# Radio Propagation Modelling: To Differentiate or To Deep Learn, That Is The Question

arXiv: https://arxiv.org/abs/2509.19337 · HTML: https://mlsanity.com/paper/2509.19337/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 69 references that are in the map.
- First posted on arXiv 15 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling](https://mlsanity.com/paper/2303.11103/) (2023)
- [NeRF2: Neural Radio-Frequency Radiance Fields](https://mlsanity.com/paper/2305.06118/) (2023)
- [RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction](https://mlsanity.com/paper/2408.08593/) (2024)
- [RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion](https://mlsanity.com/paper/2404.09140/) (2024)
- [NeWRF: A Deep Learning Framework for Wireless Radiation Field Reconstruction and Channel Prediction](https://mlsanity.com/paper/2403.03241/) (2024)
- [A Scalable and Generalizable Pathloss Map Prediction](https://mlsanity.com/paper/2312.03950/) (2023)
- [RadioNet: Transformer based Radio Map Prediction Model For Dense Urban Environments](https://mlsanity.com/paper/2105.07158/) (2021)
- [Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networks](https://mlsanity.com/paper/2110.01848/) (2021)
- [Denoising Diffusion Probabilistic Model for Radio Map Estimation in Generative Wireless Networks](https://mlsanity.com/paper/2501.06604/) (2025)
- [Artificial intelligence enabled radio propagation for communications-Part II: Scenario identification and channel modeling](https://mlsanity.com/paper/2111.12228/) (2021)
- [An Overview of Machine Learning Techniques for Radiowave Propagation Modeling](https://mlsanity.com/paper/2101.11760/) (2021)
- [WiThRay: A Versatile Ray-Tracing Simulator for Smart Wireless Environments](https://mlsanity.com/paper/2304.11385/) (2023)
- [Spatial Transformers for Radio Map Estimation](https://mlsanity.com/paper/2411.01211/) (2024)
- [Vision Transformers for Efficient Indoor Pathloss Radio Map Prediction](https://mlsanity.com/paper/2412.09507/) (2024)
- [Empowering Wireless Network Applications with Deep Learning-based Radio Propagation Models](https://mlsanity.com/paper/2408.12193/) (2024)
- [Physics-informed generative neural networks for RF propagation prediction with application to indoor body perception](https://mlsanity.com/paper/2405.02131/) (2024)

## Built on by (most cited first, 3 of 3)

- [U6G XL-MIMO Radiomap Prediction: Multi-Config Dataset and Beam Map Approach](https://mlsanity.com/paper/2603.06401/) (2026)
- [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)
- [Differentiable Ray Tracing with Gaussians for Unified Radio Propagation Simulation and View Synthesis](https://mlsanity.com/paper/2605.07781/) (2026)

## Abstract (arXiv)

Differentiable ray tracing has recently challenged the status quo in radio propagation modelling and digital twinning. Promising unprecedented speed and the ability to learn from real-world data, it offers a real alternative to conventional deep learning (DL) models. However, no experimental evaluation on production-grade networks has yet validated its assumed scalability or practical benefits. This leaves mobile network operators (MNOs) and the research community without clear guidance on its applicability. In this paper, we fill this gap by employing both differentiable ray tracing and DL models to emulate radio coverage using extensive real-world data collected from the network of a major MNO, covering 13 cities and more than 10,000 antennas. Our results show that, while differentiable ray-tracing simulators have contributed to reducing the efficiency-accuracy gap, they struggle to generalize from real-world data at a large scale, and they remain unsuitable for real-time applications. In contrast, DL models demonstrate higher accuracy and faster adaptation than differentiable ray-tracing simulators across urban, suburban, and rural deployments, achieving accuracy gains of up to 3 dB. Our experimental results aim to provide timely insights into a fundamental open question with direct implications on the wireless ecosystem and future research.