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

Over the past year, data-driven global weather forecasting has emerged as anew alternative to traditional numerical weather prediction. This innovativeapproach yields forecasts of comparable accuracy at a tiny fraction ofcomputational costs. Regrettably, as far as I know, existing models exclusivelyrely on regression losses, producing forecasts with substantial blurring. Suchblurring, although compromises practicality, enjoys an unfair advantage onevaluation metrics. In this paper, I present Kunyu, a global data-drivenweather forecasting model which delivers accurate predictions across acomprehensive array of atmospheric variables at 0.35{\deg} resolution. Withboth regression and adversarial losses integrated in its training framework,Kunyu generates forecasts with enhanced clarity and realism. Its performanceoutpaces even ECMWF HRES in some aspects such as the estimation of anomalyextremes, while remaining competitive with ECMWF HRES on evaluation metricssuch as RMSE and ACC. Kunyu is an important step forward in closing the utilitygap between numerical and data-driven weather prediction.

Kunyu: A High-Performing Global Weather Model Beyond Regression Losses