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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A common class of problems in remote sensing is scene classification, afundamentally important task for natural hazards identification, geographicimage retrieval, and environment monitoring. Recent developments in this fieldrely label-dependent supervised learning techniques which is antithetical tothe 35 petabytes of unlabelled satellite imagery in NASA GIBS. To solve thisproblem, we establish CELESTIAL-a self-supervised learning pipeline foreffectively leveraging sparsely-labeled satellite imagery. This pipelinesuccessfully adapts SimCLR, an algorithm that first learns imagerepresentations on unlabelled data and then fine-tunes this knowledge on theprovided labels. Our results show CELESTIAL requires only a third of the labelsthat the supervised method needs to attain the same accuracy on an experimentaldataset. The first unsupervised tier can enable applications such as reverseimage search for NASA Worldview (i.e. searching similar atmospheric phenomenonover years of unlabelled data with minimal samples) and the second supervisedtier can lower the necessity of expensive data annotation significantly. In thefuture, we hope we can generalize the CELESTIAL pipeline to other data types,algorithms, and applications.

CELESTIAL: Classification Enabled via Labelless Embeddings with Self-supervised Telescope Image Analysis Learning