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 precipitation nowcasting methods have been elaborated over the centuriesbecause rain has a crucial impact on human life. Not only quantitativeprecipitation forecast (QPF) models and convolutional long short-term memory(ConvLSTM), but also various sophisticated methods such as the latest MetNet-2are emerging. In this paper, we propose a paired complementary temporalcycle-consistent adversarial networks (PCT-CycleGAN) for radar-basedprecipitation nowcasting, inspired by cycle-consistent adversarial networks(CycleGAN), which shows strong performance in image-to-image translation.PCT-CycleGAN generates temporal causality using two generator networks withforward and backward temporal dynamics in paired complementary cycles. Eachgenerator network learns a huge number of one-to-one mappings abouttime-dependent radar-based precipitation data to approximate a mapping functionrepresenting the temporal dynamics in each direction. To create robust temporalcausality between paired complementary cycles, novel connection loss isproposed. And torrential loss to cover exceptional heavy rain events is alsoproposed. The generator network learning forward temporal dynamics inPCT-CycleGAN generates radar-based precipitation data 10 minutes from thecurrent time. Also, it provides a reliable prediction of up to 2 hours withiterative forecasting. The superiority of PCT-CycleGAN is demonstrated throughqualitative and quantitative comparisons with several previous methods.

PCT-CycleGAN: Paired Complementary Temporal Cycle-Consistent Adversarial Networks for Radar-Based Precipitation Nowcasting