Explainable AI-Based Channel Estimation For Intelligent Reflecting Surface-Aided Networks

Dr. D. Suryaprabha; Mrs. S. Praseetha; Sika K; M. Jeba Paulin; Dhanya Krishnan

doi:10.29284/fjrn1766

Authors

Dr. D. Suryaprabha Assistant Professor Department of Information Technology Nehru Arts and Science College, Coimbatore, Tamil Nadu, India
Mrs. S. Praseetha Assistant Professor Department of Electronics and Communication Engineering Sri Ramakrishna Engineering College, Coimbatore, Tamil Nadu, India
Sika K Assistant Professor Department of Artificial Intelligence and Data Science Nehru Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India
M. Jeba Paulin Assistant Professor (Senior Grade) Department of Electronics and Communication Engineering Nehru Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India
Dhanya Krishnan Assistant Professor Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering, Coimbatore, Tamil Nadu, India

DOI:

https://doi.org/10.29284/fjrn1766

Keywords:

Intelligent Reflecting Surface (IRS), Explainable Artificial Intelligence (XAI), Channel Estimation, 6G Wireless Networks, Deep Learning, Interpretable Machine Learning, Cascaded Channel Modeling, Spectral Efficiency, Pilot Overhead Reduction

Abstract

Intelligent Reflecting Surface (IRS)–aided wireless networks have emerged as a key enabling technology for next-generation 6G communications due to their ability to intelligently reconfigure the wireless propagation environment. Accurate channel state information (CSI) is critical for realizing the full potential of IRS-assisted systems; however, channel estimation becomes highly challenging because of the large number of passive reflecting elements, cascaded channel structure, and dynamic wireless conditions. To address these challenges, this paper proposes an Explainable Artificial Intelligence (XAI)–based channel estimation framework for IRS-aided wireless networks. The proposed approach leverages a deep learning model to capture the nonlinear relationship between pilot signals and cascaded IRS channels, while integrating explainability mechanisms to provide transparent and interpretable insights into the estimation process. XAI techniques such as feature attribution and attention-based analysis are employed to identify the most influential IRS elements, pilot configurations, and environmental parameters contributing to accurate CSI prediction. Simulation results demonstrate that the proposed XAI-based model significantly outperforms conventional estimation methods in terms of normalized mean square error (NMSE) and robustness under varying signal-to-noise ratios, while offering enhanced interpretability and reliability. The proposed framework bridges the gap between high-performance AI-driven channel estimation and trustworthy wireless communication systems, making it a promising solution for future intelligent and adaptive 6G networks.

References

1. Sejan, M. A. S., Rahman, M. H., Shin, B. S., Oh, J. H., You, Y. H., & Song, H. K. (2022). Machine learning for intelligent-reflecting-surface-based wireless communication towards 6G: A review. Sensors, 22(14), 5405.

2. Balaji, C. G., Menaka, S., Rajeswari, G., & Ponnusamy, S. (2025). A unified AI-driven framework for quantum-secured 6G THz networks with intelligent reflecting surfaces and federated edge learning: CG Balaji et al. Scientific Reports, 15(1), 42510.

3. Chen, N., Liu, C., Jia, H., & Okada, M. (2022). Intelligent reflecting surface aided network under interference toward 6G applications. IEEE Network, 36(4), 18-27.

4. Koufos, K., El Haloui, K., Zhou, C., Frascolla, V., & Dianati, M. (2023). State-of-the-art in PHY layer deep learning for future wireless communication systems and networks. In Deep Learning and Its Applications for Vehicle Networks (pp. 87-114). CRC Press.

5. Ye, M., Pan, C., Xu, Y., & Li, C. (2024). Generative Adversarial Networks-Based Channel Estimation for Intelligent Reflecting Surface Assisted mmWave MIMO Systems. IEEE Transactions on Cognitive Communications and Networking, 10(5), 1883-1896.

6. Mbakaan, C., Kpelai, J., & Tyavnande, M. (2025). AI-Driven Terahertz 6G Wireless Communication Systems: From Hardware Design to Network Intelligence. Frontiers and Results in Applied Sciences, 1(2).

7. Adams, A. M. Z., & Abdelhadi, A. RSMA-enabled RIS-assisted Integrated Sensing and Communication for 6G: A Comprehensive Survey. Authorea Preprints.

8. Jassim, M. F., Mohammed, A. T., & Abdullah, O. (2024, October). Review of deep learning applications on reconfigurable intelligent surfaces. In AIP Conference Proceedings (Vol. 3232, No. 1, p. 020060). AIP Publishing LLC.

9. Toprak, A. G., Mercan, Ö. B., Tok, Y. E., & Karahan, S. N. (2025). Explainable and Trustworthy Artificial Intelligence in 6G THz Networks: Challenges, Solutions, and Future Perspectives. ITU Journal of Wireless Communications and Cybersecurity, 2(2), 61-80.

10. Okogbaa, F. C., Ahmed, Q. Z., Khan, F. A., Abbas, W. B., Che, F., Zaidi, S. A. R., & Alade, T. (2022). Design and application of intelligent reflecting surface (IRS) for beyond 5G wireless networks: A review. Sensors, 22(7), 2436.

11. Qin, Z., Liang, L., Wang, Z., Jin, S., Tao, X., Tong, W., & Li, G. Y. (2024). AI empowered wireless communications: From bits to semantics. Proceedings of the IEEE.

12. Yildiz, O. (2025). Toward Intelligent and Sustainable Wireless Environments with Hybrid and AI-Enhanced RIS Strategies. Electronics, 14(22), 4421.

13. Maheshwari, R.U., B.Paulchamy, Pandey, B.K. et al. Enhancing Sensing and Imaging Capabilities Through Surface Plasmon Resonance for Deepfake Image Detection. Plasmonics (2024). https://doi.org/10.1007/s11468-024-02492-1

14. Maheshwari, Uma, and Kalpanaka Silingam. "Multimodal Image Fusion in Biometric Authentication." Fusion: Practice and Applications 1, no. 2 (2020): 7991

15. N.V. RK, M. A, E. B, J. SJP, A. K, S. P (2022), "Detection and monitoring of the asymptotic COVID-19 patients using IoT devices and sensors". International Journal of Pervasive Computing and Communications, Vol. 18 No. 4 pp. 407–418, doi: https://doi.org/10.1108/IJPCC-08-2020-0107

16. Subramani, P.; Rajendran, G.B.; Sengupta, J.; Pérez de Prado, R.; Divakarachari, P.B. A Block Bi-Diagonalization-Based Pre-Coding for Indoor Multiple-Input-Multiple-Output-Visible Light Communication System. Energies 2020, 13, 3466. https://doi.org/10.3390/en13133466 .

17. Merluzzi, M., Borsos, T., Rajatheva, N., Benczúr, A. A., Farhadi, H., Yassine, T., ... & Uusitalo, M. A. (2023). The hexa-x project vision on artificial intelligence and machine learning-driven communication and computation co-design for 6g. IEEE Access, 11, 65620-65648.

18. Umer, A., Müürsepp, I., Alam, M. M., & Wymeersch, H. (2023). Role of reconfigurable intelligent surfaces in 6G radio Localization: Recent developments, opportunities, challenges, and applications. arXiv preprint arXiv:2312.07288.

19. Song, W., Rajak, S., Dang, S., Liu, R., Li, J., & Chinnadurai, S. (2022). Deep learning enabled IRS for 6G intelligent transportation systems: A comprehensive study. IEEE Transactions on Intelligent Transportation Systems, 24(11), 12973-12990.

20. Hariz, H. M., Sheikhzadeh, S., Mokari, N., Javan, M. R., Abbasi-Arand, B., & Jorswieck, E. A. (2021). AI-based radio resource management and trajectory design for PD-NOMA communication in IRS-UAV assisted networks. arXiv preprint arXiv:2111.03869.