Toward a Unified Semantic Loss Model for Deep JSCC-based Transmission of EO Imagery

TL;DR

This work addresses the challenge of delivering high-resolution Earth Observation imagery over bandwidth-constrained satellite links by employing Deep Joint Source-Channel Coding (DJSCC) to preserve semantic information. It introduces a data-driven, two-dimensional semantic-loss model that jointly accounts for compression ratio $\rho$ and channel SNR $\gamma$, integrating reconstruction fidelity metrics (PSNR, MSE, SSIM) and downstream task performance (e.g., EfficientViT-based classification). The core contribution is a gradient-descent-fitted unified framework that outperforms existing one-dimensional models (e.g., $\text{G. Sigmoid}$, Sum-Exp) across multiple metrics and evaluation aspects, enabling more informed design of EO transmission systems. The framework is validated on EuroSAT with EfficientViT, providing actionable guidance for robust, bandwidth-efficient, task-aware EO communications with DJSCC.

Abstract

Modern Earth Observation (EO) systems increasingly rely on high-resolution imagery to support critical applications such as environmental monitoring, disaster response, and land-use analysis. Although these applications benefit from detailed visual data, the resulting data volumes impose significant challenges on satellite communication systems constrained by limited bandwidth, power, and dynamic link conditions. To address these limitations, this paper investigates Deep Joint Source-Channel Coding (DJSCC) as an effective source-channel paradigm for the transmission of EO imagery. We focus on two complementary aspects of semantic loss in DJSCC-based systems. First, a reconstruction-centric framework is evaluated by analyzing the semantic degradation of reconstructed images under varying compression ratios and channel signal-to-noise ratios (SNR). Second, a task-oriented framework is developed by integrating DJSCC with lightweight, application-specific models (e.g., EfficientViT), with performance measured using downstream task accuracy rather than pixel-level fidelity. Based on extensive empirical analysis, we propose a unified semantic loss framework that captures both reconstruction-centric and task-oriented performance within a single model. This framework characterizes the implicit relationship between JSCC compression, channel SNR, and semantic quality, offering actionable insights for the design of robust and efficient EO imagery transmission under resource-constrained satellite links.

Figures (4)

• Figure 1: Block diagram of SC with DJSCC.
• Figure 2: Curve fitting models for the DJSCC-AWGN case.
• Figure 3: Curve fitting models for the EfficientViT-DJSCC-AWGN case.
• Figure 4: A comparison of different fitting models.