Federated HyperFusion: Privacy-Preserving Collaborative Learning for Cross-Platform Hyperspectral and LiDAR Data Fusion
Keywords:
federated learning, hyperspectral imaging, LiDAR, data fusion, privacy preservation, collaborative learning, remote sensing, secure aggregation, differential privacy, multi-platform systemsAbstract
The integration of hyperspectral and LiDAR data has proven essential for high-resolution environmental monitoring, urban planning, and precision agriculture. However, real-world deployments increasingly involve multiple platforms—satellites, UAVs, and ground sensors—each governed by distinct institutional and privacy constraints. Traditional centralized fusion approaches require raw data to be transmitted to a single server, raising significant privacy, regulatory, and bandwidth concerns. This paper introduces Federated HyperFusion, a system-level framework that enables collaborative cross-platform learning for joint hyperspectral and LiDAR fusion without exposing sensitive raw data. We design a federated architecture where distributed clients train local models on their respective data and share only encrypted gradient updates with a central aggregation server. The framework incorporates secure aggregation mechanisms, differential privacy noise calibration, and communication-efficient compression strategies to balance accuracy, privacy, and operational cost. We analyze the structural trade-offs introduced by heterogeneous sensor resolutions, varying label availability, and non-IID data distributions across platforms. The paper further examines governance considerations such as auditability, model accountability, and data sovereignty in multi-stakeholder environments. Infrastructure aspects including edge deployment, real-time inference constraints, and energy sustainability are discussed. We also address fairness and robustness challenges arising from domain shift and biased sensor coverage. Policy implications for cross-jurisdictional data sharing and compliance with emerging privacy regulations are explored. Through this system-level perspective, Federated HyperFusion offers a viable path toward privacy-preserving, collaborative remote sensing analytics that respects institutional boundaries while achieving high-quality fused representations.
References
1. Yokoya, N., Grohnfeldt, C., & Chanussot, J. (2017). Hyperspectral and multispectral data fusion: A comparative review. IEEE Geoscience and Remote Sensing Magazine, 5(2), 28–41.
2. Ghassemian, H. (2016). A review of remote sensing image fusion methods. Information Fusion, 32, 75–89.
3. European Parliament and Council. (2016). Regulation (EU) 2016/679 of the European Parliament and of the Council (General Data Protection Regulation). Official Journal of the European Union, L 119, 1–88.
4. McMahan, B., Moore, E., Ramage, D., Hampson, S., & y Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS), 1273–1282.
5. Bonawitz, K., Ivanov, V., Kreuter, B., Marcedone, A., McMahan, H. B., Patel, S., Ramage, D., Segal, A., & Seth, K. (2017). Practical secure aggregation for privacy-preserving machine learning. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS), 1175–1191.
6. Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016). Federated learning: Strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492.
7. Sattler, F., Wiedemann, S., Müller, K. R., & Samek, W. (2020). Robust and communication-efficient federated learning from non-i.i.d. data. IEEE Transactions on Neural Networks and Learning Systems, 31(9), 3400–3413.
8. Hong, D., Yokoya, N., Chanussot, J., & Zhu, X. X. (2020). Learning to propagate labels on graphs: An iterative multitask regression framework for semi-supervised hyperspectral dimensionality reduction. ISPRS Journal of Photogrammetry and Remote Sensing, 158, 35–49.
9. Li, W., Fu, H., Yu, L., & Gong, P. (2019). Deep learning-based fusion of hyperspectral and LiDAR data for land cover classification. IEEE Geoscience and Remote Sensing Letters, 16(2), 276–280.
10. Krug, M., & Lauf, T. (2020). Privacy issues in remote sensing: A survey. Remote Sensing, 12(22), 3740.
11. Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016). Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (CCS), 308–318.
12. Diao, X., Chen, J., & Li, B. (2022). Federated learning for satellite imagery: Challenges and opportunities. IEEE Geoscience and Remote Sensing Magazine, 10(3), 8–24.
13. Qi, C. R., Yi, L., Su, H., & Guibas, L. J. (2017). PointNet++: Deep hierarchical feature learning on point sets in a metric space. In Advances in Neural Information Processing Systems (NeurIPS), 5099–5108.
14. Long, Z., Zia, A., Fu, G., Rolland, V., & Zhou, J. (2026). WS-Net: Weak-Signal Representation Learning and Gated Abundance Reconstruction for Hyperspectral Unmixing via State-Space and Weak Signal Attention Fusion. arXiv preprint arXiv:2603.09037.
15. Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated optimization in heterogeneous networks. In Proceedings of Machine Learning and Systems (MLSys), 2, 429–450.
16. Fallah, A., Mokhtari, A., & Ozdaglar, A. E. (2020). Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach. In Advances in Neural Information Processing Systems (NeurIPS), 33, 3557–3568.
17. Stich, S. U., Cordonnier, J. B., & Jaggi, M. (2018). Sparsified SGD with memory. In Advances in Neural Information Processing Systems (NeurIPS), 4447–4458.
18. Pichapati, V., Raskar, R., & Thakurta, A. (2019). AdaCliP: Adaptive clipping for private SGD. arXiv preprint arXiv:1908.07643.
19. Wang, J., Charles, Z., Xu, Z., Joshi, G., McMahan, H. B., & al. (2019). A field guide to federated optimization. arXiv preprint arXiv:1910.11852.
20. Blanchard, P., Guerraoui, R., & Stainer, J. (2017). Machine learning with adversaries: Byzantine tolerant gradient descent. In Advances in Neural Information Processing Systems (NeurIPS), 119–129.
21. Mohri, M., Sivek, G., & Suresh, A. T. (2019). Agnostic federated learning. In Proceedings of the 36th International Conference on Machine Learning (ICML), 4615–4625.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Advanced Artificial Intelligence Research
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
