English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Large-scale deployments of low Earth orbit (LEO) satellites collect massiveamount of Earth imageries and sensor data, which can empower machine learning(ML) to address global challenges such as real-time disaster navigation andmitigation. However, it is often infeasible to download all the high-resolutionimages and train these ML models on the ground because of limited downlinkbandwidth, sparse connectivity, and regularization constraints on the imageryresolution. To address these challenges, we leverage Federated Learning (FL),where ground stations and satellites collaboratively train a global ML modelwithout sharing the captured images on the satellites. We show fundamentalchallenges in applying existing FL algorithms among satellites and groundstations, and we formulate an optimization problem which captures a uniquetrade-off between staleness and idleness. We propose a novel FL framework,named FedSpace, which dynamically schedules model aggregation based on thedeterministic and time-varying connectivity according to satellite orbits.Extensive numerical evaluations based on real-world satellite images andsatellite networks show that FedSpace reduces the training time by 1.7 days(38.6%) over the state-of-the-art FL algorithms.

FedSpace: An Efficient Federated Learning Framework at Satellites and Ground Stations