In the demand for accurate predictive analysis of antenna network coverage will become an increasingly critical situation in today’s digital age, necessitating the development of advanced techniques to address the challenges posed by the evolving landscape of wireless-based communication. In this study, a novel system for antenna network coverage prediction depending on the powerful combination of gradient-based boosting with randomly format forest (RF) algorithm has been shown. The proposed systems will leverage machine learning-driven techniques to forecast ground-to-ground (G2G) antenna communication coverage with higher level precision and reliability. Specific gradient-based boosting with randomly format forest (RF) algorithm was employed as the core predictive modeling due to its robustness and capability to handle complex datasets. Through a rigorous evaluation process, the proposed system demonstrated superior performance in predicting VSWR, Antenna’s gain, losses which will be crucial metrics for assessing antenna network coverage quality. The merging of gradient-based boosting with randomly format forest (RF) algorithm enabled the proposed system to be effective in capturing intricate patterns and dependencies within the data, by resulting in high parameter predictions across diverged frequency bands and to different environmental conditions. Furthermore, the proposed system also offers scalability and adaptability, by making it suitable for deployment to real-world mobile network planning applications. By providing comprehensive coverage prediction capabilities, this system might facilitate sophisticated network analysis and optimization cycles, ultimately enhancing the overall performance and reliability suitable for modern mobile communication infrastructures.