Site-specific Deep Learning Path Loss Models based on the Method of Moments

TL;DR

This paper introduces deep learning models trained on synthetic data generated via the method of moments to predict path loss over rural terrain, demonstrating high accuracy in both synthetic and real-world scenarios.

Contribution

It presents a novel approach combining the method of moments with deep learning to create site-specific path loss models for rural environments.

Findings

High accuracy on test profiles similar to training data

Good accuracy on real-life terrain profiles

Effective use of synthetic data for training deep learning models

Abstract

This paper describes deep learning models based on convolutional neural networks applied to the problem of predicting EM wave propagation over rural terrain. A surface integral equation formulation, solved with the method of moments and accelerated using the Fast Far Field approximation, is used to generate synthetic training data which comprises path loss computed over randomly generated 1D terrain profiles. These are used to train two networks, one based on fractal profiles and one based on profiles generated using a Gaussian process. The models show excellent agreement when applied to test profiles generated using the same statistical process used to create the training data and very good accuracy when applied to real life problems.