A Context-Aware Post-Earthquake Search and Rescue with ACO-RL

Abstract

Natural hazards such as earthquakes can cause significant loss of life and extensive damage worldwide each year. Search and Rescue (SAR) operations in such critical situations require an urgent need for speed and efficiency, but are also complex challenges, given their dynamic and uncertain nature. This challenge requires approaches that integrate realistic environmental modeling with intelligent decision-making. Geospatial information systems are a powerful tool that can provide robust representations of complex terrains under time-critical circumstances, and artificial intelligence techniques can simplify decision-making and optimize decision-making under time-sensitive circumstances. In addition, context-aware SAR enables the precise identification and quantification of situational parameters, allowing better tailoring of operations to the real world. A context-aware SAR framework was developed in this study to identify and estimate key parameters in rescue operations, activities, and environmental conditions, and to model the problem within a spatial information system. And by integrating ant colony optimization (ACO), which is well-suited to modeling cooperative search behaviors, with the SARSA reinforcement learning algorithm, which is well-suited to discrete decision-making environments, a hybrid method was proposed. As part of this integration, a pheromone-like reinforcement mechanism was utilized to enhance overall performance and adaptability. A comparison of this hybrid approach against a standalone ACO model revealed that it outperformed it in both operational efficiency and solution quality, underscoring its potential for real-world SAR applications.

Keywords

• Context-Aware
• Earthquake
• Search and Rescue
• Ant Colony Optimization
• Reinforcement Learning

Supporting Institution

The authors did not receive support from any organization for the submitted work.

Ethical Statement

Not applicable.

References

1. Bahadır, M., Ocak, F., & Şen, H. (2024). Determination of the development of settlements above earthquake susceptibility classes in Atakum district (Samsun/Türkiye). International Journal of Engineering and Geosciences, 9(3), 390-405. https://doi.org/10.26833/ijeg.1465072
2. Bahrami, N., Argany, M., Samani, N.N., Vafaeinejad, A.R. (2019). Designing a context-aware recommender system in the optimization of the relief and rescue. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42, 171-177.
3. Bayata, H. F., Mazlum, Y. E., Baş, F. İ., Çolak, M. A. (2025). Erzincan kent merkezinin deprem güvenliği: yapı stoğu, ulaşım ağı, toplanma ve geçici barınma alanlarının stratejik analizi. Geomatik, 10(1), 34-44. https://doi.org/10.29128/geomatik.1512396
4. Chiacchia, K.B., Houlahan, H.E. (2023). Deriving Objective Probability of Detection for MissingPerson Search: Validating Use of Effective Sweep Width and Associated Mathematical Models. Journal of Search & Rescue 6(1).
5. Civelekler, E., & Pekkan, E. (2022). The application of GIS in visualization of geotechnical data (SPT-Soil Properties): a case study in Eskisehir-Tepebaşı, Turkey. International Journal of Engineering and Geosciences, 7(3), 302-313. https://doi.org/10.26833/ijeg.980611
6. Demir, M., & Altaş, N. T. (2024). Kars kentinde deprem hasar risk potansiyeli taşıyan alanların CBS tabanlı AHP analizlerine dayalı olarak belirlenmesi. Geomatik, 9(1), 123-140. https://doi.org/10.29128/geomatik.1375650
7. Dey, A.K., & Abowd, G.D. (1999). Towards a Better Understanding of Context and Context-Awareness. Springer.
8. Eminoğlu, Y., & Tarhan, Ç. (2025). Decadal evolution of GIS in disaster management and risk assessment. International Journal of Engineering and Geosciences, 10(2), 173-196. https://doi.org/10.26833/ijeg.1544048

9. Fan, X., Zhang, X., Wang, X., Yu, X. (2023). A deep reinforcement learning model for resilient road network recovery under earthquake or flooding hazards. J Infrastruct Preserv Resil, 4, 8.
10. Fidanova, S. (2004). Convergence Proof for a Monte Carlo Method for Combinatorial Optimization Problems, Computational Science - ICCS 2004, 523–530.
11. Jeon, J., Ji, M., Lee, J., Han, K.-S., & Cho, Y. (2024). Deep Learning-Based Emergency Rescue Positioning Technology Using Matching-Map Images. Remote Sensing, 16(21), 4014.
12. Karamouz, M., Ahmadi. A., Fallahi, M. (2013). Systems Engineering. Tehran: Amirkabir University of Technology.
13. Konda, V.R., Tsitsiklis, J.N. (2000). Actor-critic algorithms. Society for Industrial and Applied Mathematics.
14. Li, X., Liang, X., Wang, X., Wang, R., Shu, L., Xu, W. (2023). Deep reinforcement learning for optimal rescue path planning in uncertain and complex urban pluvial flood scenarios, Applied Soft Computing, 144, 110543.
15. Mazidabadi, Sh. (2003). Search and Rescue in Collapsed Buildings (Drowned Removal). Tehran: Nakhl.
16. Nalini, J., Khilar, P.M. (2021). Reinforced Ant Colony Optimization for Fault Tolerant Task Allocation in Cloud Environments. Wireless Pers Commun 121, 2441–2459.
17. Radianti, J., Granmo, O., Sarshar, P., Goodwin, M., Dugdale, J., Gonzalez, J. (2015). A spatio-temporal probabilistic model of hazard- and crowd dynamics for evacuation planning in disasters. Applied Intelligence. 42(1), 3–23.
18. Rahman, M. M., Thakur, S., Ahmed, S., Yasmin, R. (2025). GIS-based development of liquefaction hazard and soil distribution maps for Dinajpur Sadar, Bangladesh. International Journal of Engineering and Geosciences, 11(2), 263-273. https://doi.org/10.26833/ijeg.1662672
19. Rasekh, A., Vafaeinejad, A. (2012). Developing a GIS based decision support system for resource allocation in earthquake search and rescue operation, Lecture Notes in Computer Science, LNCS (Part 2), 7334, 275-285.
20. Razavi-Termeh, V., Malek, M.R. (2017). Design and Implementation of a Texture-Aware Augmented Reality System, Scientific-Research Quarterly Journal of Geographic Information, 26, 104.
21. Roche, S., Propeck-Zimmermann, E. & Mericskay, B. (2013). GeoWeb and crisis management: issues and perspectives of volunteered geographic information. GeoJournal, 78, 21–40.
22. Sajjadian-Jaghargh, B.M., Vafaeinejad, A.R., Alsheikh, A.A. (2017). Designing a Texture-Aware Recommender System in Air Pollution Conditions. Geographic Information (Sepehr), 26(101), 61 – 72.
23. Samadzadegan, F., Alizadeh, A. (2011). Computational Collective Intelligence, Fundamentals and Applications. Tehran: University of Tehran.
24. Savargaonkar, H.A., Patil, H.Y., Jindal, S.K., Chandra, A., Gawas, M.A. (2024). A Scoping Review on Role of Edge Computing in Search and Rescue Operations. Wireless Pers Commun 138, 989–1026.
25. Scheele, C., Yu, M., & Huang, Q. (2021). Geographic context-aware text mining: enhance social media message classification for situational awareness by integrating spatial and temporal features. International Journal of Digital Earth, 14(11), 1721–1743.
26. Sehili, F., Madani, S. & Meschinet de Richemond, N. (2022). Vulnerabilities of cities to disaster: the 2003 earthquake in Boumerdes (Algeria). GeoJournal 87, 1759–1776.
27. Shahakar, M., Mahajan, S. A., Patil, L. (2024). Optimizing System Resources and Adaptive Load Balancing Framework Leveraging ACO and Reinforcement Learning Algorithms. J. Electrical Systems 20(1), 244 – 256.
28. Sichugova, L., & Fazilova, D. (2024). Study of the seismic activity of the Almalyk-Angren industrial zone based on lineament analysis. International Journal of Engineering and Geosciences, 9(1), 1-11. https://doi.org/10.26833/ijeg.1192118
29. Solak, H. İ., Gezgin, C., Kilinç, A. S., … Tiryakioğlu, İ. (2025). Kahramanmaraş Deprem dizisinin Erzurum ve çevresinde meydana getirdiği Kosismik Deformasyonlar ve bölgenin Sismik Parametre Analizi. Geomatik, 10(3), 375-392. https://doi.org/10.29128/geomatik.1652700
30. Stuzle T., Hoos, H. H., (2000). Max-Min Ant System. Future Generation Computer Sytems, 16(8), 889-914.
31. Sutton, R.S., & Barto, A.G. (2018). Reinforcement Learning: An Introduction (2nd ed.). MIT Press. [ISBN: 978-0262039246]
32. Sutton, R.S., Singh, S., McAllester, D. (2000). Comparing policy-gradient algorithms. IEEE Transactions on Systems, Man, and Cybernetics.
33. Tang, Z., Wang, P., Wang, Y., Wang C., Han, Y. (2022). Distributed Small-Step Path Planning and Detection Method for Post-earthquake Robot to Inspect and Evaluate Building Damage. Front. Neurorobot, 16, 915150.
34. Vafaeinejad, A., Alesheikh, A.A., Hamrah, M., Nourjou, R., Shad, R. (2009). Using GIS to Develop an Efficient Spatio-Temporal Task Allocation Algorithm to Human Groups in an Entirely Dynamic Environment, Case Study: Earthquake Rescue Teams, Lecture Notes in Computer Science, LNCS 5592, 66-78.
35. Vafaeinejad, A., Alesheikh, A.A., Roshannejad, A.A., Shad, R. (2009). A New Approach for Modeling Spatio-Temporal Events in an Earthquake Rescue Scenario, Journal of Applied Sciences, 9(3), 513-520.
36. Watkins, Ch. J.C.H., Dayan, P. (1992). Q-learning, Technical Note. 8, 279–292.
37. Yan, L., Mahmud, S., Shen, H., Foutz, N.Z., Anton, J. (2020). MobiRescue: Reinforcement Learning based Rescue Team Dispatching in a Flooding Disaster. 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS), 111-121.
38. Zhang, J., Xu, H., Liu, D., Yu, Q. (2025). Advancing Dynamic Emergency Route Optimization with a Composite Network Deep Reinforcement Learning Model. Systems, 13(2), 127.