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 prediction (NWP) may be inaccurate or biased due toincomplete atmospheric physical processes, insufficient spatial-temporalresolution, and inherent uncertainty of weather. Previous studies haveattempted to correct biases by using handcrafted features and domain knowledge,or by applying general machine learning models naively. They do not fullyexplore the complicated meteorologic interactions and spatial dependencies inthe atmosphere dynamically, which limits their applicability in NWPbias-correction. Specifically, weather factors interact with each other incomplex ways, and these interactions can vary regionally. In addition, theinteractions between weather factors are further complicated by the spatialdependencies between regions, which are influenced by varied terrain andatmospheric motions. To address these issues, we propose WeatherGNN, an NWPbias-correction method that utilizes Graph Neural Networks (GNN) to learnmeteorologic and geographic relationships in a unified framework. Our approachincludes a factor-wise GNN that captures meteorological interactions withineach grid (a specific location) adaptively, and a fast hierarchical GNN thatcaptures spatial dependencies between grids dynamically. Notably, the fasthierarchical GNN achieves linear complexity with respect to the number ofgrids, enhancing model efficiency and scalability. Our experimental results ontwo real-world datasets demonstrate the superiority of WeatherGNN in comparisonwith other SOTA methods, with an average improvement of 40.50\% on RMSEcompared to the original NWP.

WeatherGNN: Exploiting Complicated Relationships in Numerical Weather Prediction Bias Correction