Federated Learning on Non-IID Environmental Images for Enhanced Wildfire Surveillance
DOI:
https://doi.org/10.22456/2175-2745.150636Keywords:
federated learning, convolutional neural networks, wildfire detection, hyperparameter optimization (TPE)Abstract
Wildfires pose serious threats to ecosystems and human safety, requiring accurate monitoring systems. This study proposes a Federated Learning (FL) approach with Convolutional Neural Networks (CNNs) for wildfire detection using two heterogeneous image datasets, keeping the data locally on each client. The federated setup simulates non-Independent and identically distributed (IID) conditions, where each client trains locally and updates are aggregated its weights to a remote server. To ensure effective performance, hyperparameter optimization for each architecture was conducted using the Tree of Parzen Estimators (TPE), allowing efficient exploration of the best training configurations. Results demonstrate that FL can handle data heterogeneity while preserving privacy, with deeper CNN architectures achieving superior performance. The findings highlight the feasibility of FL for wildfire surveillance and the ability of optimized CNNs to generalize effectively across diverse environmental conditions, supporting collaborative model training without sharing raw data.
Downloads
References
[1] SHIVAPRASAD, K. et al. Chapter 4 - forest fire and its impact on forest biodiversity. In: SAIKIA, P. et al. (Ed.). Forests for Inclusive and Sustainable Economic Growth. Elsevier, 2025. p. 37–53. ISBN 978-0-443-31406-3. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/B9780443314063000047⟩.
[2] ALAM, G. M. I. et al. Real-time detection of forest fires using firenet-cnn and explainable ai techniques. IEEE Access, v. 13, p. 51150–51181, 2025.
[3] ELEUTÉRIO, C. L. et al. Identifying wildfires with convolutional neural networks and remote sensing: application to amazon rainforest. International Journal of Remote Sensing, Taylor & Francis, v. 46, n. 7, p. 2665–2688, Apr 2025. ISSN 0143-1161. Disponível em: ⟨https://doi.org/10.1080/01431161.2024.2425119⟩.
[4] SHIMABUKURO, Y. E. et al. Assessment of burned areas during the pantanal fire crisis in 2020 using sentinel-2 images. Fire, v. 6, n. 7, 2023. ISSN 2571-6255. Disponível em: ⟨https://www.mdpi.com/2571-6255/6/7/277⟩.
[5] CAMPS-VALLS, G. et al. Artificial intelligence for modeling and understanding extreme weather and climate events. Nature Communications, v. 16, n. 1, p. 1919, Feb 2025. ISSN 2041-1723. Disponível em: ⟨https://doi.org/10.1038/s41467-025-56573-8⟩.
[6] SIDDIQUE, A. A. et al. Sustainable collaboration: Federated learning for environmentally conscious forest fire classification in green internet of things (iot). Internet of Things, v. 25, p. 101013, 2024. ISSN 2542-6605. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S2542660523003360⟩.
[7] LI, X. et al. Two-tier submodel partition framework for enhancing uav swarm robustness in forest fire detection. IEEE Transactions on Mobile Computing, p. 1–15, 2025.
[8] MCMAHAN, H. B. et al. Communication-efficient learning of deep networks from decentralized data. In: Proceedings of AISTATS. [s.n.], 2017. Disponível em: ⟨https://proceedings.mlr.press/v54/mcmahan17a.html⟩.
[9] CHENG, G. et al. Visual fire detection using deep learning: A survey. Neurocomputing, v. 596, p. 127975, 2024. ISSN 0925-2312. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S092523122400746X⟩.
[10] SATHISHKUMAR, V. E. et al. Forest fire and smoke detection using deep learning-based learning without forgetting. Fire Ecology, v. 19, n. 1, p. 9, Feb 2023. ISSN 1933-9747. Disponível em: ⟨https://doi.org/10.1186/s42408-022-00165-0⟩.
[11] BISWAS, A.; GHOSH, S. K.; GHOSH, A. Early fire detection and alert system using modified inception-v3 under deep learning framework. Procedia Computer Science, v. 218, p. 2243–2252, 2023. ISSN 1877-0509. International Conference on Machine Learning and Data Engineering. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S1877050923002004⟩.
[12] SHAMTA, I.; DEMIR, B. E. Development of a deep learning-based surveillance system for forest fire detection and monitoring using uav. PLOS ONE, Public Library of Science, v. 19, n. 3, p. 1–20, 03 2024. Disponível em: ⟨https://doi.org/10.1371/journal.pone.0299058⟩.
[13] LI, S. et al. Research on fire classification and detection models based on deep learning. In: Proceedings of the 2024 International Symposium on AI and Cybersecurity. New York, NY, USA: Association for Computing Machinery, 2025. (ISAICS ’24), p. 85–90. ISBN 9798400714429. Disponível em: ⟨https://doi-org.ez35.periodicos.capes.gov.br/10.1145/3744103.3744121⟩.
[14] SHARMA, A. et al. Fire detection in urban areas using multimodal data and federated learning. Fire, v. 7, n. 4, 2024. ISSN 2571-6255. Disponível em: ⟨https://www.mdpi.com/2571-6255/7/4/104⟩.
[15] PANNEERSELVAM, S. et al. Federated learning based fire detection method using local mobilenet. Scientific Reports, v. 14, n. 1, p. 30388, Dec 2024. ISSN 2045-2322. Disponível em: ⟨https://doi.org/10.1038/s41598-024-82001-w⟩.
[16] MOREIRA, R.; MOREIRA, L. F. R.; SILVA, F. D. O. Unleashing ai-empowered slices on mobile networks for natively cognitive service delivery. IEEE Access, p. 1–1, 2025.
[17] CHETTIAR, F. Federated multi-task ai for fire detection and risk assessment with edge deployment and explainability. In: 2025 7th Global Power, Energy and Communication Conference (GPECOM). Bochum, Germany: IEEE, 2025. p. 985–990.
[18] JAFAR, A. I. et al. FlameVision: A new dataset for wildfire classification and detection using aerial imagery. Mendeley Data, 2023. Disponível em: ⟨https://data.mendeley.com/datasets/fgvscdjsmt/4⟩.
[19] KHAN, A. et al. A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review, v. 53, n. 8, p. 5455–5516, Dec 2020. ISSN 1573-7462. Disponível em: ⟨https://doi.org/10.1007/s10462-020-09825-6⟩.
[20] RODRIGUES MOREIRA, L. F. et al. Deep learning based image classification for embedded devices: A systematic review. Neurocomputing, v. 623, p. 129402, 2025. ISSN 0925-2312. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0925231225000748⟩.
[21] KRIZHEVSKY, A.; SUTSKEVER, I.; HINTON, G. E. ImageNet Classification with Deep Convolutional Neural Networks. In: PEREIRA, F. et al. (Ed.). Advances in Neural Information Processing Systems 25. Curran Associates, Inc., 2012. p. 1097–1105. Disponível em: ⟨http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf⟩.
[22] HE, K. et al. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, NV, USA: IEEE, 2016. p. 770–778.
[23] TAN, M.; LE, Q. EfficientNet: Rethinking model scaling for convolutional neural networks. In: CHAUDHURI, K.; SALAKHUTDINOV, R. (Ed.). Proceedings of the 36th International Conference on Machine Learning. PMLR, 2019. (Proceedings of Machine Learning Research, v. 97), p. 6105–6114. Disponível em: ⟨https://proceedings.mlr.press/v97/tan19a.html⟩.
[24] IANDOLA, F. N. et al. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and <0.5mb model size. arXiv:1602.07360, 2016.
[25] RODRIGUES, L. F.; NALDI, M. C.; MARI, J. F. Comparing convolutional neural networks and preprocessing techniques for hep-2 cell classification in immunofluorescence images. Computers in Biology and Medicine, v. 116, p. 103542, 2020. ISSN 0010-4825. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S0010482519303993⟩.
[26] BERGSTRA, J. et al. Algorithms for hyper-parameter optimization. In: SHAWE-TAYLOR, J. et al. (Ed.). Advances in Neural Information Processing Systems. Curran Associates, Inc., 2011. v. 24, p. 4. Disponível em: ⟨https://proceedings.neurips.cc/paper_files/paper/2011/file/86e8f7ab32cfd12577bc2619bc635690-Paper.pdf⟩.
[27] GOODFELLOW, I.; BENGIO, Y.; COURVILLE, A. Deep Learning. Book in preparation for MIT Press. 2016. Disponível em: ⟨http://www.deeplearningbook.org⟩.
[28] BENGIO, Y. Practical recommendations for gradient-based training of deep architectures. In: Neural Networks: Tricks of the Trade: Second Edition. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. p. 437–478. ISBN 978-3-642-35289-8. Disponível em: ⟨https://doi.org/10.1007/978-3-642-35289-8_26⟩.
[29] MASTERS, D.; LUSCHI, C. Revisiting small batch training for deep neural networks. International Conference on Learning Representations (ICLR), 2018. Disponível em: ⟨https://arxiv.org/abs/1804.07612⟩.
[30] RUDER, S. An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04746, 2016. Disponível em: ⟨https://arxiv.org/abs/1609.04746⟩.
[31] MCMAHAN, B. et al. Communication-Efficient Learning of Deep Networks from Decentralized Data. In: SINGH, A.; ZHU, J. (Ed.). Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. PMLR, 2017. (Proceedings of Machine Learning Research, v. 54), p. 1273–1282. Disponível em: ⟨https://proceedings.mlr.press/v54/mcmahan17a.html⟩.
[32] RODRIGUES, L. G. F. et al. Medical image classification with privacy: Centralized and federated learning comparison. Revista de Informática Teórica e Aplicada, v. 32, n. 1, p. 180–187, Feb. 2025. Disponível em: ⟨https://seer.ufrgs.br/index.php/rita/article/view/143478⟩.
[33] BEUTEL, D. J. et al. Flower: A friendly federated learning research framework. arXiv preprint arXiv:2007.14390, 2020.
[34] NILSSON, A. et al. A performance evaluation of federated learning algorithms. In: Proceedings of the Second Workshop on Distributed Infrastructures for Deep Learning. New York, NY, USA: Association for Computing Machinery, 2018. (DIDL ’18), p. 1–8. ISBN 9781450361194. Disponível em: ⟨https://doi.org/10.1145/3286490.3286559⟩.
[35] BERGSTRA, J. et al. Hyperopt: a python library for model selection and hyperparameter optimization. Computational Science & Discovery, IOP Publishing, v. 8, n. 1, p. 014008, jul 2015. Disponível em: ⟨https://dx.doi.org/10.1088/1749-4699/8/1/014008⟩.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Elisa Ribeiro Gonçalves, Emanuel Teixeira Martins, Rodrigo Moreira, Larissa Ferreira Rodrigues Moreira
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Autorizo aos editores a publicação de meu artigo, caso seja aceito, em meio eletrônico de acordo com as regras do Public Knowledge Project.
