This simulation code package is mainly used to reproduce the results of the following paper [1]:

[1] J. Li, J. Zhu, and L. Dai, “Spatio-temporal electromagnetic kernel learning for channel prediction,” IEEE Trans. Wireless Commun., vol. 25, no. 1, pp. 8114-8130, Jan. 2026. 


*********************************************************************************************************************************
If you use this simulation code package in any way, please cite the original paper [1] above. 
 
The author in charge of this simulation code pacakge is: Jinke Li (email: lijk23@mails.tsinghua.edu.cn).

Reference: We highly respect reproducible research, so we try to provide the simulation codes for our published papers (more information can be found at: 
http://oa.ee.tsinghua.edu.cn/dailinglong/publications/publications.html). 

Please note that the MATLAB R2021b is used for this simulation code package, and there may be some imcompatibility problems among different MATLAB versions. 

Copyright reserved by the Broadband Communications and Signal Processing Laboratory (led by Dr. Linglong Dai), State Key Laboratory of Space Network and Communications, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China. 


*********************************************************************************************************************************
Abstract of the paper: 

Abstract—Accurate channel prediction is essential for addressing channel aging caused by user mobility. However, the actual channel variations over time are highly complex in high-mobility scenarios, which makes it difficult for existing predictors to obtain future channels accurately. The low accuracy of channel predictors leads to difficulties in supporting reliable communication.
To overcome this challenge, we propose a channel predictor based on spatio-temporal electromagnetic (EM) kernel learning (STEM-KL). Specifically, inspired by recent advancements in electromagnetic information theory (EIT), the STEM kernel function is derived. The velocity and the concentration kernel parameters are designed to reflect the time-varying propagation of the wireless signal. We obtain the parameters through kernel learning. Then, the future channels are predicted by computing their Bayesian posterior, with the STEM kernel acting as the prior. To further improve the stability and model expressibility, we propose a grid-based EM mixed kernel learning (GEM-KL) scheme. We design the mixed kernel to be a convex combination of multiple sub-kernels, where each sub-kernel corresponds to a grid point in the set of pre-selected parameters. This approach transforms the non-convex STEM kernel learning problem into a convex grid-based problem that can be easily solved by weight optimization. Finally, simulation results verify that the proposed STEM-KL and GEM-KL schemes can achieve more accurate channel prediction. This indicates that EIT can improve the performance of wireless systems efficiently. 


*********************************************************************************************************************************
How to use this simulation code package?

1. Run "CDL/sim_fig_5.m" to obtain the results in Fig. 5.

2. Run "CDL/sim_fig_6.m"to obtain the results in Fig. 6.

3. Run "CDL/sim_fig_7_8.m"to obtain the results in Fig. 7 and Fig. 8.

4. Run "CDL/sim_fig_9.m" to obtain the results in Fig. 9.

5. Run "ray_tracing/sim_fig_10.m" to obtain the results in Fig. 10.

7. Run "ray_tracing/sim_fig_11_12.m" to obtain the results in Fig. 11 and Fig. 12.

6. Run "ray_tracing/sim_fig_13.m" to obtain the results in Fig. 13.


*********************************************************************************************************************************
Enjoy the reproducible research!
