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

Accurately forecasting extreme rainfall is notoriously difficult, but is alsoever more crucial for society as climate change increases the frequency of suchextremes. Global numerical weather prediction models often fail to captureextremes, and are produced at too low a resolution to be actionable, whileregional, high-resolution models are hugely expensive both in computation andlabour. In this paper we explore the use of deep generative models tosimultaneously correct and downscale (super-resolve) global ensemble forecastsover the Continental US. Specifically, using fine-grained radar observations asour ground truth, we train a conditional Generative Adversarial Network --coined CorrectorGAN -- via a custom training procedure and augmented lossfunction, to produce ensembles of high-resolution, bias-corrected forecastsbased on coarse, global precipitation forecasts in addition to other relevantmeteorological fields. Our model outperforms an interpolation baseline, as wellas super-resolution-only and CNN-based univariate methods, and approaches theperformance of an operational regional high-resolution model across an array ofestablished probabilistic metrics. Crucially, CorrectorGAN, once trained,produces predictions in seconds on a single machine. These results raiseexciting questions about the necessity of regional models, and whetherdata-driven downscaling and correction methods can be transferred to data-poorregions that so far have had no access to high-resolution forecasts.

Increasing the accuracy and resolution of precipitation forecasts using deep generative models