Spiking neural networks with specialized modules can effectively perform cloud removal in satellite imagery onboard LEO satellites using federated learning

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

http://arxiv.org/abs/2608.24073v1