Protecting Forests Through Intelligent Edge Computing: CBAM-UNet for Real-Time Deforestation Detection
DOI:
https://doi.org/10.59796/jcst.V16N4.2026.207Keywords:
attention, CBAM, deforestation, deep learning, edge computing, MobileNetV2, remote sensing, satellite imagery, semantic segmentation, UNetAbstract
The accelerating loss and degradation of forest ecosystems necessitate accurate and efficient monitoring approaches. This study presents a lightweight, attention-enhanced semantic segmentation framework for binary forest canopy segmentation using satellite imagery. The proposed model integrates a U-Net architecture with a MobileNetV2 encoder and a Convolutional Block Attention Module (CBAM) to improve feature representation while maintaining computational efficiency. The model is evaluated on the Bragagnolo Amazon Rainforest dataset for forest-versus-non-forest segmentation. The CBAM-enhanced model achieved a mean Intersection over Union (mIoU) of 0.6339 compared with 0.6282 for the baseline U-Net–MobileNetV2, while maintaining a comparable Dice score (0.6141 vs. 0.6187), indicating more consistent class-wise segmentation. The exported ONNX model sustained approximately 5.9 frames per second on an NVIDIA Jetson Nano while consuming under 80 MB of memory, confirming its feasibility for resource-constrained edge deployment. This work focuses strictly on binary canopy segmentation and provides insights into the trade-offs between accuracy and efficiency in lightweight deep-learning models for remote-sensing applications.
References
Albrecht, C. M., Marianno, F., & Klein, L. J. (2021). Autogeolabel: Automated label generation for geospatial machine learning [Conference presentation]. 2021 IEEE International Conference on Big Data (Big Data). IEEE, Orlando, FL, USA. https://doi.org/10.1109/BigData52589.2021.9672060
Alshehri, M., Ouadou, A., & Scott, G. J. (2024). Deep transformer-based network deforestation detection in the Brazilian Amazon using Sentinel-2 imagery. IEEE Geoscience and Remote Sensing Letters, 21, 1-5. https://doi.org/10.1109/LGRS.2024.3355104
Bhola, A., Verma, S., & Kumar, P. (2023). A comparative analysis of deep learning models for cucumber disease classification using transfer learning. Journal of Current Science and Technology, 13(1), 23-35. https://doi.org/10.14456/jcst.2023.3
Bragagnolo, L., da Silva, R. V., & Grzybowski, J. M. V. (2019). Amazon rainforest dataset for semantic segmentation [Data set]. https://doi.org/10.5281/zenodo.3233081
Chau, W. Y., Chow, J. K., Tan, T. J., Wu, J., Leung, M. L., Tan, P. S., ... & Wang, Y. H. (2024). Towards automatic urban tree inventory: Enhancing tree instance segmentation via moving object removal and a chord length-based DBH estimation approach. Computers and Electronics in Agriculture, 226, Article 109378. https://doi.org/10.1016/j.compag.2024.109378
Dascălu, A., Catalão, J., & Navarro, A. (2023). Detecting deforestation using logistic analysis and Sentinel-1 multitemporal backscatter data. Remote Sensing, 15(2), Article 290. https://doi.org/10.3390/rs15020290
de Andrade, R. B., Mota, G. L. A., & da Costa, G. A. O. P. (2022). Deforestation detection in the amazon using DeepLabv3+ semantic segmentation model variants. Remote Sensing, 14(19), Article 4694. https://doi.org/10.3390/rs14194694
Durga, P., & Karthikeyan, S. (2023). Comparative analysis for augmented decision-making applications using deep learning models. Journal of Current Science and Technology, 13(3), 791-803. https://doi.org/10.59796/jcst.V13N3.2023.2273
Fodor, G., & Conde, M. V. (2023). Rapid deforestation and burned area detection using deep multimodal learning on satellite imagery. arXiv preprint arXiv:2307.04916. https://doi.org/10.48550/arXiv.2307.04916
Gharineiat, Z., Tarsha Kurdi, F., & Campbell, G. (2022). Review of automatic processing of topography and surface feature identification LiDAR data using machine learning techniques. Remote Sensing, 14(19), Article 4685. https://doi.org/10.3390/rs14194685
Ghazal, S., Munir, A., & Qureshi, W. S. (2024). Computer vision in smart agriculture and precision farming: Techniques and applications. Artificial Intelligence in Agriculture, 13, 64-83. https://doi.org/10.1016/j.aiia.2024.06.004
Gibril, M. B. A., Shafri, H. Z. M., Shanableh, A., Al-Ruzouq, R., Wayayok, A., & Hashim, S. J. (2021). Deep convolutional neural network for large-scale date palm tree mapping from UAV-based images. Remote Sensing, 13(14), Article 2787. https://doi.org/10.3390/rs13142787
Hai, T., Wang, W., Yan, F., Liu, M., Li, C., Li, S., ... & Lv, C. (2025). A deep learning-based approach to apple tree pruning and evaluation with multi-modal data for enhanced accuracy in agricultural practices. Agronomy, 15(5), Article 1242. https://doi.org/10.3390/agronomy15051242
Haq, B., Jamshed, M. A., Ali, K., Kasi, B., Arshad, S., Kasi, M. K., ... & Ur-Rehman, M. (2024). Tech-driven forest conservation: Combating deforestation with internet of things, artificial intelligence, and remote sensing. IEEE Internet of Things Journal, 11(14), 24551-24568. https://doi.org/10.1109/JIOT.2024.3378671
Hasan, R., Farabi, S. F., Kamruzzaman, M., Bhuyan, M. K., Nilima, S. I., & Shahana, A. (2024). AI-driven strategies for reducing deforestation. American Journal of Engineering and Technology, 6(6), 6–20. https://doi.org/10.37547/tajet/Volume06Issue06-02
Jiang, L., Li, C., & Fu, L. (2025). Apple tree architectural trait phenotyping with organ-level instance segmentation from point cloud. Computers and Electronics in Agriculture, 229, Article 109708. https://doi.org/10.1016/j.compag.2024.109708
John, D., & Zhang, C. (2022). An attention-based U-Net for detecting deforestation within satellite sensor imagery. International Journal of Applied Earth Observation and Geoinformation, 107, Article 102685. https://doi.org/10.1016/j.jag.2022.102685
Kar, S., & Singh, P. K. (2025). MBTC-Net: Multimodal brain tumor classification from CT and MRI scans using deep neural network with multi-head attention mechanism. Medicine in Novel Technology and Devices, 27, Article 100382. https://doi.org/10.1016/j.medntd.2025.100382
Karaman, K., Sainte Fare Garnot, V., & Wegner, J. D. (2023). Deforestation detection in the Amazon with Sentinel-1 SAR image time series. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 10, 835-842. https://doi.org/10.5194/isprs-annals-X-1-W1-2023-835-2023
Kaselimi, M., Voulodimos, A., Daskalopoulos, I., Doulamis, N., & Doulamis, A. (2022). A vision transformer model for convolution-free multilabel classification of satellite imagery in deforestation monitoring. IEEE Transactions on Neural Networks and Learning Systems, 34(7), 3299-3307. https://doi.org/10.1109/TNNLS.2022.3144791
Li, R., Sun, G., Wang, S., Tan, T., & Xu, F. (2023). Tree trunk detection in urban scenes using a multiscale attention-based deep learning method. Ecological Informatics, 77, Article 102215. https://doi.org/10.1016/j.ecoinf.2023.102215
Liu, Y., Chen, D., Na, J., Peethambaran, J., Pfeifer, N., & Zhang, L. (2025). Segmentation of individual trees in TLS point clouds via graph optimization. IEEE Transactions on Geoscience and Remote Sensing, 63, 1-21. https://doi.org/10.1109/TGRS.2025.3567357
Noa, J., Soto, P. J., Costa, G. A. O. P., Wittich, D., Feitosa, R. Q., & Rottensteiner, F. (2021). Adversarial discriminative domain adaptation for deforestation detection. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 3, 151-158. https://doi.org/10.15488/16631
Ortega Adarme, M., Doblas Prieto, J., Queiroz Feitosa, R., & De Almeida, C. A. (2022). Improving deforestation detection on tropical rainforests using Sentinel-1 data and convolutional neural networks. Remote Sensing, 14(14), Article 3290. https://doi.org/10.3390/rs14143290
Pechprasarn, S., Wattanapermpool, O., Warunlawan, M., Homsud, P., & Akarajarasroj, T. (2023). Identification of important factors in the diagnosis of breast cancer cells using machine learning models and principal component analysis. Journal of Current Science and Technology, 13(3), 642-656. https://doi.org/10.59796/jcst.V13N3.2023.700
Phoophuangpairoj, R., & Charnkeitkong, P. (2026). A hybrid deep learning and machine learning approach for predicting aqueous solution concentrations. Journal of Current Science and Technology, 16(2), Article 173. https://doi.org/10.59796/jcst.V16N2.2026.173
Rianthakool, L., Yingdee, J., Chumsangsri, T., & Sittibal, D. (2025). Assessment of eucalyptus stem diameter estimation using terrestrial laser scanning. Current Applied Science and Technology, 25(5), Article e0264569. https://doi.org/10.55003/cast.2025.264569
Saikhammoon, R., Sungkaew, S., Thinkampaeng, S., Phumphuang, W., Kamyo, T., & Marod, D. (2023). Forest restoration in an abandoned seasonally dry tropical forest in the Mae Klong Watershed, Western Thailand. Environment and Natural Resources Journal, 21(5), 443-457. https://doi.org/10.32526/ennrj/21/20230121
Shaladi, T. A. H., Nashnosh, M. T. R., & Alkabir, M. M. (2025). Forest tree AI SDN firewall: A hierarchical architecture for adaptive network security. International Journal of Current Science Research and Review, 8(5), 2519-2530. https://doi.org/10.47191/ijcsrr/V8-i5-62
Silva, C. A., Guerrisi, G., Del Frate, F., & Sano, E. E. (2022). Near-real time deforestation detection in the Brazilian Amazon with Sentinel-1 and neural networks. European Journal of Remote Sensing, 55(1), 129-149. https://doi.org/10.1080/22797254.2021.2025154
Solórzano, J. V., Mas, J. F., Gallardo-Cruz, J. A., Gao, Y., & de Oca, A. F. M. (2023). Deforestation detection using a spatio-temporal deep learning approach with synthetic aperture radar and multispectral images. ISPRS Journal of Photogrammetry and Remote Sensing, 199, 87-101. https://doi.org/10.1016/j.isprsjprs.2023.03.017
Soni, A., & Rai, A. (2023). A systematic survey on deep learning techniques for chest disease detection using chest radiographs. Journal of Current Science and Technology, 13(2), 267-295. https://doi.org/10.59796/jcst.V13N2.2023.1744
Sugimoto, R., Kato, S., Nakamura, R., Tsutsumi, C., & Yamaguchi, Y. (2022). Deforestation detection using scattering power decomposition and optimal averaging of volume scattering power in tropical rainforest regions. Remote Sensing of Environment, 275, Article 113018. https://doi.org/10.1016/j.rse.2022.113018
Tang, J., Weeramongkolkul, M., Suwankesawong, S., Saengtabtim, K., Leelawat, N., & Wongwailikhit, K. (2024). Toward a more resilient Thailand: Developing a machine learning-powered forest fire warning system. Heliyon, 10(13), Article e34021. https://doi.org/10.1016/j.heliyon.2024.e34021
Tarazona, Y., Zabala, A., Pons, X., Broquetas, A., Nowosad, J., & Zurqani, H. A. (2021). Fusing Landsat and SAR data for mapping tropical deforestation through machine learning classification and the PVts-β non-seasonal detection approach. Canadian Journal of Remote Sensing, 47(5), 677-696. https://doi.org/10.1080/07038992.2021.1941823
Thakur, P. S., Khanna, P., Sheorey, T., & Ojha, A. (2022). Trends in vision-based machine learning techniques for plant disease identification: A systematic review. Expert Systems with Applications, 208, Article 118117. https://doi.org/10.1016/j.eswa.2022.118117
Torres, D. L., Turnes, J. N., Soto Vega, P. J., Feitosa, R. Q., Silva, D. E., Marcato Junior, J., & Almeida, C. (2021). Deforestation detection with fully convolutional networks in the Amazon Forest from Landsat-8 and Sentinel-2 images. Remote Sensing, 13(24), Article 5084. https://doi.org/10.3390/rs13245084
Vega, P. J. S., da Costa, G. A. O. P., Feitosa, R. Q., Adarme, M. X. O., de Almeida, C. A., Heipke, C., & Rottensteiner, F. (2021). An unsupervised domain adaptation approach for change detection and its application to deforestation mapping in tropical biomes. ISPRS Journal of Photogrammetry and Remote Sensing, 181, 113-128. https://doi.org/10.1016/j.isprsjprs.2021.08.026
Vorotyntsev, P., Gordienko, Y., Alienin, O., Rokovyi, O., & Stirenko, S. (2021). Satellite image segmentation using deep learning for deforestation detection [Conference presentation]. 2021 IEEE 3rd ukraine conference on electrical and computer engineering (UKRCON). IEEE, Lviv, Ukraine. https://doi.org/10.1109/UKRCON53503.2021.9575783
Wang, Y., Sun, J., & Wang, F. (2023a). Estimation of forest Diameter-at-Breast-Height: A fusion of machine learning and 3D image processing innovations. Traitement du Signal, 40(5), Article 2291. https://doi.org/10.18280/ts.400547
Wang, Z., Liu, D., Liao, X., Pu, W., Wang, Z., & Zhang, Q. (2023b). SiamHRnet-OCR: A novel deforestation detection model with high-resolution imagery and deep learning. Remote Sensing, 15(2), Article 463. https://doi.org/10.3390/rs15020463
Wu, M., Liu, S., Li, Z., Ou, M., Dai, S., Dong, X., ... & Jia, W. (2025). A review of intelligent orchard sprayer technologies: Perception, control, and system integration. Horticulturae, 11(6), Article 668. https://doi.org/10.3390/horticulturae11060668
Xiao, W., Cao, H., Tang, M., Zhang, Z., & Chen, N. (2023). 3D urban object change detection from aerial and terrestrial point clouds: A review. International Journal of Applied Earth Observation and Geoinformation, 118, Article 103258. https://doi.org/10.1016/j.jag.2023.103258
Yin, L., Zhou, Z., Zhao, W., Liao, Y., Huang, D., & Li, W. (2025). Research on identification and extraction of crop plants in plateau mountainous areas based on multi-dimensional features. International Journal of Remote Sensing, 46(1), 77-104. https://doi.org/10.1080/01431161.2024.2391080
Zhang, J., Wang, Z., Bai, L., Song, G., Tao, J., & Chen, L. (2021). Deforestation detection based on U-Net and LSTM in optical satellite remote sensing images [Conference presentation]. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE, Brussels, Belgium. https://doi.org/10.1109/IGARSS47720.2021.9554689
Zhao, H., Morgenroth, J., Pearse, G., & Schindler, J. (2023). A systematic review of individual tree crown detection and delineation with convolutional neural networks (CNN). Current Forestry Reports, 9(3), 149-170. https://doi.org/10.1007/s40725-023-00184-3
Zhao, J., Fan, S., Zhang, B., Wang, A., Zhang, L., & Zhu, Q. (2025). Research status and development trends of deep reinforcement learning in the intelligent transformation of agricultural machinery. Agriculture, 15(11), Article 1223. https://doi.org/10.3390/agriculture15111223
Zheng, J., Yuan, S., Li, W., Fu, H., Yu, L., & Huang, J. (2024). A review of individual tree crown detection and delineation from optical remote sensing images: Current progress and future. IEEE Geoscience and Remote Sensing Magazine, 13(1), 209-236. https://doi.org/10.1109/MGRS.2024.3479871
Zhou, C., Ge, X., Chang, Y., Wang, M., Shi, Z., Ji, M., ... & Lv, C. (2025). A multimodal parallel transformer framework for apple disease detection and severity classification with lightweight optimization. Agronomy, 15(5), Article 1246. https://doi.org/10.3390/agronomy15051246
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Current Science and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
