AIRMap: AI-Generated Radio Maps for Wireless Digital Twins

Researchers developed AIRMap, a deep-learning framework that generates radio maps for wireless network simulation over 100x faster than traditional ray tracing methods. The AI model achieves under 4 dB RMSE accuracy in 4 ms per inference and significantly outperforms traditional simulators when calibrated with field measurements.

• →AIRMap processes 2D elevation maps to predict wireless signal propagation over 100x faster than GPU-accelerated ray tracing.
• →The framework was trained on 1.2M Boston-area samples and validated across four distinct urban and rural environments.
• →Lightweight calibration using 20% of field measurements reduces median error to approximately 5% versus 50% for traditional simulators.
• →The system enables real-time wireless network simulation and digital-twin applications with near-zero error in spectral efficiency.
• →Integration into Colosseum emulator and Sionna SYS platform demonstrates practical viability for wireless infrastructure modeling.