Abstract :
[en] Modern remote monitoring systems (RMS) 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 increasingly fine spatial resolution and higher temporal sampling rates of modern visual sensors, the resulting growth in imagery data volume imposes significant challenges on RMS 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 SemCom paradigm for the imagery transmission. 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), where semantic quality is quantified using reconstruction fidelity and perceptual similarity metrics. Second, a task-oriented framework is developed by integrating DJSCC with lightweight, application-specific models, with semantic quality measured directly through downstream task performance metrics 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 DJSCC compression, channel SNR, and semantic quality, offering actionable insights for the design of robust and efficient imagery transmission under resourceconstrained satellite links. We then investigate a resource allocation framework for satellite systems that leverages the semantic loss model to maximize the minimum weighted worst-case semantic performance among ground users executing Earth observation imagery-based applications. Extensive numerical results validate the effectiveness of the proposed loss model and the associated resource management strategy.
