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

We consider the problem of short-term forecasting of surface wind speedprobability distribution. Our approach simply consists in predicting theparameters of a probability density function by training a neural network modelwhose loss function is the log-likelihood provided by this distribution. Wecompare different possibilities among a set of laws that have been previouslyconsidered in the context of modeling wind fluctuations. Our results rely ontwo different hourly wind speed datasets: the first one has been recorded byM\'et\'eo-France in Corsica (South France), a very mountainous Mediterraneanisland while the other one relies on KNMI database that provides records ofvarious stations over the Netherlands, a very flat country in NorthwesternEurope. A first part of our work globally unveils the superiority of theso-called "Multifractal Rice" (M-Rice) distribution over alternative parametricmodels, showcasing its potential as a reliable tool for wind speed forecasting.This family of distributions has been proposed in the context of modeling windspeed fluctuations as a random cascade model. For all stations in both regions,it consistently provides better results regardless the considered probabilisticscoring rule or forecasting horizon. Our second findings demonstratesignificant enhancements in forecasting accuracy when one incorporates windspeed data from proximate weather stations, in full agreement with the resultsobtained formerly for point-wise wind speed prediction. Moreover, we revealthat the incorporation of ERA5 reanalysis of 10 m wind data from neighboringgrid points contributes to a substantial improvement at time horizon $h=6$hours. We also find out that accounting for more explanatory factors mainlyincreases the resolution performances while it does not change the reliabilitycontribution to the prediction performance metric considered (CRPS).

Improving probabilistic wind speed forecasting using M-Rice distribution and spatial data integration