arXiv AI By Sai Puppala, Koushik Sinha

FractalNet-Based Heterogeneous Federated Learning for Orbital Edge Intelligence in Satellite Mega-Constellations: A Wildfire Case Study

Read the original on arXiv AI →

The paper introduces a heterogeneous federated learning approach using the FractalNet architecture tailored for satellite mega‑constellations. It formalizes contact‑window‑constrained, depth‑heterogeneous optimization and proposes a distributed path scheduler that assigns model depth based on satellite SWAP‑C constraints, predicted contacts, and training statistics. The framework includes periodic update pooling and a three‑tier agentic control plane, and is validated through a wildfire detection case study across LEO, MEO, and GEO/HEO shells, demonstrating improvements in convergence, communication efficiency, energy adaptation, and robustness.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Aug 26

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

The paper introduces OrbitALIF, a federated learning framework that performs cloud removal on low‑earth‑orbit satellites. It uses a compact 2.30 M‑parameter spiking neural network with adaptive gated fusion and spectral‑spatial hybrid attention modules, enabling both training and inference onboard. The approach achieves competitive cloud‑removal quality while consuming only 0.287 mJ per inference on neuromorphic hardware, a 72.3‑fold energy reduction compared to an equivalent ANN.

By Bohan Zhang, Chenyu Xu, Yijie Mao, Yuanming Shi
arXiv AI
Aug 10

PHOENIX: Fine-Tuned SLM-Powered Autonomous Satellite Lifetime Extension via Predictive Self-Healing and Multi-Agent AI Recovery

arXiv:2608. 07126v1 Announce Type: cross Abstract: Most CubeSats, small and low-cost satellites roughly the size of a shoebox, do not survive as long as they were designed to: a study of 178 missions found that only 48-65% remain operational after two years, against a designed lifetime of 2-5 years.

By Sumaiya Islam, Harsha Kumara Moraliyage