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

Numerical weather forecasting using high-resolution physical models oftenrequires extensive computational resources on supercomputers, which diminishestheir wide usage in most real-life applications. As a remedy, applying deeplearning methods has revealed innovative solutions within this field. To thisend, we introduce a novel deep learning architecture for forecastinghigh-resolution spatio-temporal weather data. Our approach extends theconventional encoder-decoder structure by integrating Convolutional Long-shortTerm Memory and Convolutional Neural Networks. In addition, we incorporateattention and context matcher mechanisms into the model architecture. OurWeather Model achieves significant performance improvements compared tobaseline deep learning models, including ConvLSTM, TrajGRU, and U-Net. Ourexperimental evaluation involves high-scale, real-world benchmark numericalweather datasets, namely the ERA5 hourly dataset on pressure levels andWeatherBench. Our results demonstrate substantial improvements in identifyingspatial and temporal correlations with attention matrices focusing on distinctparts of the input series to model atmospheric circulations. We also compareour model with high-resolution physical models using the benchmark metrics andshow that our Weather Model is accurate and easy to interpret.

Numerical Weather Forecasting using Convolutional-LSTM with Attention and Context Matcher Mechanisms