Satellite Edge Artificial Intelligence with Large Models: Architectures and Technologies

2025-04-02

AI Summary

To address high latency and low data trustworthiness caused by raw-data downlink, as well as the challenges of deploying large AI models in resource-constrained, topologically dynamic space networks, this paper proposes a novel on-board edge AI paradigm. Our method introduces (i) the first satellite-based federated fine-tuning architecture and (ii) a microservice-enabled edge large language model (LLM) inference framework, integrating satellite federated learning, task-oriented communication, multi-task multimodal inference, and space–ground collaborative optimization. The resulting Space Computing and Communication Network (Space-CPN) enables on-orbit LLM training and lightweight inference, reducing end-to-end latency by up to 60% and significantly improving real-time performance and data trustworthiness for critical applications such as extreme weather forecasting and disaster monitoring. This work provides a system-level architectural foundation and key enabling technologies for operational deployment of large models on satellites.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Large language models for search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Driven by the growing demand for intelligent remote sensing applications, large artificial intelligence (AI) models pre-trained on large-scale unlabeled datasets and fine-tuned for downstream tasks have significantly improved learning performance for various downstream tasks due to their generalization capabilities. However, many specific downstream tasks, such as extreme weather nowcasting (e.g., downburst and tornado), disaster monitoring, and battlefield surveillance, require real-time data processing. Traditional methods via transferring raw data to ground stations for processing often cause significant issues in terms of latency and trustworthiness. To address these challenges, satellite edge AI provides a paradigm shift from ground-based to on-board data processing by leveraging the integrated communication-and-computation capabilities in space computing power networks (Space-CPN), thereby enhancing the timeliness, effectiveness, and trustworthiness for remote sensing downstream tasks. Moreover, satellite edge large AI model (LAM) involves both the training (i.e., fine-tuning) and inference phases, where a key challenge lies in developing computation task decomposition principles to support scalable LAM deployment in resource-constrained space networks with time-varying topologies. In this article, we first propose a satellite federated fine-tuning architecture to split and deploy the modules of LAM over space and ground networks for efficient LAM fine-tuning. We then introduce a microservice-empowered satellite edge LAM inference architecture that virtualizes LAM components into lightweight microservices tailored for multi-task multimodal inference. Finally, we discuss the future directions for enhancing the efficiency and scalability of satellite edge LAM, including task-oriented communication, brain-inspired computing, and satellite edge AI network optimization.

Problem

• Real-time processing for remote sensing tasks
• Scalable large AI model deployment in space
• Efficient satellite-edge AI training and inference

Innovation

• Satellite edge AI for real-time processing
• Federated fine-tuning over space networks
• Microservice-empowered lightweight LAM inference