Modeling radio wave propagation in a fifth generation (5G) or other next generation network

First network equipment, comprising:

• a processor;
• and
• a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
• identifying a graphical representation of a layout of a geographic location, wherein the graphical representation comprises a first identified point on the layout, comprising a sample propagation point of a signal,
• sending, to second network equipment, a second identified point on the layout, comprising a sample signal receiving point, and
• receiving, from the second network equipment, an estimated propagation of a signal applicable to a propagation of the signal from the first identified point to the second identified point, wherein the second network equipment estimated the propagation of the signal based on the graphical representation and a feature map for the geographic location generated by employing a neural network trained with training data, resulting in an estimated propagation, and wherein the feature map comprises a map depicting the estimated propagation of the signal at identified locations within the geographic location, wherein the training data of the neural network corresponds to:
• training of graphical representations based on the graphical representation, and
• training values determined based on indicated conditions that were indicated by the training of the graphical representations, and
• a convolutional neural network employed by the second network equipment by a process comprising:
• based on the indicated conditions, convoluting data corresponding to the graphical representation and the identified locations, resulting in a matrix of weighted values, and
• combining the matrix with the graphical representation, resulting in the feature map.

A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor of a system, facilitate performance of operations, comprising:

• based on a satellite image associated with a geographic area, identifying a feature of the geographic area relevant to propagation of a signal propagated from a signal point on the satellite image, resulting in an identified feature;
• and
• based on the identified feature and the signal point, generating a feature map for the geographic area by employing a neural network, wherein the feature map comprises a map depicting estimates of the propagation of the signal at locations within the geographic area, wherein the neural network was trained based on a deep learning process with training data representative of:
• training graphical representations similar to composition of graphics of the satellite image according to a first defined similarity criterion, and
• training values corresponding to propagations of signals in conditions indicated by the training graphical representations, wherein the neural network is trained with training data corresponding to:
• training of graphical representations based on the graphical representation, and
• training values based on indicated conditions that were indicated by the training graphical representations, and
• a convolutional neural network employed by a process comprising:
• based on the indicated conditions, convoluting data corresponding to the graphical representation and the identified feature, resulting in a matrix of weighted values, and
• combining the matrix with the graphical representation, resulting in the feature map.