Geo2SigMap: High-Fidelity RF Signal Mapping Using Geographic Databases

TL;DR

Geo2SigMap is a machine learning framework that combines geographic databases, ray tracing, and deep learning to produce high-fidelity RF signal maps with improved accuracy over traditional methods.

Contribution

The paper introduces Geo2SigMap, integrating open-source tools and a cascaded U-Net model for efficient, high-accuracy RF signal mapping using environmental data and synthetic pre-training.

Findings

Achieves an average RMSE of 6.04 dB in RSRP prediction.

Outperforms existing methods with an RMSE improvement of 3.59 dB.

Validated with over 45,000 real-world measurement points.

Abstract

Radio frequency (RF) signal mapping, which is the process of analyzing and predicting the RF signal strength and distribution across specific areas, is crucial for cellular network planning and deployment. Traditional approaches to RF signal mapping rely on statistical models constructed based on measurement data, which offer low complexity but often lack accuracy, or ray tracing tools, which provide enhanced precision for the target area but suffer from increased computational complexity. Recently, machine learning (ML) has emerged as a data-driven method for modeling RF signal propagation, which leverages models trained on synthetic datasets to perform RF signal mapping in "unseen" areas. In this paper, we present Geo2SigMap, an ML-based framework for efficient and high-fidelity RF signal mapping using geographic databases. First, we develop an automated framework that seamlessly integrates three open-source tools: OpenStreetMap (geographic databases), Blender (computer graphics), and Sionna (ray tracing), enabling the efficient generation of large-scale 3D building maps and ray tracing models. Second, we propose a cascaded U-Net model, which is pre-trained on synthetic datasets and employed to generate detailed RF signal maps, leveraging environmental information and sparse measurement data. Finally, we evaluate the performance of Geo2SigMap via a real-world measurement campaign, where three types of user equipment (UE) collect over 45,000 data points related to cellular information from six LTE cells operating in the citizens broadband radio service (CBRS) band. Our results show that Geo2SigMap achieves an average root-mean-square-error (RMSE) of 6.04 dB for predicting the reference signal received power (RSRP) at the UE, representing an average RMSE improvement of 3.59 dB compared to existing methods.