# Fast model inference and training on-board of Satellites

arXiv: https://arxiv.org/abs/2307.08700 · HTML: https://mlsanity.com/paper/2307.08700/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 16 references that are in the map.
- First posted on arXiv 17 Jul 2023.

## Builds on (most cited first, 1 of 1)

- [Fast and accurate object detection in high resolution 4K and 8K video using GPUs](https://mlsanity.com/paper/1810.10551/) (2018)

## Built on by (most cited first, 11 of 11)

- [HyperspectralViTs: General Hyperspectral Models for On-board Remote Sensing](https://mlsanity.com/paper/2410.17248/) (2024)
- [Satellite Federated Edge Learning: Architecture Design and Convergence Analysis](https://mlsanity.com/paper/2404.01875/) (2024)
- [Training-free AI for Earth Observation Change Detection using Physics Aware Neuromorphic Networks](https://mlsanity.com/paper/2506.04285/) (2025)
- [Optimizing Methane Detection On Board Satellites: Speed, Accuracy, and Low-Power Solutions for Resource-Constrained Hardware](https://mlsanity.com/paper/2507.01472/) (2025)
- [Domain Adaptation for Satellite-Borne Hyperspectral Cloud Detection](https://mlsanity.com/paper/2309.02150/) (2023)
- [Bringing Federated Learning to Space](https://mlsanity.com/paper/2511.14889/) (2025)
- [First On-Orbit Demonstration of a Geospatial Foundation Model](https://mlsanity.com/paper/2512.01181/) (2025)
- [Rapid Distributed Fine-tuning of a Segmentation Model Onboard Satellites](https://mlsanity.com/paper/2411.17831/) (2024)
- [Efficient SAR Vessel Detection for FPGA-Based On-Satellite Sensing](https://mlsanity.com/paper/2507.04842/) (2025)
- [SAT-Edge-Agent: Hardware-in-the-Loop Edge-Agent Orchestration for Onboard Satellite Intelligence](https://mlsanity.com/paper/2608.03728/) (2026)
- [Learning in Orbit: Onboard Training and Closed-Loop Attitude Control with a Thermal Segmentation Model on a Spacecraft](https://mlsanity.com/paper/2610.19122/) (2026)

## Abstract (arXiv)

Artificial intelligence onboard satellites has the potential to reduce data transmission requirements, enable real-time decision-making and collaboration within constellations. This study deploys a lightweight foundational model called RaVAEn on D-Orbit's ION SCV004 satellite. RaVAEn is a variational auto-encoder (VAE) that generates compressed latent vectors from small image tiles, enabling several downstream tasks. In this work we demonstrate the reliable use of RaVAEn onboard a satellite, achieving an encoding time of 0.110s for tiles of a 4.8x4.8 km2 area. In addition, we showcase fast few-shot training onboard a satellite using the latent representation of data. We compare the deployment of the model on the on-board CPU and on the available Myriad vision processing unit (VPU) accelerator. To our knowledge, this work shows for the first time the deployment of a multi-task model on-board a CubeSat and the on-board training of a machine learning model.