Enhancing OFDM Channel Estimation Accuracy with CNN-LSTM Hybrid Architectures

Abstract

Accurate channel estimation remains a fundamental challenge for next-generation orthogonal frequency-division multiplexing (OFDM) systems, especially in environments with high mobility, sparse pilot allocation, and time-varying multipath fading. Traditional pilot-based methods, such as Least Squares (LS) and Minimum Mean Square Error (MMSE), are easy to implement but suffer from noise sensitivity, high computational costs, and a reliance on prior channel statistics. Recently, deep learning techniques have shown promising results; yet many do not fully capture the joint spatial and temporal characteristics of wireless channels or overlook realistic pilot-grid structures. This study introduces a pilot-grid-aware hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) for spatial feature extraction with Long Short-Term Memory (LSTM) networks for temporal sequence modeling. The model is trained using the Root Mean Square Propagation (RMSprop) optimizer, selected for its robustness in adapting learning rates and effectively capturing dependencies across both spatial and temporal dimensions. Benchmark evaluations against conventional estimators and theoretical limits under different modulation formats demonstrate that the proposed model consistently achieves a lower estimation error and bit error rate across a wide range of signal-to-noise ratios. The results confirm that the hybrid architecture provides a scalable and reliable solution for future wireless systems including sixth-generation (6G) networks, vehicular communications, and satellite applications where both adaptability and robustness are essential.

Keywords

• Channel Estimation
• Deep Learning
• Hybrid CNN-LSTM
• OFDM

References

1. [1]. Guan, P, Wu, D, Tian, T, Zhou, J, Zhang, X, Gu, L. 2017. 5G Field Trials: OFDM-Based Waveforms and Mixed Numerologies. IEEE Journal on Selected Areas in Communications, 35(6): 1234-1243. (https://doi.org/10.1109/JSAC.2017.2687718)
2. [2]. Baştürk, I. 2007. Iterative Channel Estimation Techniques for Multiple Input Multiple Output Orthogonal Frequency Division Multiplexing Systems. Master Thesis, Izmir Institute of Technology, Izmir, Türkiye. Available: (http://hdl.handle.net/11147/3637)
3. [3]. Zhao, J, Liu, C, Liao, J, Wang, D. 2024. Deep learning in wireless communications for physical layer. Physical Communication, 67: 102503. (https://doi.org/10.1016/j.phycom.2024.102503)
4. [4]. Ye, H, Li, GY, Juang, BH. 2018. Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems. IEEE Wireless Communications Letters, 7(1): 114-117. (https://doi.org/10.1109/LWC.2017.2757490)
5. [5]. Wang, S, Yao, R, Tsiftsis, TA, Miridakis, NI, Qi, N. 2020. Signal Detection in Uplink Time-Varying OFDM Systems Using RNN with Bidirectional LSTM. IEEE Wireless Communications Letters, 9(11): 1947-1951. (https://doi.org/10.1109/LWC.2020.3009170)
6. [6]. Zhao, Z, Vuran, MC, Guo, F, Scott, SD. 2018. Deep-waveform: A learned OFDM receiver based on deep complex-valued convolutional networks. arXiv preprint. (https://arxiv.org/abs/1810.07181)
7. [7]. Roozitalab, T, Bahramgiri, H, Farhang, M, Javadyfar, A. 2022. Deep learning-based channel estimation in OFDM systems for time-varying Rayleigh fading channels. Journal of Communication Engineering, 11(1): 1-20.
8. [8]. A. Siriwanitpong, K. Sanada, H. Hatano, K. Mori and P. Boonsrimuang. 2025. Deep Learning-Based Channel Estimation With 1D CNN for OFDM Systems Under High-Speed Railway Environments. IEEE Access, vol. 13, pp. 13128-13142. (https://doi.org/10.1109/ACCESS.2025.3531009)

9. [9]. Reis, AFD, Chang, BS, Medjahdi, Y, Brante, G, Bader, F. 2024. LSTM-based time-frequency domain channel estimation for OTFS modulation. IEEE Transactions on Vehicular Technology, 73(10): 15049-15060. (https://doi.org/10.1109/TVT.2024.3406192)
10. [10]. Ali, MHE, Abdellah, AR, Atallah, HA, Ahmed GS, Muthanna, A, Koucheryavy, A. 2023. Deep learning peephole LSTM neural network-based channel state estimators for OFDM 5G and beyond networks. Mathematics, 11(15): 3386. (https://doi.org/10.3390/math11153386)
11. [11]. Zhang, Z, Luo, H, Wang, C, Gan, Chenquan, Xiang, Y. 2020. Automatic Modulation Classification Using CNN-LSTM Based Dual-Stream Structure. IEEE Transactions on Vehicular Technology, 69(11): 13521-13531. (https://doi.org/10.1109/TVT.2020.3030018)
12. [12]. Nguyen, C, Hoang TM, Cheema, A.A. 2023. Channel Estimation Using CNN-LSTM in RIS-NOMA Assisted 6G Network. IEEE Transactions on Machine Learning in Communications and Networking, 1: 43-60. (https://doi.org/10.1109/TMLCN.2023.3278232)
13. [13]. Nyamakeur, K, Yongchareon, S, Yu, J, Sheng, QZ. 2022. Deep CNN-LSTM network for indoor location estimation using analog signals of passive infrared sensors. IEEE Internet of Things Journal, 9(22): 22582-22594. (https://doi.org/10.1109/JIOT.2022.3183148)
14. [14]. Filippo, BD, Amatetti, C, Coralli, AV. 2025. Uplink OFDM Channel Prediction with Hybrid CNN-LSTM for 6G Non-Terrestrial Networks. Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), Poznan, Poland: 7-12. (https://doi.org/10.1109/EuCNC/6GSummit63408.2025.11037085)
15. [15]. Thoong, QT, Cheema, AA, Khosravirad, SR, Dobre, OA, Duong, TQ. 2024. Channel Estimation for Reconfigurable Intelligent Surface-aided 6G NOMA Systems using CNN-based Quantum LSTM Model, IEEE 100th Vehicular Technology Conference (VTC2024-Fall), Washington, DC: 1-5. (https://doi.org/10.1109/VTC2024-Fall63153.2024.10757552)
16. [16]. Massalay S.J, Basturk I., Koçyiğit Y. (2025, August). Deep Learning-Based Channel Estimation for Wireless Communication Networks. Abant 5th International Conference On Scientific Researches, Bolu, Türkiye, Jul. 18-20, 2025, pp. 774-786.
17. [17]. Van de Beek, JJ, Edofors, O, Sandell, M, Wilson, SK, Börjesson, PO. 1995. On channel estimation in OFDM systems, Proc. IEEE 45th Vehicular Technology Conf. (VTC), Chicago, IL, USA. 2: 815-819. (https://doi.org/10.1109/VETEC.1995.504981)
18. [18]. Shen, Y., & Martinez, E. (2006). Channel estimation in OFDM systems. Freescale semiconductor application note, 1-15.
19. [19]. Coleri, S, Ergen, M, Puri, A, Bahai, A. 2002. Channel estimation techniques based on pilot arrangement in OFDM systems. IEEE Trans. Broadcasting, 48(3): 223-229. (https://doi.org/10.1109/TBC.2002.804034)
20. [20]. Li, Y. 2002. Simplified channel estimation for OFDM systems with multiple transmit antennas. IEEE Transactions on Wireless Communications, 1(1): 67-75. (https://doi.org/10.1109/7693.975446)
21. [21]. Ibarra-Hernández, R. F., Castillo-Soria, F. R., Gutiérrez, C. A., García-Barrientos, A., Vásquez-Toledo, L. A., & Del-Puerto-Flores, J. A. (2024). Machine learning strategies for reconfigurable intelligent surface-assisted communication systems-A Review. Future Internet, 16(5), 173. (https://www.mdpi.com/1999-5903/16/5/173#)