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/

Zendy Plus

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

Zendy Tools

Zendy Open

We describe our submission to the Extreme Value Analysis 2019 Data Challengein which teams were asked to predict extremes of sea surface temperatureanomaly within spatio-temporal regions of missing data. We present acomputational framework which reconstructs missing data using convolutionaldeep neural networks. Conditioned on incomplete data, we employautoencoder-like models as multivariate conditional distributions from whichpossible reconstructions of the complete dataset are sampled using imputednoise. In order to mitigate bias introduced by any one particular model, aprediction ensemble is constructed to create the final distribution of extremalvalues. Our method does not rely on expert knowledge in order to accuratelyreproduce dynamic features of a complex oceanographic system with minimalassumptions. The obtained results promise reusability and generalization toother domains.

BlackBox: Generalizable Reconstruction of Extremal Values from Incomplete Spatio-Temporal Data