# Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2110.01848 · HTML: https://mlsanity.com/paper/2110.01848/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 5 Oct 2021.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Hypercolumns for Object Segmentation and Fine-grained Localization](https://mlsanity.com/paper/1411.5752/) (2014)

## Built on by (most cited first, 15 of 15)

- [Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling](https://mlsanity.com/paper/2303.11103/) (2023)
- [Learning Radio Environments by Differentiable Ray Tracing](https://mlsanity.com/paper/2311.18558/) (2023)
- [Calibrating Wireless Ray Tracing for Digital Twinning using Local Phase Error Estimates](https://mlsanity.com/paper/2312.12625/) (2023)
- [Radio Map Prediction from Aerial Images and Application to Coverage Optimization](https://mlsanity.com/paper/2410.17264/) (2024)
- [Radio Map Estimation -- An Open Dataset with Directive Transmitter Antennas and Initial Experiments](https://mlsanity.com/paper/2402.00878/) (2024)
- [Geo2SigMap: High-Fidelity RF Signal Mapping Using Geographic Databases](https://mlsanity.com/paper/2312.14303/) (2023)
- [Radio Propagation Modelling: To Differentiate or To Deep Learn, That Is The Question](https://mlsanity.com/paper/2509.19337/) (2025)
- [Wireless Channel Prediction in Partially Observed Environments](https://mlsanity.com/paper/2207.00934/) (2022)
- [Data-Driven Radio Environment Map Estimation Using Graph Neural Networks](https://mlsanity.com/paper/2407.07713/) (2024)
- [Data-Driven Radio Propagation Modeling using Graph Neural Networks](https://mlsanity.com/paper/2501.06236/) (2025)
- [Variational Autoencoder Assisted Neural Network Likelihood RSRP Prediction Model](https://mlsanity.com/paper/2207.00166/) (2022)
- [Simulation-Enhanced Data Augmentation for Machine Learning Pathloss Prediction](https://mlsanity.com/paper/2402.01969/) (2024)
- [Context-Aware Mobile Network Performance Prediction Using Network & Remote Sensing Data](https://mlsanity.com/paper/2405.00220/) (2024)
- [Learning Coverage- and Power-Optimal Transmitter Placement from City Maps: A Comparative Study of Direct and Indirect Neural Approaches](https://mlsanity.com/paper/2604.22056/) (2026)
- [Multi-Modal Conditioned High-Resolution Transformer for Urban Electromagnetic Field Map Prediction Download PDF](https://mlsanity.com/paper/2606.27671/) (2026)

## Abstract (arXiv)

Radio propagation modeling and prediction is fundamental for modern cellular network planning and optimization. Conventional radio propagation models fall into two categories. Empirical models, based on coarse statistics, are simple and computationally efficient, but are inaccurate due to oversimplification. Deterministic models, such as ray tracing based on physical laws of wave propagation, are more accurate and site specific. But they have higher computational complexity and are inflexible to utilize site information other than traditional global information system (GIS) maps. In this article we present a novel method to model radio propagation using deep convolutional neural networks and report significantly improved performance compared to conventional models. We also lay down the framework for data-driven modeling of radio propagation and enable future research to utilize rich and unconventional information of the site, e.g. satellite photos, to provide more accurate and flexible models.