Abstract: The coverage range of mobile communication base stations is not only related to the transmission power, frequency, and antennas, but also significantly influenced by geospatial environmental information. However, there are still many problems to be solved in terms of associating and visualizing them. In response to this problem, a web-based mobile communication base station coverage prediction system is proposed in this paper. First, data screening and cellular scenario reconstruction are conducted using Huawei′s open source dataset. Second, various machine learning models are trained, with comparative analysis performed between three empirical radio propagation models and nine machine learning models based on testing results. The results show that the machine learning models generally outperform the empirical models, and the prediction performance of the ensemble model is better than that of the single machine learning model. Among them, the root mean square error of the extreme random tree model is 5.23 dB, which has the best prediction performance. Finally, the visualization of mobile communication base station coverage is implemented based on the Web architecture.