Field strength is a typical indicator of air access network signals, and the prediction of field strength has important reference significance for the estimation of aerial access network signals. However, many factors affecting the field strength, such as path, terrain, sunshine, and climate, increase the computational complexity, which greatly increases the difficulty of establishing an accurate prediction system. After persistent research by researchers in recent years, the ITU‐R P.1546 model has gradually become a point‐to‐surface forecasting method for ground services recommended by ITU for ground operations in the frequency range of 30 MHz~3000 MHz. In view of the characteristics of electromagnetic signal propagation in mountainous environment, the influence of diffraction is also considered in this paper. Based on more accurate scene information such as actual terrain, the prediction calculation of electromagnetic signal propagation in a mountainous environment is proposed by using the corrected ITU‐R P.1546 model. In addition, the influence of the actual terrain is taken into account to correct the relevant parameters, and the predicted results are compared with the measured data. The results indicate that field strength prediction results of the ITU‐R P.1546 model based on the diffraction effect correction proposed in this paper in specific physical areas have better performance than those of the traditional ITU‐R P.1546 model. Among them, the determination coefficient between the measured data and the predicted results is 0.87, the average error is 5.097 dBμV/m, and the root mean square error is 6.6228 dBμV/m, which proves that the ITU‐R P.1546 model based on the corrected model is effective in the prediction of electromagnetic field intensity in the actual mountainous environment.

In this paper, Computer Vision (CV) sensing technology based on Convolutional Neural Network (CNN) is introduced to process topographic maps for predicting wireless signal propagation models, which are applied in the field of forestry security monitoring. In this way, the terrain-related radio propagation characteristic including diffraction loss and shadow fading correlation distance can be predicted or extracted accurately and efficiently. Two data sets are generated for the two prediction tasks, respectively, and are used to train the CNN. To enhance the efficiency for the CNN to predict diffraction losses, multiple output values for different locations on the map are obtained in parallel by the CNN to greatly boost the calculation speed. The proposed scheme achieved a good performance in terms of prediction accuracy and efficiency. For the diffraction loss prediction task, 50% of the normalized prediction error was less than 0.518%, and 95% of the normalized prediction error was less than 8.238%. For the correlation distance extraction task, 50% of the normalized prediction error was less than 1.747%, and 95% of the normalized prediction error was less than 6.423%. Moreover, diffraction losses at 100 positions were predicted simultaneously in one run of CNN under the settings in this paper, for which the processing time of one map is about 6.28 ms, and the average processing time of one location point can be as low as 62.8 us. This paper shows that our proposed CV sensing technology is more efficient in processing geographic information in the target area. Combining a convolutional neural network to realize the close coupling of a prediction model and geographic information, it improves the efficiency and accuracy of prediction.