# AIRMap: AI-Generated Radio Maps for Wireless Digital Twins

arXiv: https://arxiv.org/abs/2511.05522 · HTML: https://mlsanity.com/paper/2511.05522/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 57 references that are in the map.
- First posted on arXiv 28 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [Intelligence and Learning in O-RAN for Data-driven NextG Cellular Networks](https://mlsanity.com/paper/2012.01263/) (2020)
- [Deep Learning for mmWave Beam and Blockage Prediction Using Sub-6GHz Channels](https://mlsanity.com/paper/1910.02900/) (2019)
- [Real-Time Digital Twins: Vision and Research Directions for 6G and Beyond](https://mlsanity.com/paper/2301.11283/) (2023)
- [Learning Radio Environments by Differentiable Ray Tracing](https://mlsanity.com/paper/2311.18558/) (2023)
- [A Scalable and Generalizable Pathloss Map Prediction](https://mlsanity.com/paper/2312.03950/) (2023)
- [dApps: Distributed Applications for Real-time Inference and Control in O-RAN](https://mlsanity.com/paper/2203.02370/) (2022)
- [PMNet: Robust Pathloss Map Prediction via Supervised Learning](https://mlsanity.com/paper/2211.10527/) (2022)
- [Deep Learning for Joint Channel Estimation and Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2011.07242/) (2020)
- [dApps: Enabling Real-Time AI-Based Open RAN Control](https://mlsanity.com/paper/2501.16502/) (2025)
- [Artificial intelligence enabled radio propagation for communications-Part II: Scenario identification and channel modeling](https://mlsanity.com/paper/2111.12228/) (2021)
- [Deep Learning-based Signal Strength Prediction Using Geographical Images and Expert Knowledge](https://mlsanity.com/paper/2008.07747/) (2020)
- [An Overview of Machine Learning Techniques for Radiowave Propagation Modeling](https://mlsanity.com/paper/2101.11760/) (2021)
- [Machine Learning-based Urban Canyon Path Loss Prediction using 28 GHz Manhattan Measurements](https://mlsanity.com/paper/2202.05107/) (2022)
- [Colosseum: The Open RAN Digital Twin](https://mlsanity.com/paper/2404.17317/) (2024)
- [BostonTwin: the Boston Digital Twin for Ray-Tracing in 6G Networks](https://mlsanity.com/paper/2403.12289/) (2024)
- [An empirical study on using CNNs for fast radio signal prediction](https://mlsanity.com/paper/2006.09245/) (2020)
- [A Big Data Enabled Channel Model for 5G Wireless Communication Systems](https://mlsanity.com/paper/2002.12561/) (2020)
- [Radio Resource and Beam Management in 5G mmWave Using Clustering and Deep Reinforcement Learning](https://mlsanity.com/paper/2103.05047/) (2021)
- [AI-assisted Agile Propagation Modeling for Real-time Digital Twin Wireless Networks](https://mlsanity.com/paper/2410.22437/) (2024)
- [TwiNet: Connecting Real World Networks to their Digital Twins Through a Live Bidirectional Link](https://mlsanity.com/paper/2411.03503/) (2024)
- [ColosSUMO: Evaluating Cooperative Driving Applications with Colosseum](https://mlsanity.com/paper/2404.19686/) (2024)
- [Site-Specific Radio Channel Representation for 5G and 6G](https://mlsanity.com/paper/2406.09025/) (2024)

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

- [Should I Use This Synthetic Dataset for Training? How to Test with Minimal Real Data](https://mlsanity.com/paper/2608.27996/) (2026)

## Abstract (arXiv)

Accurate, low-latency channel modeling is essential for real-time wireless network simulation and digital-twin applications. Traditional modeling methods like ray tracing are however computationally demanding and unsuited to model dynamic conditions. In this paper, we propose AIRMap, a deep-learning framework for ultra-fast radio-map estimation, along with an automated pipeline for creating the largest radio-map dataset to date. AIRMap uses a single-input U-Net autoencoder that processes only a 2D elevation map of terrain and building heights. Trained on 1.2M Boston-area samples and validated across four distinct urban and rural environments with varying terrain and building density, AIRMap predicts path gain with under 4 dB RMSE in 4 ms per inference on an NVIDIA L40S-over 100x faster than GPU-accelerated ray tracing based radio maps. A lightweight calibration using just 20% of field measurements reduces the median error to approximately 5%, significantly outperforming traditional simulators, which exceed 50% error. Integration into the Colosseum emulator and the Sionna SYS platform demonstrate near-zero error in spectral efficiency and block-error rate compared to measurement-based channels. These findings validate AIRMap's potential for scalable, accurate, and real-time radio map estimation in wireless digital twins.