APPLYING MACHINE LEARNING TECHNIQUES TO ANALYZE FOREST FIRE IMPACTS ON SENTINEL-2 IMAGERY ACROSS UKRAINE
DOI:
https://doi.org/10.34185/1562-9945-5-162-2026-03Keywords:
burnt forest area detection, machine learning, convolutional neural networks, spectral bands, Ukraine forestsAbstract
Forest fires pose severe ecological and socio-economic threats, necessitating efficient tools for rapid damage assessment. This study presents a machine learning approach for detecting burnt forest areas in Ukraine using multispectral Sentinel-2 imagery. A new manually annotated dataset was developed for training semantic segmentation models, addressing the scarcity of open data for the region. The proposed convolutional neural network, based on an encoder–decoder architecture with Xception blocks, effectively captures spectral patterns associated with fire damage. Experiments conducted on Sentinel-2 Level-2A imagery of the Kinburn Peninsula (October 2022) demonstrate high detection performance, achieving an Intersection over Union (IoU) of 95%. The results confirm the model’s capability for accurate burnt-area mapping and highlight its potential for broader applications in regional fire monitoring and environmental management.
References
Zibtsev, Sergiy & Soshenskyi, Oleksandr & Myroniuk, Viktor & Gumeniuk, Vasyl. (2020). Wildfire in Ukraine: an overview of fires and fire management system. Ukrainian Journal of Forest and Wood Science. 11. 15-31. 10.31548/forest2020.02.015.
Barmpoutis, Panagiotis & Papaioannou, Periklis & Dimitropoulos, Kosmas & Nikos, Grammalidis. (2020). A Review on Early Forest Fire Detection Systems Using Optical Re-mote Sensing. Sensors. 20. 6442. 10.3390/s20226442.
Hu, X., Ban, Y., & Nascetti, A. (2021). Uni-Temporal Multispectral Imagery for Burned Area Mapping with Deep Learning. Remote Sensing, 13(8), 1509. https://doi.org/10.3390/rs13081509
Hnatushenko, V., Hnatushenko, V., Soldatenko, D., and Heipke, C. (2023). Enhancing the quality of CNN-based burned area detection in satellite imagery through data augmentation, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-1/W2-2023(pp.1749–1755).
Knopp, L., Wieland, M., Rättich, M., & Martinis, S. (2020). A Deep Learning Approach for Burned Area Segmentation with Sentinel-2 Data. Remote Sensing, 12(15), 2422. https://doi.org/10.3390/rs12152422.
Hnatushenko, Vik., Honcharov, O. (2024). Land cover mapping with Sentinel-2 imagery using deep learning semantic segmentation models. Information Technology and Implementa-tion, Kyiv, Ukraine, 2024, p.1-18. https://ceur-ws.org/Vol-3983/paper11.pdf
Chaurasia, Kuldeep & Nandy, Rijul & Pawar, Omkar & Singh, Ravi & Ahire, Meghana. (2021). Semantic segmentation of high-resolution satellite images using deep learning. Earth Science Informatics. 14. 1-10. 10.1007/s12145-021-00674-7.
M., Mishchenko & Vik, Hnatushenko & Anastasiia-Dzhei, Sinher. (2024). Implementation of satelite image classification using PyTorch. System technologies. 4. 102-109. 10.34185/1562-9945-4-153-2024-10.
Abdi, A. M. (2020). Land cover and land use classification performance of machine learn-ing algorithms in a boreal landscape using Sentinel-2 data. GIScience & Remote Sens-ing, 57(1), 1–20. https://doi.org/10.1080/15481603.2019.1650447
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 1251-1258). doi: 10.1109/CVPR.2017.195.
Li, M., Soltanolkotabi, M., &Oymak, S. (2020). Gradient descent with early stopping is provably robust to label noise for overparameterized neural networks. In International confer-ence on artificial intelligence and statistics (pp. 4313-4324). https://doi.org/10.48550/arXiv.1903.11680.
Carass, A., Roy, S., Gherman, A., Reinhold, J. C., Jesson, A., Arbel, T., ... &Oguz, I. (2020). Evaluating white matter lesion segmentations with refined Sørensen-Dice analysis. Scientific reports, 10(1), 8242. https://doi.org/10.1038/s41598-020-64803-w
Downloads
Published
Issue
Section
License
Copyright (c) 2026 System technologies
This work is licensed under a Creative Commons Attribution 4.0 International License.
