Optimizing Maritime Search and Rescue Planning via Genetic Algorithms: Incorporating Civilian Vessel Collaboration
Abstract
1. Introduction
1.1. Motivation
1.2. Genetic Algorithms
2. Materials and Methods
2.1. Input Data
2.2. Genetic Algorithm Design for SRU Deployment
2.3. Greedy Algorithm
2.4. Comparison Methods
- Step 1:
- Divide the entire search area into N equally sized sub-regions.
- Step 2:
- For each subregion, generate a candidate set of search areas.
- Step 3:
- For each subregion:
- (a)
- Use a (1 + 1)-EA to deploy the largest search area, focusing on maximizing fitness.
- (b)
- Deploy the remaining search areas using a greedy algorithm explained in Section 2.2.
2.5. Local Optimization Algorithm
- (i)
- Move search area A in either the x or y direction, whichever requires less distance, until it no longer overlaps with search area B.
- (ii)
- Move search area B using the same method.
- (iii)
- Move both search areas A and B equally in opposite directions to resolve the overlap.
- (iv)
- Reduce the track spacing of search area A, thereby shrinking its coverage area but increasing its POD value.
- (v)
- Reduce the track spacing of search area B.
3. Results
3.1. Experimental Data
- Under Case 1 (civilian-only deployment), 35 SRUs are required to achieve 50% coverage and 66 SRUs for 100% coverage.
- Under Case 2 (official-first deployment), only 18 SRUs are needed for 50% coverage and 35 SRUs for 100% coverage.
- Case 1—Civilian-only: All search tasks are assigned exclusively to civilian SRUs. This represents a stress-test scenario, intended to evaluate the robustness of our algorithm in the absence of formal SAR units.
- Case 2—Official-first: Official SRUs are deployed first, and civilian SRUs are used to cover the remaining uncovered areas. This scenario reflects a more realistic operational setting, where coordination between official and civilian resources is essential.
3.2. Experimental Results
4. Discussion
- It frames SAR planning as a biomimetic optimization problem and applies a robust GA framework tailored to its structural complexities.
- It introduces a novel greedy initialization algorithm that enhances solution quality and convergence. This initialization approach was empirically validated to operate within strict SAR time limits, thus ensuring both effectiveness and practical deployability.
- It presents one of the few algorithmic studies that systematically integrate civilian SRU participation into SAR optimization, offering new directions for both computational research and real-world operational planning. Additionally, we incorporated statistical validation through t-tests, consistently obtaining p-values less than 0.001, which provides strong evidence of the significance of GA’s improvements over EAGD.
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- International Maritime Organization. International Aeronautical and Maritime Search and Rescue (IAMSAR) Manual: Volume I—Organization and Management; IMO: London, UK, 2019. [Google Scholar]
- Kratzke, T.M.; Stone, L.D.; Frost, J.R. Search and Rescue Optimal Planning System. In Proceedings of the 2010 13th International Conference on Information Fusion, Edinburgh, UK, 26–29 July 2010; pp. 1–8. [Google Scholar] [CrossRef]
- Breivik, Ø.; Allen, A.A. An operational search and rescue model for the Norwegian Sea and the North Sea. J. Mar. Syst. 2008, 69, 99–113. [Google Scholar] [CrossRef]
- Ai, B.; Li, B.; Gao, S.; Xu, J.; Shang, H. An Intelligent Decision Algorithm for the Generation of Maritime Search and Rescue Emergency Response Plans. IEEE Access 2019, 7, 155835–155850. [Google Scholar] [CrossRef]
- Dong, Y.; Ren, H.; Zhu, Y.; Tao, R.; Duan, Y.; Shao, N. A Multi-Objective Optimization Method for Maritime Search and Rescue Resource Allocation: An Application to the South China Sea. J. Mar. Sci. Eng. 2024, 12, 184. [Google Scholar] [CrossRef]
- Yoo, S.L.; Kim, K.I. Maritime accidents-based optimal rescue ship location using dynamic programming and particle swarm optimisation algorithm. J. Navig. 2024, 77, 543–558. [Google Scholar] [CrossRef]
- Cai, L.; Wu, Y.; Zhu, S.; Tan, Z.; Yi, W. Bi-level programming enabled design of an intelligent maritime search and rescue system. Adv. Eng. Inform. 2020, 46, 101194. [Google Scholar] [CrossRef]
- Chen, Z.; Liu, H.; Tian, Y.; Wang, R.; Xiong, P.; Wu, G. A Particle Swarm Optimization Algorithm Based on Time-Space Weight for Helicopter Maritime Search and Rescue Decision-Making. IEEE Access 2020, 8, 81526–81541. [Google Scholar] [CrossRef]
- Wu, J.; Wang, Z.; Song, Y.; Zhou, X.; Cheng, L. A reinforcement learning-assisted search and rescue resource allocation decision-making approach for maritime emergencies. Comput. Ind. Eng. 2025, 201, 110933. [Google Scholar] [CrossRef]
- Zeng, H.; Tong, L.; Xia, X. Multi-UAV Cooperative Coverage Search for Various Regions Based on Differential Evolution Algorithm. Biomimetics 2024, 9, 384. [Google Scholar] [CrossRef] [PubMed]
- Sun, Y.; Cao, Y.; Chen, X.; Chen, L.; Hu, Q. Marine accident black spot clustering and search and rescue resource optimization based on multiple features. Ocean Eng. 2025, 333, 121546. [Google Scholar] [CrossRef]
- Sar, A.B. Considerations on assistance and rescue at sea in the light of the increasing autonomy in shipping. Mar. Policy 2023, 153, 105639. [Google Scholar] [CrossRef]
- Cusumano, E. Emptying the sea with a spoon? Non-governmental providers of migrants search and rescue in the Mediterranean. Mar. Policy 2017, 75, 91–98. [Google Scholar] [CrossRef]
- Holland, J.H. Adaptation in Natural and Artificial Systems; The MIT Press: Cambridge, MA, USA, 1992. [Google Scholar] [CrossRef]
- Eiben, A.E.; Smith, J.E. Introduction to Evolutionary Computing; Springer: Berlin/Heidelberg, Germany, 2015. [Google Scholar]
- Song, Y.; Wang, D.; Xiong, X.; Cheng, X.; Huang, L.; Zhang, Y. The Prediction and Dynamic Correction of Drifting Trajectory for Unmanned Maritime Equipment Based on Fully Connected Neural Network (FCNN) Embedding Model. J. Mar. Sci. Eng. 2024, 12, 2262. [Google Scholar] [CrossRef]
- Córdova, P.; Flores, R.P. Hydrodynamic and Particle Drift Modeling as a Support System for Maritime Search and Rescue (SAR) Emergencies: Application to the C-212 Aircraft Accident on 2 September 2011, in the Juan Fernández Archipelago, Chile. J. Mar. Sci. Eng. 2022, 10, 1649. [Google Scholar] [CrossRef]
- Abi-Zeid, I.; Morin, M.; Nilo, O. Decision support for planning maritime search and rescue operations in Canada. In Proceedings of the 21st International Conference on Enterprise Information Systems, Heraklion, Greece, 3–5 May 2019. [Google Scholar] [CrossRef]
- International Maritime Organization. IAMSAR Manual: Volume III—Mobile Facilities; International Maritime Organization: London, UK, 2016. [Google Scholar]
- Snyder, J.P. Map Projections—A Working Manual; US Government Printing Office: Washington, DC, USA, 1987; Volume 1395.
- Xiong, W.; van Gelder, P.H.A.J.M.; Yang, K. A decision support method for design and operationalization of search and rescue in maritime emergency. Ocean Eng. 2020, 207, 107399. [Google Scholar] [CrossRef]
- United States Coast Guard. Theory of Search: A Simplified Explanation; Technical report; USCG: Washington, DC, USA, 1996. [Google Scholar]
- Golberg, D.E. Genetic algorithms in search, optimization, and machine learning. Addion Wesley 1989, 1989, 36. [Google Scholar]
- De Jong, K.A. An Analysis of the Behavior of a Class of Genetic Adaptive Systems; University of Michigan: Ann Arbor, MI, USA, 1975. [Google Scholar]
- Syswerda, G. Uniform Crossover in Genetic Algorithms. In Proceedings of the 3rd International Conference on Genetic Algorithms, San Francisco, CA, USA, 1 January 1989; pp. 2–9. [Google Scholar]
- Deb, K.; Pratap, A.; Agarwal, S.; Meyarivan, T. A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II. IEEE Trans. Evol. Comput. 2002, 6, 182–197. [Google Scholar] [CrossRef]
- Doerr, B.; Pohl, S. Run-time analysis of the (1+1) evolutionary algorithm optimizing linear functions over a finite alphabet. In Proceedings of the 14th Annual Conference on Genetic and Evolutionary Computation, Philadelphia, PA, USA, 7–11 July 2012; pp. 1317–1324. [Google Scholar] [CrossRef]
- Koester, R.J.; Stansfield, D.; Giguere, P.; Leone, J.; Frost, J. Compatibility of Land SAR Procedures with Search Theory; Technical Report CG-D-05-08; U.S. Coast Guard Research and Development Center: Groton, CT, USA, 2008. [Google Scholar]
- Hong, S.Y.; Kim, Y.H. Maximizing Particle Coverage with Fixed-Area Rectangles. In Proceedings of the International Joint Conference on Computational Intelligence (IJCCI), Rome, Italy, 13–15 November 2023; pp. 172–178. [Google Scholar] [CrossRef]
- Ruxton, G.D. The unequal variance t-test is an underused alternative to Student’s t-test and the Mann–Whitney U test. Behav. Ecol. 2006, 17, 688–690. [Google Scholar] [CrossRef]
Case | Scenario | Ratio | GA | EAGD | p-Value | ||||
---|---|---|---|---|---|---|---|---|---|
Best | Ave 1 | SD 2 | Best | Ave 1 | SD 2 | ||||
Case 1 | Scenario 1 | 0.5 | 8439.82 | 8288.54 | 65.90 | 8101.64 | 8082.55 | 16.44 | < 0.001 |
0.6 | 9129.64 | 8976.14 | 76.38 | 8790.82 | 8759.99 | 11.19 | <0.001 | ||
0.7 | 9691.76 | 9524.65 | 65.28 | 9268.87 | 9261.94 | 4.09 | < 0.001 | ||
0.8 | 10,200.80 | 10,057.40 | 66.48 | 9765.89 | 9749.18 | 8.18 | <0.001 | ||
0.9 | 10,752.20 | 10,619.60 | 60.15 | 10,335.00 | 10,326.00 | 5.48 | <0.001 | ||
1.0 | 11,460.50 | 11,264.90 | 85.63 | 10,980.80 | 10,951.30 | 32.91 | <0.001 | ||
Scenario 2 | 0.5 | 7244.98 | 7198.26 | 23.75 | 6709.86 | 6697.30 | 4.48 | <0.001 | |
0.6 | 7799.73 | 7719.80 | 23.88 | 7293.77 | 7282.74 | 19.30 | <0.001 | ||
0.7 | 8226.80 | 8112.64 | 48.06 | 7570.00 | 7557.90 | 18.14 | <0.001 | ||
0.8 | 8633.88 | 8545.65 | 35.58 | 7815.22 | 7803.50 | 12.01 | <0.001 | ||
0.9 | 9056.57 | 8990.16 | 34.08 | 8318.61 | 8290.85 | 9.08 | <0.001 | ||
1.0 | 9539.08 | 9443.64 | 37.74 | 8636.23 | 8617.21 | 5.65 | <0.001 | ||
Scenario 3 | 0.5 | 9342.44 | 9222.76 | 50.18 | 8375.92 | 8345.14 | 19.94 | <0.001 | |
0.6 | 10,308.60 | 10,194.30 | 47.14 | 9378.72 | 9365.15 | 21.57 | <0.001 | ||
0.7 | 11,303.40 | 11,206.10 | 36.94 | 10,459.50 | 10,454.50 | 3.64 | <0.001 | ||
0.8 | 12,302.60 | 12,163.90 | 55.95 | 11,487.20 | 11,473.60 | 7.83 | <0.001 | ||
0.9 | 13,205.20 | 13,090.70 | 65.50 | 12,432.90 | 12,393.20 | 23.15 | <0.001 | ||
1.0 | 13,992.40 | 13,876.70 | 53.52 | 13,297.10 | 13,083.28 | 408.57 | <0.001 | ||
Case 2 | Scenario 1 | 0.5 | 9073.02 | 9014.23 | 22.10 | 8938.47 | 8837.08 | 50.75 | <0.001 |
0.6 | 9447.08 | 9396.65 | 24.32 | 9307.12 | 9228.98 | 53.77 | <0.001 | ||
0.7 | 9746.78 | 9691.09 | 23.59 | 9609.45 | 9482.29 | 79.57 | <0.001 | ||
0.8 | 10,105.30 | 10,068.50 | 23.47 | 9998.63 | 9813.68 | 89.56 | <0.001 | ||
0.9 | 10,411.50 | 10,347.60 | 24.93 | 10,246.10 | 10,060.40 | 70.48 | <0.001 | ||
1.0 | 10,755.90 | 10,708.20 | 23.92 | 10,650.10 | 10,383.20 | 177.57 | <0.001 | ||
Scenario 2 | 0.5 | 7391.88 | 7379.82 | 7.03 | 6936.58 | 6936.36 | 0.08 | <0.001 | |
0.6 | 7537.96 | 7518.36 | 9.80 | 7130.54 | 7130.28 | 0.13 | <0.001 | ||
0.7 | 7783.76 | 7766.34 | 8.81 | 7318.68 | 7318.54 | 0.18 | <0.001 | ||
0.8 | 7909.14 | 7883.98 | 20.67 | 7492.18 | 7491.96 | 0.14 | <0.001 | ||
0.9 | 8053.76 | 8027.97 | 14.43 | 7760.88 | 7760.18 | 0.67 | <0.001 | ||
1.0 | 8194.92 | 8162.28 | 18.81 | 7883.20 | 7882.20 | 0.80 | <0.001 | ||
Scenario 3 | 0.5 | 7843.45 | 7805.61 | 22.83 | 7498.11 | 7495.10 | 4.41 | <0.001 | |
0.6 | 8192.54 | 8153.44 | 18.02 | 7887.63 | 7877.57 | 5.31 | <0.001 | ||
0.7 | 8533.79 | 8486.09 | 22.59 | 8245.69 | 8234.85 | 5.70 | <0.001 | ||
0.8 | 8941.63 | 8896.42 | 20.15 | 8689.94 | 8670.18 | 8.79 | <0.001 | ||
0.9 | 9285.73 | 9237.69 | 26.80 | 9036.05 | 9022.18 | 9.47 | <0.001 | ||
1.0 | 9638.11 | 9569.24 | 31.44 | 9314.58 | 9302.30 | 7.04 | <0.001 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Hong, S.-Y.; Kim, Y.-H. Optimizing Maritime Search and Rescue Planning via Genetic Algorithms: Incorporating Civilian Vessel Collaboration. Biomimetics 2025, 10, 588. https://doi.org/10.3390/biomimetics10090588
Hong S-Y, Kim Y-H. Optimizing Maritime Search and Rescue Planning via Genetic Algorithms: Incorporating Civilian Vessel Collaboration. Biomimetics. 2025; 10(9):588. https://doi.org/10.3390/biomimetics10090588
Chicago/Turabian StyleHong, Seung-Yeol, and Yong-Hyuk Kim. 2025. "Optimizing Maritime Search and Rescue Planning via Genetic Algorithms: Incorporating Civilian Vessel Collaboration" Biomimetics 10, no. 9: 588. https://doi.org/10.3390/biomimetics10090588
APA StyleHong, S.-Y., & Kim, Y.-H. (2025). Optimizing Maritime Search and Rescue Planning via Genetic Algorithms: Incorporating Civilian Vessel Collaboration. Biomimetics, 10(9), 588. https://doi.org/10.3390/biomimetics10090588