Information technologies and computer sciences

Prediction of Landmine Contamination Risk Using a Machine Learning Model Ensemble

Authors

D. I. Bratasiuk
Lviv Polytechnic National University ROR
D. V. Fedasyuk ORCID 0000-0003-3552-7454
Lviv Polytechnic National University ROR
DOI https://doi.org/10.31649/1997-9266-2026-185-2-40-47

Keywords

logistic regression machine learning model ensemble prediction

Abstract

Landmine contamination remains one of the most serious humanitarian challenges in modern Ukraine. As a result of the full-scale war, vast areas have been mined, and according to international organizations, nearly one quarter of the country’s territory is considered potentially dangerous. Traditional demining methods require substantial time and resources, creating the need for intelligent systems capable of predicting landmine risk, automatically identifying high-hazard areas, and improving demining planning. This study proposes a method for predicting landmine contamination risk using machine learning and geospatial technologies. A multilayer dataset was constructed, incorporating geospatial, socio-economic, and military features. The spatial grid covers more than 0.55 million cells sized 500×500 m, ensuring a high level of detail in mapping contaminated areas. Four baseline algorithms: Logistic Regression, Random Forest, XGBoost, and Invariant Risk Minimization were employed for data analysis. Based on these models, an ensemble architecture using the Stacked Generalization approach was implemented, where a meta-model integrates the outputs of the base learners into a unified prediction. Model performance was assessed using AUC, Precision, Recall, and F1-score metrics. Experimental results show that the ensemble outperformed the best individual model (XGBoost), confirming the effectiveness of combining heterogeneous algorithms to improve prediction accuracy. The study demonstrates that ensemble machine learning methods enable accurate and automated prediction of landmine contamination risk, enhancing demining planning and contributing to improved civilian safety.

192 125

How to Cite

[1]
“Prediction of Landmine Contamination Risk Using a Machine Learning Model Ensemble”, Вісник ВПІ, no. 2, pp. 40–47, Apr. 2026, doi: 10.31649/1997-9266-2026-185-2-40-47.

Author Biographies

D. I. Bratasiuk, Lviv Polytechnic National University

 Post-Graduate Student, of the Chair of Software Engineering

D. V. Fedasyuk, Lviv Polytechnic National University

Dr. Sc. (Eng.), Professor, Head of the Chair of Software Engineering

References

J. Cervantes, F. Garcia-Lamont, L. Rodríguez-Mazahua, and A. Lopez, “A comprehensive survey on support vector machine classification: Applications, challenges and trends,” Neurocomputing, vol. 408, pp. 189-215, 2020. https://doi.org/10.1016/j.neucom.2019.10.118 .
P. Zhang, Y. Jia, and Y. Shang, “Research and application of XGBoost in imbalanced data,” International Journal of Distributed Sensor Networks, vol. 18, no. 6, 2022. https://doi.org/10.1177/15501329221106935 .
M. Arjovsky, L. Bottou, I. Gulrajani, and D. Lopez-Paz, “Invariant Risk Minimization,” arXiv preprint arXiv:1907.02893, 2019. https://doi.org/10.48550/arXiv.1907.02893 .
E. Richardson, et al., “The receiver operating characteristic curve accurately assesses imbalanced datasets,” Patterns, vol. 5, no. 6, 2024. https://doi.org/10.1016/j.patter.2024.100994 .
P. Kosmas, W. Rafique, J. Barras, S. P. Joglekar, and D. Zheng, “Predictive Analysis of Landmine Risk,” IEEE Access,
no. 7, pp.107259-107269, 2019. https://doi.org/10.1109/ACCESS.2019.2929677 .
R. Cirillo, et al., “Desk-AId: Humanitarian Aid Desk Assessment with Geospatial AI for Predicting Landmine Areas,” arXiv preprint arXiv:2405.09444, 2024. https://doi.org/10.48550/arXiv.2405.09444 .
M. D. Rubio, S. Zeng, Q. Wang, H. Heidari, and F. Fang, “RELand: Risk Estimation of Landmines via Interpretable Invariant Risk Minimization,” ACM Journal on Computing and Sustainable Societies, vol. 2, no. 2, pp. 1-29, 2024. https://doi.org/10.1145/3648437 .
L. Sun, “Landmine Classification and Prediction Using Machine Learning Techniques,” in Proc. IEEE ICIPCA, 2025,
pp. 407-414. https://doi.org/10.1109/ICIPCA65645.2025.11138774 .
E. Vivoli, M. Bertini, and L. Capineri, “Deep learning-based real-time detection of surface landmines using optical imaging,” Remote Sensing, vol. 16, no. 4, p. 677, 2024, https://doi.org/10.3390/rs16040677 .
S. Lameri, F. Lombardi, P. Bestagini, M. Lualdi, and S. Tubaro, “Landmine detection from GPR data using convolutional neural networks,” in Proc. 25th European Signal Processing Conf., 2017, pp. 508-512, https://doi.org/10.23919/EUSIPCO.2017.8081259 .
Y. Lin, H. Dong, H. Wang, and T. Zhang, “Bayesian Invariant Risk Minimization” in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 16000-16009. https://doi.org/10.1109/CVPR52688.2022.01555 .
A. Krtalić, and M. Bajić, “Development of the TIRAMISU Advanced Intelligence Decision Support System,” European Journal of Remote Sensing, vol. 52, no. 1, pp. 40-55, 2019. https://doi.org/10.1080/22797254.2018.1550351 .
O. A. Pryshchenko, et al., “Implementation of an artificial intelligence approach to GPR systems for landmine detection,” Remote Sensing, vol. 14, no. 17, p. 4421, 2022. https://doi.org/10.3390/rs14174421 .
DeepStateMap, Frontline dynamics and military activity 2025. [Electronic resource]. Available: https://deepstatemap.live .
State Emergency Service of Ukraine (DSNS), “Interactive map of areas that may be contaminated with explosive objects,” 2025. [Electronic resource]. Available: https://mine.dsns.gov.ua/ .