Semantic Forwarding and Codebook-Enhanced Model Division Multiple Access for Satellite-Terrestrial Networks

TL;DR

A vector-quantized joint semantic coding and modulation scheme is developed, in which the semantic encoder and semantic codebook are jointly optimized to shape the constellation symbol distribution, improving channel adaptability and semantic compression efficiency.

Abstract

Satellite-terrestrial communications are severely constrained by high path loss, limited spectrum resources, and time-varying channel conditions, rendering conventional bit-level transmission schemes inefficient and fragile, particularly in low signal-to-noise ratio (SNR) regimes. Semantic communication has emerged as a promising paradigm to address these challenges by prioritizing task-relevant information over exact bit recovery. In this paper, we propose a semantic forwarding-based semantic communication (SFSC) framework optimized for satellite-terrestrial networks. Specifically, we develop a vector-quantized joint semantic coding and modulation scheme, in which the semantic encoder and semantic codebook are jointly optimized to shape the constellation symbol distribution, improving channel adaptability and semantic compression efficiency. To mitigate noise accumulation and reduce on-board computational burden, we introduce a satellite semantic forwarding mechanism, enabling relay satellites to forward signals directly at the semantic level without full decoding and re-encoding. Furthermore, we design a channel-aware semantic reconstruction scheme based on feature-wise linear modulation (FiLM) to fuse the received SNR with semantic features, enhancing robustness under dynamic channel conditions. To support multi-user access, we further propose a codebook split-enhanced model division multiple access (CS-MDMA) method to improve spectral efficiency. Simulation results show that the proposed SFSC framework achieves a peak signal-to-noise ratio (PSNR) gain of approximately 7.9 dB over existing benchmarks in the low-SNR regime, demonstrating its effectiveness for robust and spectrum-efficient semantic transmission in satellite-terrestrial networks.

Figures (9)

• Figure 1: System model of relay-assisted LEO satellite-terrestrial communications. The ground gateway connects to the satellite via the feeder link, while the satellite serves multiple users through the service link. Furthermore, different satellites are interconnected via inter-satellite links to achieve wider network coverage.
• Figure 2: Semantic forwarding-based semantic communication framework for satellite-terrestrial networks. The UT encodes original image into semantic codebook indices via VQ-PEM. The satellite utilizes a semantic forwarder to encode the received signal into recovered semantic codebook indices. The gateway reconstructs image via index restoration and semantic decoding.
• Figure 3: Illustration of the SNR adaptive feature-wise linear modulation. By concatenating SNR with spatial coordinate maps, the generator outputs the channel scaling factor $\boldsymbol\gamma$ and channel shifting factor $\boldsymbol\beta$ to modulate intermediate feature maps via affine transformation.
• Figure 4: Framework of downlink CS-MDMA transmission from the satellite relay node to the ground receivers, with detailed neural network structures presented. It illustrates the satellite relay node employing the common orthogonal codebook to produce common signals, and deriving private signals via the enhanced feature extractor. At the receiver, the index restorers and enhanced feature restorers cooperatively recover the latent semantic features for high-fidelity decoding.
• Figure 5: Illustration of the process of codebook split. A common orthogonal codebook is divided into disjoint user-specific sub-codebooks. This enables the system to map combined features to unique indices and decouple them into private semantics.