Edge Intelligence for Satellite-based Earth Observation: Scheduling Image Acquisition and Processing

2026-04-07

AI Summary

This work addresses the bottlenecks in space-to-ground links and ground-based computing that hinder real-time processing of massive remote sensing data from low Earth orbit (LEO) satellite constellations. To overcome these challenges, the authors propose an energy-aware edge intelligence framework that jointly optimizes imaging scheduling and semantic task allocation. The framework employs a turbulence-aware observation scheduling mechanism to enhance image quality and a satellite-ground collaborative semantic processing strategy to achieve task-agnostic optimization. Integrating a coupled optimization model, YOLOv8-based object detection, performance modeling of heterogeneous edge platforms, and quantification of atmospheric turbulence effects, the approach significantly increases the number of detectable maritime targets, improves image fidelity, and reduces energy consumption through intra-constellation cooperative edge processing, outperforming conventional data-downlink-centric architectures.

Abstract

Modern Earth Observation (EO) missions generate massive volumes of imagery that challenge existing downlink and ground-processing capabilities, particularly for time-critical applications. This work investigates how a low Earth orbit (LEO) satellite constellation equipped with heterogeneous edge computing resources can enable real-time semantic processing of data acquired by EO satellites. We introduce an energy-aware framework that optimizes the use of resources accounting for data acquisition, computing, and communication constraints. Although we focus on maritime surveillance, the formulation is task-agnostic and accommodates a broad class of semantic and goal-oriented inference problems. Specifically, we formulate two coupled optimization problems: (i) observation scheduling, which selects image acquisition opportunities while accounting for turbulence-induced image degradation and energy budget, and (ii) processing scheduling, which allocates semantic workloads across onboard and ground processors. We evaluate these mechanisms for the task of detection and localization of vessels, for which we quantify the benefits of turbulence-aware observation scheduling for preserving image quality and experimentally characterize the execution-time distribution of YOLOv8 on different computing platforms. Results demonstrate that task- and turbulence-aware observation scheduling can significantly improve the quality and quantity of observed targets. Furthermore, cooperative edge processing within the constellation substantially reduces power consumption compared to traditional downlink-centric architectures. These findings highlight the potential of distributed edge intelligence to enhance the responsiveness and autonomy of future satellite-based EO systems.

Problem

• Edge Intelligence
• Earth Observation
• Scheduling
• Image Acquisition
• Processing

Innovation

• Edge Intelligence
• Observation Scheduling
• Turbulence-aware Imaging
• Onboard Processing
• LEO Constellation