBO model with simulated annealing supports selected routing and facility-allocation tasks. A React 19/FastAPI dashboard provides maps, alerts and reports. The study compares simulator-based quantum models with classical baselines and demonstrates an integrated prediction-to-navigation workflow for flood preparedness.


Keywords

Flood-Risk Assessment, Quantum Machine Learning, Sentinel-1 SAR, Digital Elevation Model, GIS, Rainfall Forecasting, Variational Quantum Classifier, Evacuation Routing, A* and Dijkstra Algorithms, Disaster Management.



Full Text:

Download Paper PDF


References


  1. Muthukumar, S. Rajesh, A. Talpallikar, and T. K. Mishra, “A systematic review of artificial intelligence frameworks for holistic disaster management,” Discover Artificial Intelligence, vol. 6, no. 1, Art. no. 308, Dec. 2026, doi: 10.1007/s44163-026-01020-w.
  2. Whyte and B. B. Haupt, “Building centaur responders: Is emergency management ready for artificial intelligence?” Disasters, vol. 50, no. 3, Art. no. e70054, Jul. 2026, doi: 10.1111/disa.70054.
  3. M. Mabina, F. M. Mashao, F. I. Mathivha, M. V. Singo, and H. Chikoore, “Deep learning and geospatial approaches for post-flood disaster damage assessment: A systematic review,” Applied Geomatics, vol. 18, no. 2, Art. no. 95, Jun. 2026, doi: 10.1007/s12518-026-00745-8.
  4. Mishra et al., “Integrating machine learning and geospatial analysis for flood hazard, vulnerability, and risk assessment in Odisha, India,” Water Resources Management, vol. 40, no. 4, Art. no. 348, Mar. 2026, doi: 10.1007/s11269-026-04709-w.
  5. Kumar, G. Pandey, and R. V. Kale, “Ensemble machine learning and deep learning framework for flood susceptibility mapping in the transboundary Rapti River Basin,” Environmental Earth Sciences, vol. 85, no. 3, Art. no. 168, Feb. 2026, doi: 10.1007/s12665-026-12912-6.
  6. Zhao, W. Feng, and X. Yi, “A spatial prediction architecture utilizing machine learning models for diverse forecasting demands in coseismic landslide scenarios,” International Journal of Disaster Risk Science, vol. 17, no. 1, pp. 45–58, Feb. 2026, doi: 10.1007/s13753-026-00749-3.
  7. G. Dcruz, A. Zolotas, N. R. Greenwood, and M. Arana-Catania, “Structured AI decision-making in disaster management,” Scientific Reports, vol. 15, no. 1, Art. no. 32093, Dec. 2025, doi: 10.1038/s41598-025-15317-w.
  8. Bao et al., “A machine learning-based prediction-to-map framework for rapid and accurate spatial flood prediction,” npj Natural Hazards, vol. 2, no. 1, Art. no. 71, Oct. 2025, doi: 10.1038/s44304-025-00122-2.
  9. Lagap et al., “Towards reliable deep learning for post-disaster damage assessment: An XAI-based evaluation,” International Journal of Disaster Risk Reduction, vol. 130, Art. no. 105839, Sep. 2025.
  10. Özen and A. Souri, “Cloud-based disaster management architecture using hybrid machine learning approach in IoT,” Multimedia Tools and Applications, vol. 83, no. 14, pp. 24105–24128, May 2024, doi: 10.1007/s11042-024-18333-6.
  11. Song, L. Hao, and W. Li, “Landslide detection using deep learning on remotely sensed images,” Applied Computing and Geosciences, vol. 27, Art. no. 100278, Sep. 2025, doi: 10.1016/j.acags.2025.100278.
  12. Ouyang et al., “Escape: An optimization method based on crowd evacuation behaviors,” Artificial Intelligence Review, vol. 58, no. 1, Art. no. 19, Jan. 2025, doi: 10.1007/s10462-024-11008-6.
  13. Sevim, Q. Guo, and E. E. Ozguven, “A simulation-based framework for leveraging shared autonomous vehicles to enhance disaster evacuations in rural regions with a focus on vulnerable populations,” Journal of Infrastructure Preservation and Resilience, vol. 6, no. 1, Art. no. 10, Mar. 2025, doi: 10.1186/s43065-025-00122-6.
  14. Visave, “Transparency in AI for emergency management: Building trust and accountability,” AI and Ethics, vol. 5, no. 4, pp. 3967–3980, Nov. 2025, doi: 10.1007/s43681-025-00692-x.
  15. Yang, Y. Wu, and S. K. K. Chow, “Deep learning method for real-time fire detection system for urban fire monitoring and control,” International Journal of Computational Intelligence Systems, vol. 17, no. 1, Art. no. 216, Aug. 2024, doi: 10.1007/s44196-024-00592-8.

 

 

Share your valuable work from Social Media Buttons