Burned Area Segmentation Using Random Band Selection and Ensemble Encoder
DOI:
https://doi.org/10.29207/resti.v10i3.7370Keywords:
burned area segmentation, deep learning, ensemble learning, multispectral imagery, random subspace, remote sensing, U-NetAbstract
Wildfires are increasingly recognized as major environmental hazards that endanger ecosystems, human health, and economic stability. In practice, various monitoring efforts, such as hotspot detection, burned-area indices, and field inspections still depend on reliable spatial information to quantify fire impacts over large regions. Accurate segmentation of burned areas from satellite imagery plays a vital role in supporting post-disaster response and sustainable land management. This paper proposes a novel framework for burned area segmentation using multispectral imagery sampled by Random Subspace Band Selection (RSBS) with a U-Net architecture with an ensemble encoder. The RSBS module generates multiple 3-band subsets from Landsat-8 data, incorporating spectrally informative bands such as Near-Infrared (NIR) or Shortwave Infrared (SWIR). These subsets are used to train U-Net models with an ensemble of encoder backbones ResNet34, ResNet50, DenseNet121, MobileNetV2 and InceptionV4 for spectral and architectural diversity. The final predictions are aggregated using majority voting to enhance robustness and generalization. The framework is evaluated on a publicly available Indonesian burned area dataset encompassing diverse land cover types. Experimental results demonstrate that the proposed ensemble model achieves up to 0.7673 IoU, 0.8734 mIoU, and 0.8683 F1 Score, outperforming the best single-backbone model. These findings confirm that the proposed framework offers a scalable, accurate, and adaptable solution for wildfire damage assessment using satellite data.
Downloads
References
X. Hu, Y. Ban, and A. Nascetti, “Uni-temporal multispectral imagery for burned area mapping with deep learning,” Remote Sensing, vol. 13, no. 8, Art. no. 1509, 2021, doi: 10.3390/rs13081509.
D. Lee, S. Son, J. Bae, S. Park, J. Seo, D. Seo, Y. Lee, and J. Kim, “Single-temporal Sentinel-2 for analyzing burned area detection methods: A study of 14 cases in Republic of Korea considering land cover,” Remote Sensing, vol. 16, no. 5, Art. no. 884, 2024, doi: 10.3390/rs16050884.
Q. Zhang, L. Ge, R. Zhang, G. I. Metternicht, Z. Du, J. Kuang, and M. Xu, “Deep-learning-based burned area mapping using the synergy of Sentinel-1&2 data,” Remote Sensing of Environment, vol. 264, Art. no. 112575, 2021, doi: 10.1016/j.rse.2021.112575.
B. Kim, K. Lee, and S. Park, “Burned-area mapping using post-fire PlanetScope images and a convolutional neural network,” Remote Sensing, vol. 16, no. 14, Art. no. 2629, 2024, doi: 10.3390/rs16142629.
L. Knopp, M. Wieland, M. Rättich, and S. Martinis, “A deep learning approach for burned area segmentation with Sentinel-2 data,” Remote Sensing, vol. 12, no. 15, Art. no. 2422, 2020, doi: 10.3390/rs12152422.
Z. Shirvani, O. Abdi, and R. C. Goodman, “High-resolution semantic segmentation of woodland fires using residual attention UNet and time series of Sentinel-2,” Remote Sensing, vol. 15, no. 5, Art. no. 1342, 2023, doi: 10.3390/rs15051342.
D. Alkan and L. Karasaka, “Image segmentation for burned area detection from satellite imagery using the U-Net deep learning model,” Bollettino di Geofisica Teorica ed Applicata, vol. 65, no. 4, pp. 649–674, 2024, doi: 10.4430/bgo00472.
I. Mancilla-Wulff, J. Carrasco, C. Pais, A. Miranda, and A. Weintraub, “Two scalable approaches for burned-area mapping using U-Net and Landsat imagery,” arXiv preprint arXiv:2311.17368, 2023, doi: 10.48550/arXiv.2311.17368.
E. Arnaudo, L. Barco, M. Merlo, and C. Rossi, “Robust burned area delineation through multitask learning,” Communications in Computer and Information Science, vol. 2135, pp. 436–447, 2025, doi: 10.1007/978-3-031-74633-8_32.
R. Ghali and M. A. Akhloufi, “Deep learning approaches for wildland fires using satellite remote sensing data: Detection, mapping, and prediction,” Fire, vol. 6, no. 5, Art. no. 192, 2023, doi: 10.3390/fire6050192.
P. Zhang, Y. Ban, and A. Nascetti, “Total-variation regularized U-Net for wildfire burned area mapping based on Sentinel-1 C-Band SAR backscattering data,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 203, pp. 301–313, 2023, doi: 10.1016/j.isprsjprs.2023.07.024.
T. Sui, Q. Huang, M. Wu, M. Wu, and Z. Zhang, “BiAU-Net: Wildfire burnt area mapping using bitemporal Sentinel-2 imagery and U-Net with attention mechanism,” International Journal of Applied Earth Observation and Geoinformation, vol. 132, Art. no. 104034, 2024, doi: 10.1016/j.jag.2024.104034.
E. Khankeshizadeh, S. Tahermanesh, A. Mohsenifar, A. Moghimi, and A. Mohammadzadeh, “FBA-DPAttResU-Net: Forest burned area detection using a novel end-to-end dual-path attention residual-based U-Net from post-fire Sentinel-1 and Sentinel-2 images,” Ecological Indicators, vol. 167, Art. no. 112589, 2024, doi: 10.1016/j.ecolind.2024.112589.
W. Bo, J. Liu, X. Fan, T. Tjahjadi, Q. Ye, and L. Fu, “BASNet: Burned area segmentation network for real-time detection of damage maps in remote sensing images,” IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–13, Art. no. 5627913, 2022, doi: 10.1109/TGRS.2022.3197647.
S. Liu, Y. Xue, H. Chen, Y. Chen, and T. Zhan, “Segmentation of Any Fire Event (SAFE): A rapid and high-precision approach for burned area extraction using Sentinel-2 imagery,” Remote Sensing, vol. 17, no. 1, Art. no. 54, 2025, doi: 10.3390/rs17010054.
S. T. Seydi, M. Hasanlou, and J. Chanussot, “Burnt-Net: Wildfire burned area mapping with single post-fire Sentinel-2 data and deep learning morphological neural network,” Ecological Indicators, vol. 140, Art. no. 108999, 2022, doi: 10.1016/j.ecolind.2022.108999.
S. T. Seydi and M. Sadegh, “Improved burned area mapping using monotemporal Landsat-9 imagery and convolutional shift-transformer,” Measurement, vol. 216, Art. no. 112961, 2023, doi: 10.1016/j.measurement.2023.112961.
S. Balakavi, V. Vadrevu, and K. Lasko, “Exploring burnt area delineation with cross-resolution mapping: A case study of very high and medium-resolution data,” Sensors, vol. 25, no. 10, Art. no. 3009, 2025, doi: 10.3390/s25103009.
X. Xi, M. Kang, L. Dai, Y. Jing, P. Han, and C. Hou, “Identifying forest burned area using a deep learning model based on post-fire optical and SAR remote sensing images,” IEEE Access, vol. 12, pp. 188102–188113, 2024, doi: 10.1109/ACCESS.2024.3515205.
L. Liu, Y. Guo, E. Chen, Z. Li, Y. Li, Y. Liu, Q. Zhang, and B. Wang, “A lightweight Deeplab V3+ network integrating deep transitive transfer learning and attention mechanism for burned area identification,” Scientific Reports, vol. 15, Art. no. 15969, 2025, doi: 10.1038/s41598-024-66060-7.
D. Stavrakoudis and I. Gitas, “Object-based burned area mapping with extreme gradient boosting using Sentinel-2 imagery,” Journal of Geographic Information System, vol. 15, pp. 53–72, 2023, doi: 10.4236/jgis.2023.151004.
A. K. Brand and A. Manandhar, “Semantic segmentation of burned areas in satellite images using a U-Net-based convolutional neural network,” The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol. XLIII-B3-2021, pp. 47–53, 2021, doi: 10.5194/isprs-archives-XLIII-B3-2021-47-2021.
R. N. Vasconcelos et al., “Fire detection with deep learning: A comprehensive review,” Land, vol. 13, no. 10, Art. no. 1696, 2024, doi: 10.3390/land13101696.
D. M. Nelson, Y. He, and G. W. K. Moore, “Trends and applications in wildfire burned area mapping: Remote sensing data, cloud geoprocessing platforms, and emerging algorithms,” Geomatica, vol. 76, no. 1, Art. no. 100008, 2024, doi: 10.1016/j.geomat.2024.100008.
C. Lee, S. Park, T. Kim, S. Liu, M. N. Md Reba, J. Oh, and Y. Han, “Machine learning-based forest burned area detection with various input variables: A case study of South Korea,” Applied Sciences, vol. 12, no. 19, Art. no. 10077, 2022, doi: 10.3390/app121910077.
M. M. Pinto, R. Libonati, R. M. Trigo, I. F. Trigo, and C. C. DaCamara, “A deep learning approach for mapping and dating burned areas using temporal sequences of satellite images,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 160, pp. 260–274, 2020, doi: 10.1016/j.isprsjprs.2019.12.014.
S. Sivanandham and D. B. Gunaseelan, “Development of an ensembled meta-deep learning model for semantic road-scene segmentation in an unstructured environment,” Applied Sciences, vol. 12, no. 23, Art. no. 12214, 2022, doi: 10.3390/app122312214.
N. Soucy and S. Y. Sekeh, “CEU-Net: Ensemble semantic segmentation of hyperspectral images using clustering,” Journal of Big Data, vol. 10, no. 1, Art. no. 43, 2023, doi: 10.1186/s40537-023-00718-3.
I. Dimitrovski, V. Spasev, S. Loshkovska, and I. Kitanovski, “U-Net ensemble for enhanced semantic segmentation in remote sensing imagery,” Remote Sensing, vol. 16, no. 12, Art. no. 2077, 2024, doi: 10.3390/rs16122077.
Y. Prabowo, A. D. Sakti, K. A. Pradono, Q. Amriyah, F. H. Rasyidy, I. Bengkulah, K. Ulfa, D. S. Candra, M. T. Imdad, and S. Ali, “Deep learning dataset for estimating burned areas: Case study, Indonesia,” Data, vol. 7, no. 6, Art. no. 78, 2022, doi: 10.3390/data7060078.
S. Deegalla, K. Walgama, P. Papapetrou, and H. Boström, “Random subspace and random projection nearest neighbor ensembles for high dimensional data,” Expert Systems with Applications, vol. 191, Art. no. 116078, 2022, doi: 10.1016/j.eswa.2021.116078.
O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in Proc. MICCAI, 2015, pp. 234–241, doi: 10.1007/978-3-319-24574-4_28.
J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in Proc. CVPR, 2009, pp. 248–255, doi: 10.1109/CVPR.2009.5206848.
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. CVPR, 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proc. CVPR, 2017, pp. 4700–4708, doi: 10.1109/CVPR.2017.243.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in Proc. CVPR, 2018, pp. 4510–4520, doi: 10.1109/CVPR.2018.00474.
C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi, “Inception-v4, Inception-ResNet and the impact of residual connections on learning,” in Proc. AAAI Conf. Artif. Intell., vol. 31, no. 1, pp. 4278–4284, 2017, doi: 10.1609/aaai.v31i1.11231.
Downloads
Published
Issue
Section
License
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
