# Physics-informed neural networks for pathloss prediction

arXiv: https://arxiv.org/abs/2211.12986 · HTML: https://mlsanity.com/paper/2211.12986/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 13 references that are in the map.
- First posted on arXiv 23 Nov 2022.

## Builds on (most cited first, 4 of 4)

- [AutoInt: Automatic Integration for Fast Neural Volume Rendering](https://mlsanity.com/paper/2012.01714/) (2020)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [Neural Control Variates](https://mlsanity.com/paper/2006.01524/) (2020)
- [In-Building Wideband Partition Loss Measurements at 2.5 GHz and 60 GHz](https://mlsanity.com/paper/1701.03415/) (2016)

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

- [Neural-ANOVA: Analytical Model Decomposition using Automatic Integration](https://mlsanity.com/paper/2408.12319/) (2024)

## Abstract (arXiv)

This paper introduces a physics-informed machine learning approach for pathloss prediction. This is achieved by including in the training phase simultaneously (i) physical dependencies between spatial loss field and (ii) measured pathloss values in the field. It is shown that the solution to a proposed learning problem improves generalization and prediction quality with a small number of neural network layers and parameters. The latter leads to fast inference times which are favorable for downstream tasks such as localization. Moreover, the physics-informed formulation allows training and prediction with a small amount of training data which makes it appealing for a wide range of practical pathloss prediction scenarios.