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

Humans excel at detecting interesting patterns in images, for example thosetaken from satellites. This kind of anecdotal evidence can lead to thediscovery of new phenomena. However, it is often difficult to gather enoughdata of subjective features for significant analysis. This paper presents anexample of how two tools that have recently become accessible to a wide rangeof researchers, crowd-sourcing and deep learning, can be combined to exploresatellite imagery at scale. In particular, the focus is on the organization ofshallow cumulus convection in the trade wind regions. Shallow clouds play alarge role in the Earth's radiation balance yet are poorly represented inclimate models. For this project four subjective patterns of organization weredefined: Sugar, Flower, Fish and Gravel. On cloud labeling days at twoinstitutes, 67 scientists screened 10,000 satellite images on a crowd-sourcingplatform and classified almost 50,000 mesoscale cloud clusters. This dataset isthen used as a training dataset for deep learning algorithms that make itpossible to automate the pattern detection and create global climatologies ofthe four patterns. Analysis of the geographical distribution and large-scaleenvironmental conditions indicates that the four patterns have some overlapwith established modes of organization, such as open and closed cellularconvection, but also differ in important ways. The results and dataset fromthis project suggests promising research questions. Further, this studyillustrates that crowd-sourcing and deep learning complement each other wellfor the exploration of image datasets.

Combining crowd-sourcing and deep learning to explore the meso-scale organization of shallow convection