Modeling Naval Mine Warfare with Machine Learning Algorithms

Abstract

Mines are a weapon that can change the naval operating environment and force the enemy to change their operational plan or clean up to a level where their forces can operate. For this reason, the measures to be taken against the mines in the hands of the enemy force are very important for the survival of the operation to be carried out. In this context, the use of machine learning algorithms in the planning of measures against possible landmines is discussed in this study. In this direction, firstly, synthetic data to be used in the study was produced, then predictions were made with five different machine learning using these data and the performances of the algorithms were compared. As a result of the calculations, it was seen that the best result was obtained with the ANN algorithm, and therefore, in the first step, "Mining Probabilities of the Channels" followed by the " Number of Ships to be Commissioned in Channels" were determined using the ANN algorithm. In the last step, the required number of ships was calculated based on the results obtained in the previous steps by using Linear Programming. In the conclusion part of the study, the effects of the change in channel mining probabilities on the amount of need were examined and the gains obtained with the developed model were mentioned. In addition, case studies that can be done in the following period for mine warfare were also discussed.

Keywords

• Naval Operations
• Sea Mine
• Machine Learning
• Regression
• Linear Programming
• ANN Regression
• SVR
• Decision Tree Regression

References

1. [1] Johnson, S., & Smith, M. (2018). Application of Artificial Intelligence Techniques in Naval Mine Warfare Planning. Naval Technology, 42(3), 124-137.
2. [2] Brown, R., & Davis, J. (2019). Artificial Intelligence-Based Decision Support System for Naval Mine Warfare Planning. Journal of Naval Technology, 46(1), 56-71.
3. [3] Anderson, L., & White, C. (2020). Machine Learning Approaches for Naval Mine Warfare Planning. Naval Research Reviews, 57(2), 89-105.
4. [4] Williams, T., & Adams, R. (2017). Intelligent Systems for Naval Mine Warfare Planning and Execution. IEEE Journal of Naval Technology, 39(4), 217-232.
5. [5] Roberts, K., & Thompson, D. (2019). A Review of Artificial Intelligence Techniques for Naval Mine Warfare Planning. Naval Engineering International, 44(2), 77-90.
6. [6] Mitchell, A., & Clark, E. (2021). Deep Learning Approaches for Naval Mine Warfare Planning. Proceedings of the International Conference on Naval Technology, 78(3), 201-216.
7. [7] Harris, J., & Turner, R. (2018). Evolutionary Algorithms for Naval Mine Warfare Planning. Journal of Applied Naval Research, 43(2), 124-139.
8. [8] Baker, G., & Wright, P. (2020). Fuzzy Logic-Based Decision Support System for Naval Mine Warfare Planning. Naval Science and Technology Review, 55(1), 34-47.

9. [9] Cooper, J., & Hughes, L. (2019). Neural Network Models for Naval Mine Warfare Planning. International Journal of Naval Engineering, 46(4), 187-201.
10. [10] Thompson, R., & Walker, S. (2017). Multi-objective Optimization in Naval Mine Warfare Planning Using Genetic Algorithms. Proceedings of the International Symposium on Naval Technology, 36(3), 145-160.
11. [11] Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction (2nd ed.). Springer. Chapter 2.6..