Enhancing wind field resolution in complex terrain through a knowledge-driven machine learning approach
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911822365327360 |
|---|---|
| author | Wold, Jacob Wulff Stadtmann, Florian Rasheed, Adil Tabib, Mandar San, Omer Horn, Jan-Tore |
| author_facet | Wold, Jacob Wulff Stadtmann, Florian Rasheed, Adil Tabib, Mandar San, Omer Horn, Jan-Tore |
| contents | Atmospheric flows are governed by a broad variety of spatio-temporal scales, thus making real-time numerical modeling of such turbulent flows in complex terrain at high resolution computationally intractable. In this study, we demonstrate a neural network approach motivated by Enhanced Super-Resolution Generative Adversarial Networks to upscale low-resolution wind fields to generate high-resolution wind fields in an actual wind farm in Bessaker, Norway. The neural network-based model is shown to successfully reconstruct fully resolved 3D velocity fields from a coarser scale while respecting the local terrain and that it easily outperforms trilinear interpolation. We also demonstrate that by using appropriate cost function based on domain knowledge, we can alleviate the use of adversarial training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_10172 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Enhancing wind field resolution in complex terrain through a knowledge-driven machine learning approach Wold, Jacob Wulff Stadtmann, Florian Rasheed, Adil Tabib, Mandar San, Omer Horn, Jan-Tore Fluid Dynamics Computer Vision and Pattern Recognition Atmospheric flows are governed by a broad variety of spatio-temporal scales, thus making real-time numerical modeling of such turbulent flows in complex terrain at high resolution computationally intractable. In this study, we demonstrate a neural network approach motivated by Enhanced Super-Resolution Generative Adversarial Networks to upscale low-resolution wind fields to generate high-resolution wind fields in an actual wind farm in Bessaker, Norway. The neural network-based model is shown to successfully reconstruct fully resolved 3D velocity fields from a coarser scale while respecting the local terrain and that it easily outperforms trilinear interpolation. We also demonstrate that by using appropriate cost function based on domain knowledge, we can alleviate the use of adversarial training. |
| title | Enhancing wind field resolution in complex terrain through a knowledge-driven machine learning approach |
| topic | Fluid Dynamics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2309.10172 |