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

A data-driven model for predicting the surface temperature using neuralnetworks was proposed to alleviate the computational burden of numericalweather prediction (NWP). Our model, named TPTNet uses only 2m temperaturemeasured at the weather stations of the South Korean Peninsula as input topredict the local temperature at finite forecast hours. The turbulentfluctuation component of the temperature was extracted from the stationmeasurements by separating the climatology component accounting for the yearlyand daily variations. The effect of station altitude was then compensated byintroducing a potential temperature. The resulting turbulent potentialtemperature data at irregularly distributed stations were used as input forpredicting the turbulent potential temperature at forecast hours through threetrained networks based on convolutional neural network (CNN), Swin Transformer,and a graphic neural network (GNN). The prediction performance of our networkwas compared with that of persistence and NWP, confirming that our modeloutperformed NWP for up to 12 forecast hours.

TPTNet: A Data-Driven Temperature Prediction Model Based on Turbulent Potential Temperature