# Investigating Map-Based Path Loss Models: A Study of Feature Representations in Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2501.07534 · HTML: https://mlsanity.com/paper/2501.07534/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 16 references that are in the map.
- First posted on arXiv 13 Jan 2025.

## Builds on (most cited first, 2 of 2)

- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [Machine Learning-Based Path Loss Modeling with Simplified Features](https://mlsanity.com/paper/2405.10006/) (2024)

## Built on by (most cited first, 1 of 1)

- [Reciprocity-Aware Convolutional Neural Networks for Map-Based Path Loss Prediction](https://mlsanity.com/paper/2504.03625/) (2025)

## Abstract (arXiv)

Path loss prediction is a beneficial tool for efficient use of the radio frequency spectrum. Building on prior research on high-resolution map-based path loss models, this paper studies convolutional neural network input representations in more detail. We investigate different methods of representing scalar features in convolutional neural networks. Specifically, we compare using frequency and distance as input channels to convolutional layers or as scalar inputs to regression layers. We assess model performance using three different feature configurations and find that representing scalar features as image channels results in the strongest generalization.