Spatiotemporal Multivariate Weather Prediction Network Based on CNN-Transformer
Ruowu Wu, Yandan Liang, Lianlei Lin, Zongwei Zhang, Marcin Woźniak · 2024
Read Spatiotemporal Multivariate Weather Prediction Network Based on CNN-Transformer by Ruowu Wu, Yandan Liang, Lianlei Lin, Zongwei Zhang, Marcin Woźniak (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11644947.txt.
Description
Five authors present a study from two thousand twenty-four on a neural network for weather forecasting. Good forecasts matter for daily work, disaster warning, and care of the environment. Older data-driven methods often miss how weather patterns grow and move across a region over time.
Their network joins two designs: convolutional layers that read spatial patterns, and a transformer that tracks change over time. A spatial attention block first pulls out the layout of a weather field and rebuilds it. The design also tracks how variables such as heat and wind affect each other. The aim is forecasts that are both fast and accurate enough for real use.
Catalog record
| CREATOR | Ruowu Wu, Yandan Liang, Lianlei Lin, Zongwei Zhang, Marcin Woźniak |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |