Using 2W-PE method based on machine learning to accurately predict field strength distribution in flat-top obstacle environment

A Fast Algorithm for Solving Radio Wave Propagation Based on Machine Learning and Domain Decomposition Method

“…where ( ) N is the number of terms retained in the KL expansion and also the number of random variables required for calculation. As shown in (7), random terrain surfaces with varying degrees of undulation can be generated.…”

“…Among these, the RT method [1][2] is a highfrequency prediction method whose accuracy is proportional to the number of rays that satisfy convergence; however, the number of required rays is too large in complex environments, thus resulting in low efficiency. In our previous studies [4][5][6][7], 2W-PE was shown to have advantages in regular obstacle environments. However, in steep and undulating terrain, the propagation angle limitations of 2W-PE cause significant errors.…”

“…However, calculating radio wave propagation in complex environments remains highly challenging. The most common calculation methods for this process include the ray tracing (RT) method [1][2], two-way parabolic equation (2W-PE) method [3][4][5][6][7], full wave analysis method [8], etc. Among these, the RT method [1][2] is a highfrequency prediction method whose accuracy is proportional to the number of rays that satisfy convergence; however, the number of required rays is too large in complex environments, thus resulting in low efficiency.…”

An Efficient and Accurate 2W-PE Method for Solving Spatial Field Strength Based on CVNN and PINN

“…Te results in Figure 12 show that the new 2W-PE and the original 2W-PE are only in good agreement before the obstacles, and there are relatively large errors between the obstacles and after the obstacles. According to [17], this is caused by the inaccurate boundary conditions during the calculation of the internal feld value of the obstacle. However, from Figure 12, we can see that our new 2W-PE and MoM always match better whether the observation point is close to the source or between two obstacles.…”

“…Since then, the traditional 2W-PE [10,11] and its solution method [12][13][14] have been continuously developed, but traditional 2W-PE ignores the calculation of the spatial feld inside the obstacle, which will cause a large error in the case of a low-lossy obstacle. In response to the abovementioned problems, in our previous research [15][16][17], we proposed a 2W-PE that considers multiple refections inside the obstacle based on the principle of domain decomposition. Ten, we used the split-step Fourier transform (SSFT) and FD methods to solve the 2W-PE with boundary conditions to determine the feld values of the areas above and inside the obstacle, respectively.…”