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

The troposphere is one of the atmospheric layers where most weather phenomenaoccur. Temperature variations in the troposphere, especially at 500 hPa, atypical level of the middle troposphere, are significant indicators of futureweather changes. Numerical weather prediction is effective for temperatureprediction, but its computational complexity hinders a timely response. Thispaper proposes a novel temperature prediction approach in frameworkofphysics-informed deep learning. The new model, called PGnet, builds upon agenerative neural network with a mask matrix. The mask is designed todistinguish the low-quality predicted regions generated by the first physicalstage. The generative neural network takes the mask as prior for thesecond-stage refined predictions. A mask-loss and a jump pattern strategy aredeveloped to train the generative neural network without accumulating errorsduring making time-series predictions. Experiments on ERA5 demonstrate thatPGnet can generate more refined temperature predictions than thestate-of-the-art.

Physics-informed generative neural network: an application to troposphere temperature prediction