FARM: Foundational Aerial Radio Map for Intelligent Low-Altitude Networking

TL;DR

FARM is a novel foundation model utilizing a high-resolution dataset and deep learning techniques to accurately characterize aerial radio environments for low-altitude networking.

Contribution

It introduces a unified aerial radio map estimation framework with a new dataset and deep learning architecture, improving accuracy and generalization over existing methods.

Findings

FARM outperforms state-of-the-art benchmarks in accuracy.

The model demonstrates strong generalization to unseen scenarios.

Extensive experiments validate the effectiveness of FARM.

Abstract

Precise aerial radio environment characterization is vital for low-altitude planning. However, existing datasets and estimation methods lack the high-resolution granularity required for complex aerial spaces. Additionally, current schemes suffer from poor generalization and heavy reliance on environmental priors. To address these gaps, this paper introduces FARM, a pioneering foundation model for unified aerial radio map estimation. This model is supported by a newly curated, high-resolution dataset featuring multi-band and multi-antenna configurations specifically for low-altitude environments. FARM utilizes a masked autoencoder to extract deep latent representations of the aerial radio environment, which then guide a diffusion-based decoder to generate high-fidelity signal distributions through iterative refinement. Extensive experiments demonstrate that FARM significantly outperforms state-of-the-art benchmarks and exhibits superior generalization capabilities across unseen scenarios. Ultimately, FARM serves as a critical infrastructure for low-altitude economy by enabling autonomous aerial logistics and intelligent urban networking.