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

Running high-resolution physical models is computationally expensive andessential for many disciplines. Agriculture, transportation, and energy aresectors that depend on high-resolution weather models, which typically consumemany hours of large High Performance Computing (HPC) systems to deliver timelyresults. Many users cannot afford to run the desired resolution and are forcedto use low resolution output. One simple solution is to interpolate results forvisualization. It is also possible to combine an ensemble of low resolutionmodels to obtain a better prediction. However, these approaches fail to capturethe redundant information and patterns in the low-resolution input that couldhelp improve the quality of prediction. In this paper, we propose and evaluatea strategy based on a deep neural network to learn a high-resolutionrepresentation from low-resolution predictions using weather forecast as apractical use case. We take a supervised learning approach, since obtaininglabeled data can be done automatically. Our results show significantimprovement when compared with standard practices and the strategy is stilllightweight enough to run on modest computer systems.

DeepDownscale: a Deep Learning Strategy for High-Resolution Weather Forecast