# ORBITALIF: An Efficient Spiking Federated Learning Framework for Onboard Cloud Removal

arXiv: https://arxiv.org/abs/2608.24073 · HTML: https://mlsanity.com/paper/2608.24073/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 25 Aug 2026.

## Builds on (most cited first, 9 of 9)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Ground-Assisted Federated Learning in LEO Satellite Constellations](https://mlsanity.com/paper/2109.01348/) (2021)
- [Diffusion Enhancement for Cloud Removal in Ultra-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2401.15105/) (2024)
- [Satellite Federated Edge Learning: Architecture Design and Convergence Analysis](https://mlsanity.com/paper/2404.01875/) (2024)
- [FSTA-SNN:Frequency-based Spatial-Temporal Attention Module for Spiking Neural Networks](https://mlsanity.com/paper/2501.14744/) (2024)
- [Memory augment is All You Need for image restoration](https://mlsanity.com/paper/2309.01377/) (2023)
- [DFedSat: Communication-Efficient and Robust Decentralized Federated Learning for LEO Satellite Constellations](https://mlsanity.com/paper/2407.05850/) (2024)
- [Exploring the Potentials of Spiking Neural Networks for Image Deraining](https://mlsanity.com/paper/2512.02258/) (2025)
- [Brain-Inspired Decentralized Satellite Learning in Space Computing Power Networks](https://mlsanity.com/paper/2501.15995/) (2025)

## Abstract (arXiv)

Low-earth-orbit (LEO) satellites enable high-resolution, large-scale Earth observation for applications such as disaster monitoring and environmental surveillance. However, cloud coverage often obscures the Earth's surface, and conventional cloud-removal pipelines that download cloudy images to ground stations for processing suffer from limited contact windows, constrained satellite-to-ground bandwidth, and high latency. In this work, we propose a novel satellite federated learning framework for cloud removal across LEO constellations, named orbital attention leaky integrate-and-fire (OrbitALIF). OrbitALIF performs both onboard training and inference using a compact 2.30,M-parameter spiking neural network (SNN) backbone with an adaptive gated fusion module (AGFM) and a spectral-spatial hybrid attention module (SHAM), combined with a decentralized federated learning strategy that shares model weights via inter-satellite links. Our experiments show that OrbitALIF achieves competitive cloud removal quality while consuming only 0.287,mJ per inference on neuromorphic hardware, a 72.3 times (98.6%) energy reduction versus an equivalent artificial neural network (ANN).