Explainable Causal Forecasting Model for Maximum Usable Frequency in HF Wireless Communications

Accurate forecasting of the Maximum Usable Frequency (MUF) remains a major challenge in high-frequency (HF) wireless communications, where ionospheric variability directly impacts channel availability. This study develops a high-accuracy MUF forecasting framework using empirical data from 17 HF circuits across China to enhance the precision of frequency selection in HF communication. The main contributions are: (1) This study applies the Granger causality test for the first time to identify statistically significant causal relationships between MUF and space weather parameters. Lagged variables demonstrating causal influence are then selected as input features for the forecasting model. (2) In addition to traditional solar activity indices and geomagnetic data, this study also considers the influence of interplanetary parameters (Bz and solar wind) on MUF forecasting performance. (3) This study is the first to utilize the interpretable TabNet model for MUF forecasting, enabling quantification of input feature importance. Hyperparameter tuning is performed using simulated annealing to enhance model performance. Compared with the VOACAP and ITU-R REC533 models, the proposed TabNet model demonstrates high stability and forecasting accuracy across seasonal and hourly timescales. Overall, across these established models, it achieves a 35.34% improvement in performance. This work offers a fresh perspective on frequency optimization in HF communications, laying the groundwork for future advancements in adaptive communication strategies.