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

Probabilistic weather forecasting is critical for decision-making inhigh-impact domains such as flood forecasting, energy system planning ortransportation routing, where quantifying the uncertainty of a forecast --including probabilities of extreme events -- is essential to guide importantcost-benefit trade-offs and mitigation measures. Traditional probabilisticapproaches rely on producing ensembles from physics-based models, which samplefrom a joint distribution over spatio-temporally coherent weather trajectories,but are expensive to run. An efficient alternative is to use a machine learning(ML) forecast model to generate the ensemble, however state-of-the-art MLforecast models for medium-range weather are largely trained to producedeterministic forecasts which minimise mean-squared-error. Despite improvingskills scores, they lack physical consistency, a limitation that grows atlonger lead times and impacts their ability to characterize the jointdistribution. We introduce GenCast, a ML-based generative model for ensembleweather forecasting, trained from reanalysis data. It forecasts ensembles oftrajectories for 84 weather variables, for up to 15 days at 1 degree resolutionglobally, taking around a minute per ensemble member on a single Cloud TPU v4device. We show that GenCast is more skillful than ENS, a top operationalensemble forecast, for more than 96\% of all 1320 verification targets on CRPSand Ensemble-Mean RMSE, while maintaining good reliability and physicallyconsistent power spectra. Together our results demonstrate that ML-basedprobabilistic weather forecasting can now outperform traditional ensemblesystems at 1 degree, opening new doors to skillful, fast weather forecasts thatare useful in key applications.

GenCast: Diffusion-based ensemble forecasting for medium-range weather