Hybrid Deep Learning for Channel Estimation and Tracking in RIS-Assisted UAV Wireless Communications

Channel estimation in reconfigurable intelligent surface (RIS)-aided unmanned aerial vehicle (UAV) systems is severely hindered by high-dimensional cascaded channels, UAV-induced fast time variation, and the passive nature of RIS elements that precludes conventional pilot-based acquisition. This paper proposes a hybrid deep learning framework synergistically combining convolutional neural networks (CNN) for spatial feature extraction with bidirectional long short-term memory (BiLSTM) networks for temporal sequence modeling.
The architecture hierarchically decomposes estimation into: CNNs extracting multipath spatial patterns from canonical K-path representations, then BiLSTMs modeling temporal evolution across sequential snapshots, effectively capturing spatial-temporal coupling in RIS-UAV propagation.
We develop comprehensive methodology with DeepMIMO ray-tracing generation, K=10 path selection achieving >95% channel power capture, and systematic preprocessing. Extensive evaluation across SNR -10 to 30 dB demonstrates hybrid CNN-BiLSTM achieves NRMSE 0.018 at 30 dB (21.7% improvement over CNN, 33.3% over BiLSTM, 50-60% over LS/LMMSE/CS-OMP), correlation 0.989, SSIM 0.985, with 3.5M FLOPs and 2.0 ms inference on NVIDIA Tesla V100 enabling real-time operation within 5-10 ms UAV channel coherence time. This validates the hybrid approach as an enabling technology for next-generation 6G aerial communications requiring ultra-reliable, low-latency channel acquisition in highly dynamic three-dimensional environments.

Reconfigurable Intelligent Surface, Unmanned Aerial Vehicle, Channel Estimation, Deep Learning, CNN, BiLSTM, Spatial-Temporal Learning, 6G Wireless, Ray Tracing

1. ITU-R. (2023) IMT VisionFramework and Overall Objectives of the Future Development of IMT for 2030 and Beyond. Recommendation ITU-R M.2083-0, International Telecommunication Union, Geneva. https://www.itu.int/rec/R-REC-M.2083 [Google Scholar] [Crossref]

2. Zeng, Y., Wu, Q. and Zhang, R. (2019) Accessing from the Sky: A Tutorial on UAV Communications for 5G and Beyond. Proceedings of the IEEE, 107, 2327-2375. http://dx.doi.org/10.1109/JPROC.2019.2952892 [Google Scholar] [Crossref]

3. Mozaffari, M., Saad, W., Bennis, M., Nam, Y.-H. and Debbah, M. (2019) A Tutorial on UAVs for Wireless Networks: Applications, Challenges, and Open Problems. IEEE Communications Surveys & Tutorials, 21, 2334-2360. http://dx.doi.org/10.1109/COMST.2019.2902862 [Google Scholar] [Crossref]

4. Basar, E., Di Renzo, M., De Rosny, J., Debbah, M., Alouini, M.-S. and Zhang, R. (2019) Wireless Communications through Reconfigurable Intelligent Surfaces. IEEE Access, 7, 116753-116773. http://dx.doi.org/10.1109/ACCESS.2019.2935192 [Google Scholar] [Crossref]

5. Di Renzo, M., Zappone, A., Debbah, M., Alouini, M.-S., Yuen, C., de Rosny, J. and Tretyakov, S. (2020) Smart Radio Environments Empowered by Reconfigurable Intelligent Surfaces: How It Works, State of Research, and the Road Ahead. IEEE Journal on Selected Areas in Communications, 38, 2450-2525. http://dx.doi.org/10.1109/JSAC.2020.3007211 [Google Scholar] [Crossref]

6. Wu, Q. and Zhang, R. (2020) Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive Beamforming. IEEE Transactions on Wireless Communications, 18, 5394-5409. http://dx.doi.org/10.1109/TWC.2019.2936025 [Google Scholar] [Crossref]

7. Li, S., Duo, B., Yuan, X., Liang, Y.-C. and Di Renzo, M. (2020) Reconfigurable Intelligent Surface Assisted UAV Communication: Joint Trajectory Design and Passive Beamforming. IEEE Wireless Communications Letters, 9, 716-720. http://dx.doi.org/10.1109/LWC.2020.2966705 [Google Scholar] [Crossref]

8. You, C., Zheng, B. and Zhang, R. (2021) Channel Estimation and Passive Beamforming for Intelligent Reflecting Surface: Discrete Phase Shift and Progressive Refinement. IEEE Journal on Selected Areas in Communications, 38, 2604-2620. http://dx.doi.org/10.1109/JSAC.2020.3007060 [Google Scholar] [Crossref]

9. Pang, X., Zhao, N., Tang, J., Wu, C., Niyato, D. and Wong, K.-K. (2021) IRS-Assisted Secure UAV Transmission via Joint Trajectory and Beamforming Design. IEEE Transactions on Communications, 70, 1140-1152. http://dx.doi.org/10.1109/TCOMM.2021.3136563 [Google Scholar] [Crossref]

10. Ge, L., Dong, Y., Wang, H. and Liang, Y.-C. (2021) Joint Beamforming and Trajectory Optimization for Intelligent Reflecting Surface-Assisted UAV Communications. IEEE Access, 9, 78702-78712. http://dx.doi.org/10.1109/ACCESS.2021.3083404 [Google Scholar] [Crossref]

11. Mishra, D. and Johansson, H. (2019) Channel Estimation and Low-Complexity Beamforming Design for Passive Intelligent Surface Assisted MISO Wireless Energy Transfer. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, 12-17 May 2019, 4659-4663. http://dx.doi.org/10.1109/ICASSP.2019.8683780 [Google Scholar] [Crossref]

12. Wang, P., Fang, J., Duan, H. and Li, H. (2020) Compressed Channel Estimation for Intelligent Reflecting Surface-Assisted Millimeter Wave Systems. IEEE Signal Processing Letters, 27, 905-909. http://dx.doi.org/10.1109/LSP.2020.2998357 [Google Scholar] [Crossref]

13. Gizzini, A.K., Chafii, M., Nimr, A., Fettweis, G. and Shubair, R.M. (2021) Deep Learning-Based Channel Estimation for IRS-Aided Communication Systems. Proceedings of IEEE Global Communications Conference (GLOBECOM), Madrid, 7-11 December 2021, 1-6. http://dx.doi.org/10.1109/GLOBECOM46510.2021.9685404 [Google Scholar] [Crossref]

14. Hu, X., Masouros, C. and Wong, K.-K. (2021) Two-Timescale Channel Estimation for Reconfigurable Intelligent Surface Aided Wireless Communications. IEEE Transactions on Communications, 69, 7736-7747. http://dx.doi.org/10.1109/TCOMM.2021.3072729 [Google Scholar] [Crossref]

15. Ardah, K., Gherekhloo, S., de Almeida, A.L.F. and Haardt, M. (2021) TRICE: A Channel Estimation Framework for RIS-Aided Millimeter-Wave MIMO Systems. IEEE Signal Processing Letters, 28, 513-517. http://dx.doi.org/10.1109/LSP.2021.3059363 [Google Scholar] [Crossref]

16. Wei, L., Huang, C., Alexandropoulos, G.C. and Yuen, C. (2021) Parallel Factor Decomposition Channel Estimation in RIS-Assisted Multi-User MISO Communication. Proceedings of IEEE International Conference on Communications (ICC), Montreal, 14-23 June 2021, 1-6. http://dx.doi.org/10.1109/ICC42927.2021.9500502 [Google Scholar] [Crossref]

17. Jensen, T.L. and de Carvalho, E. (2021) An Optimal Channel Estimation Scheme for Intelligent Reflecting Surfaces Based on a Minimum Variance Unbiased Estimator. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, 6-11 June 2021, 4555-4559. http://dx.doi.org/10.1109/ICASSP39728.2021.9414748 [Google Scholar] [Crossref]

18. Ye, H., Li, G.Y. and Juang, B.-H. (2018) Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems. IEEE Wireless Communications Letters, 7, 114-117. http://dx.doi.org/10.1109/LWC.2017.2757490 [Google Scholar] [Crossref]

19. O'Shea, T. and Hoydis, J. (2017) An Introduction to Deep Learning for the Physical Layer. IEEE Transactions on Cognitive Communications and Networking, 3, 563-575. http://dx.doi.org/10.1109/TCCN.2017.2758370 [Google Scholar] [Crossref]

20. Jiang, P., Wen, C.-K., Jin, S. and Li, G.Y. (2020) Deep Learning for Massive MIMO CSI Feedback in Blockchain-Enabled Internet of Things. IEEE Internet of Things Journal, 7, 10174-10187. http://dx.doi.org/10.1109/JIOT.2020.2996207 [Google Scholar] [Crossref]

21. Gizzini, A.K., Chafii, M., Ehsanfar, S., Nimr, A. and Fettweis, G. (2022) CNN Aided Weighted Interpolation for Channel Estimation in IRS Assisted MIMO Systems. Proceedings of IEEE 95th Vehicular Technology Conference (VTC2022-Spring), Helsinki, 19-22 June 2022, 1-6. http://dx.doi.org/10.1109/VTC2022-Spring54318.2022.9860654 [Google Scholar] [Crossref]

22. Samuel, N., Diskin, T. and Wiesel, A. (2019) Deep MIMO Detection. IEEE Transactions on Signal Processing, 67, 1352-1366. http://dx.doi.org/10.1109/TSP.2018.2887192 [Google Scholar] [Crossref]

23. Yang, H., Xiong, Z., Zhao, J., Niyato, D., Xiao, L. and Wu, Q. (2023) Deep Reinforcement Learning-Based Intelligent Reflecting Surface for Secure Wireless Communications. IEEE Transactions on Wireless Communications, 20, 375-388. http://dx.doi.org/10.1109/TWC.2020.3024860 [Google Scholar] [Crossref]

24. Alkhateeb, A., Sam, A., Alex, A., Maeng, S.J. and Ayach, O.E. (2019) DeepMIMO: A Generic Deep Learning Dataset for Millimeter Wave and Massive MIMO Applications. arXiv preprint arXiv:1902.06435. http://dx.doi.org/10.48550/arXiv.1902.06435 [Google Scholar] [Crossref]

25. Hu, X., Zhong, C., Zhang, Y., Chen, X. and Zhang, Z. (2020) Location Information Aided Multiple Intelligent Reflecting Surface Systems. IEEE Transactions on Communications, 68, 7948-7962. http://dx.doi.org/10.1109/TCOMM.2020.3020577 [Google Scholar] [Crossref]

26. Ge, L., Dong, Y., Wang, H. and Liang, Y.-C. (2021) Joint Beamforming and Trajectory Optimization for Intelligent Reflecting Surface-Assisted UAV Communications. IEEE Access, 9, 78702-78712. http://dx.doi.org/10.1109/ACCESS.2021.3083404 [Google Scholar] [Crossref]

27. Ma, W., Qi, C., Zhang, Z. and Cheng, J. (2022) Sparse Channel Estimation and Hybrid Precoding Using Deep Learning for Millimeter Wave Massive MIMO. IEEE Transactions on Communications, 70, 1998-2011. http://dx.doi.org/10.1109/TCOMM.2022.3142214 [Google Scholar] [Crossref]

28. Liu, T., Wang, C.-X., Huang, J., Zhang, X. and Yuan, J. (2021) 3-D Non-Stationary Wideband GBSM for Low-Altitude UAV-to-Ground V2V MIMO Channels. IEEE Internet of Things Journal, 8, 4954-4968. http://dx.doi.org/10.1109/JIOT.2020.3029230 [Google Scholar] [Crossref]

29. Huang, C., Zappone, A., Alexandropoulos, G.C., Debbah, M. and Yuen, C. (2019) Reconfigurable Intelligent Surfaces for Energy Efficiency in Wireless Communication. IEEE Transactions on Wireless Communications, 18, 4157-4170. http://dx.doi.org/10.1109/TWC.2019.2922609 [Google Scholar] [Crossref]

30. Björnson, E., Özdogan, Ö. and Larsson, E.G. (2020) Reconfigurable Intelligent Surfaces: Three Myths and Two Critical Questions. IEEE Communications Magazine, 58, 90-96. http://dx.doi.org/10.1109/MCOM.001.2000407 [Google Scholar] [Crossref]

31. Zhang, Y., Chen, L. and Wang, M. (2024) Transformer-Based Channel Estimation for Reconfigurable Intelligent Surface Aided Wireless Systems. IEEE Transactions on Wireless Communications, 23, 9234-9248. http://dx.doi.org/10.1109/TWC.2024.3401245 [Google Scholar] [Crossref]

32. Liu, H., Zhao, S. and Kim, J. (2024) Graph Neural Network Assisted Channel Estimation for Intelligent Reflecting Surfaces. IEEE Communications Letters, 28, 1342-1346. http://dx.doi.org/10.1109/LCOMM.2024.3398765 [Google Scholar] [Crossref]

33. Wang, X., Liu, Y. and Chen, Z. (2025) Meta-Learning Enhanced Channel Estimation for Reconfigurable Intelligent Surfaces in Time-Varying Environments. IEEE Transactions on Vehicular Technology, 74, 2156-2170. http://dx.doi.org/10.1109/TVT.2025.3445612 [Google Scholar] [Crossref]

34. Chen, M., Zhang, K. and Li, W. (2024) Deep Reinforcement Learning for Joint UAV Trajectory and RIS Phase Shift Optimization. IEEE Journal on Selected Areas in Communications, 42, 2845-2860. http://dx.doi.org/10.1109/JSAC.2024.3412398 [Google Scholar] [Crossref]

35. Huang, C., Sun, R. and Dai, L. (2024) CNN-Transformer Hybrid Network for Massive MIMO CSI Feedback. IEEE Transactions on Signal Processing, 72, 4523-4538. http://dx.doi.org/10.1109/TSP.2024.3398234 [Google Scholar] [Crossref]

36. Wang, P., Chen, Y. and Zhang, H. (2025) Federated Learning with CNN-LSTM for Privacy-Preserving Channel Estimation in Beyond-5G Networks. IEEE Wireless Communications Letters, 14, 876-880. http://dx.doi.org/10.1109/LWL.2025.3456789 [Google Scholar] [Crossref]