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

Previous post-processing studies on rainfall forecasts using numericalweather prediction (NWP) mainly focus on statistics-based aspects, whilelearning-based aspects are rarely investigated. Although some manually-designedmodels are proposed to raise accuracy, they are customized networks, which needto be repeatedly tried and verified, at a huge cost in time and labor.Therefore, a self-supervised neural architecture search (NAS) method withoutsignificant manual efforts called AdaNAS is proposed in this study to performrainfall forecast post-processing and predict rainfall with high accuracy. Inaddition, we design a rainfall-aware search space to significantly improveforecasts for high-rainfall areas. Furthermore, we propose a rainfall-levelregularization function to eliminate the effect of noise data during thetraining. Validation experiments have been performed under the cases of\emph{None}, \emph{Light}, \emph{Moderate}, \emph{Heavy} and \emph{Violent} ona large-scale precipitation benchmark named TIGGE. Finally, the averagemean-absolute error (MAE) and average root-mean-square error (RMSE) of theproposed AdaNAS model are 0.98 and 2.04 mm/day, respectively. Additionally, theproposed AdaNAS model is compared with other neural architecture search methodsand previous studies. Compared results reveal the satisfactory performance andsuperiority of the proposed AdaNAS model in terms of precipitation amountprediction and intensity classification. Concretely, the proposed AdaNAS modeloutperformed previous best-performing manual methods with MAE and RMSEimproving by 80.5\% and 80.3\%, respectively.

AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts