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

TL;DR

AIRMap presents a DL-based framework for real-time radio-map estimation tailored for wireless digital twins. A single-input U‑Net takes a 2D elevation map to predict area-wide path gain with sub‑5 dB RMSE and ~4 ms inference, trained on a large 60k-sample Boston dataset; lightweight transfer-learning calibration using 20% field data reduces median error to ~10%. The authors automate the largest site-specific radio-map dataset to date and validate AIRMap within Sionna SYS and the Colosseum emulator, achieving near-zero system-level error relative to measurements. The work demonstrates substantial speedups over ray-tracing, enabling real-time, end-to-end emulation across protocol layers and broad applicability to digital-twin workflows. Overall, AIRMap combines data-driven accuracy with scalable, low-latency inference to transform propagation modeling for real-time wireless networks.

Abstract

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 and evaluated on 60,000 Boston-area samples, spanning coverage areas from 500 m to 3 km per side, AIRMap predicts path gain with under 5 dB RMSE in 4 ms per inference on an NVIDIA L40S -- over 7000x faster than GPU-accelerated ray tracing based radio maps. A lightweight transfer learning calibration using just 20% of field measurements reduces the median error to approximately 10%, 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.

Figures (19)

• Figure 1: Measurement campaign map showing the location and route. The line color represents the path gain and coverage distribution.
• Figure 2: Evaluation of ray tracing performance by comparing with actual measurement data.
• Figure 3: Material and antenna misconfigurations in ray tracing.
• Figure 4: Measurement results ordered by distance from the , highlighting the difficulty of fitting traditional empirical models to real-world data.
• Figure 5: Geographic study area in Boston. The red-outlined region marks the environment used for dataset generation, while the blue-highlighted region corresponds to the area used in the measurement campaign shown in Fig. \ref{['fig:meas_route']}.