the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
A two-folds deep learning strategy to correct and downscale winds over mountains
Louis Le Toumelin
Isabelle Gouttevin
Clovis Galiez
Nora Helbig
Abstract. Assessing wind fields at a local scale in mountainous terrain has long been a scientific challenge partly because of the complex interaction between large-scale flows and local topography. Traditionally, the operational applications that require high resolution wind forcings rely on downscaled outputs of numerical weather predictions systems. Downscaling models either proceed from a function that links large scale wind fields to local observations (hence including a corrective step), or use operations that account for local scale processes, through statistics or dynamical simulations, and without prior knowledge of large scale modeling errors. This work presents a strategy to first correct and then downscale the wind fields of the numerical weather prediction model AROME operating at 1300 m grid spacing, by using a modular architecture composed of two artificial neural networks and the DEVINE downscaling model. We show that our method is able to first correct the wind direction and speed from the large scale model (1300 m), and then accurately downscale it to a local scale (30 m) by using the DEVINE downscaling model. The innovative aspect of our method lies in its optimization scheme that accounts for the downscaling step in the computations of the corrections of the coarse scale wind fields. This modular architecture yields competitive results without suppressing the versatility of the downscaling model DEVINE, which remains unbounded to any wind observations.
- Preprint
(8421 KB) -
Supplement
(206 KB) - BibTeX
- EndNote
Louis Le Toumelin et al.
Status: open (until 05 Jul 2023)
Louis Le Toumelin et al.
Louis Le Toumelin et al.
Viewed
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
162 | 36 | 4 | 202 | 10 | 1 | 0 |
- HTML: 162
- PDF: 36
- XML: 4
- Total: 202
- Supplement: 10
- BibTeX: 1
- EndNote: 0
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1