Knowledge-Driven 3D Semantic Spectrum Map: KE-VQ-Transformer Based UAV Semantic Communication and Map Completion

2025-12-24

AI Summary

In complex communication environments, sparse sampling severely degrades the accuracy, physical consistency, and computational efficiency of 3D spectrum map reconstruction. Method: This paper proposes a knowledge-enhanced semantic communication framework for air-ground collaborative spectrum monitoring. It jointly leverages sparse spatial sampling by UAVs and intelligent ground-based completion, introducing a novel physics-model-driven knowledge constraint mechanism. We design the KE-VQ-Transformer architecture, integrating sparse-window attention, multi-scale feature modeling, and embedded signal propagation models. A new evaluation metric—KMSE/RKMSE—is proposed, and the model is trained via a hybrid objective combining offline supervised and online unsupervised knowledge losses. Results: Experiments demonstrate that our method significantly outperforms state-of-the-art approaches in RKMSE, achieving high-fidelity 3D spectrum map reconstruction with improved physical consistency, robustness, and interpretability, while substantially reducing computational overhead.

Technology Category

• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data
• Machine Learning: Multimodal Learning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Security and Privacy: Large-scale security measurements

Abstract

Artificial intelligence (AI)-native three-dimensional (3D) spectrum maps are crucial in spectrum monitoring for intelligent communication networks. However, it is challenging to obtain and transmit 3D spectrum maps in a spectrum-efficient, computation-efficient, and AI-driven manner, especially under complex communication environments and sparse sampling data. In this paper, we consider practical air-to-ground semantic communications for spectrum map completion, where the unmanned aerial vehicle (UAV) measures the spectrum at spatial points and extracts the spectrum semantics, which are then utilized to complete spectrum maps at the ground device. Since statistical machine learning can easily be misled by superficial data correlations with the lack of interpretability, we propose a novel knowledge-enhanced semantic spectrum map completion framework with two expert knowledge-driven constraints from physical signal propagation models. This framework can capture the real-world physics and avoid getting stuck in the mindset of superficial data distributions. Furthermore, a knowledge-enhanced vector-quantized Transformer (KE-VQ-Transformer) based multi-scale low-complex intelligent completion approach is proposed, where the sparse window is applied to avoid ultra-large 3D attention computation, and the multi-scale design improves the completion performance. The knowledge-enhanced mean square error (KMSE) and root KMSE (RKMSE) are introduced as novel metrics for semantic spectrum map completion that jointly consider the numerical precision and physical consistency with the signal propagation model, based on which a joint offline and online training method is developed with supervised and unsupervised knowledge loss. The simulation demonstrates that our proposed scheme outperforms the state-of-the-art benchmark schemes in terms of RKMSE.

Problem

• Efficiently obtaining and transmitting 3D spectrum maps in AI-driven networks
• Completing spectrum maps under sparse data and complex environments
• Enhancing semantic communication with physics-based constraints for accuracy

Innovation

• Knowledge-enhanced semantic framework with physical constraints
• KE-VQ-Transformer with sparse window and multi-scale design
• Joint offline-online training using KMSE and RKMSE metrics