Adaptable Deep Joint Source-and-Channel Coding for Small Satellite Applications

TL;DR

This paper introduces an adaptable deep joint source-and-channel coding method using neural networks for small satellite Earth observation data transmission, effectively handling varying channel conditions with a single model.

Contribution

It proposes a single neural network architecture with attention modules for adaptable satellite communication, reducing overhead compared to multiple models for different channel states.

Findings

Achieves comparable performance to multiple separate neural networks.

Handles diverse satellite channel conditions effectively.

Uses Sentinel-2 imagery for realistic training and evaluation.

Abstract

Earth observation with small satellites serves a wide range of relevant applications. However, significant advances in sensor technology (e.g., higher resolution, multiple spectrums beyond visible light) in combination with challenging channel characteristics lead to a communication bottleneck when transmitting the collected data to Earth. Recently, joint source coding, channel coding, and modulation based on neuronal networks has been proposed to combine image compression and communication. Though this approach achieves promising results when applied to standard terrestrial channel models, it remains an open question whether it is suitable for the more complicated and quickly varying satellite communication channel. In this paper, we consider a detailed satellite channel model accounting for different shadowing conditions and train an encoder-decoder architecture with realistic Sentinel-2 satellite imagery. In addition, to reduce the overhead associated with applying multiple neural networks for various channel states, we leverage attention modules and train a single adaptable neural network that covers a wide range of different channel conditions. Our evaluation results show that the proposed approach achieves similar performance when compared to less space-efficient schemes that utilize separate neuronal networks for differing channel conditions.