EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Variational Autoencoder to Obtain High Resolution Wind Fields from Reanalysis Data

Bernhard Rösch, Konstantin Zacharias, Luca Fabian Schlaug, Daniel Westerfeld, Stefan Geißelsöder, Alexander Buchele

Wind · 18.03.2026 · 6 (1) · 13

DOI: 10.3390/wind6010013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Wind, online erschienen am 18.03.2026. Verfasst von Bernhard Rösch und 5 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Federal Ministry of Transport and Digital Infrastructure.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate wind flow prediction is essential for various applications, including the placement of wind turbines and a multitude of environmental assessments. Traditionally this can be achieved by using time-consuming computational fluid dynamics (CFD) simulations on reanalysis data. This study explores the performance of an autoencoder (AE) and a variational autoencoder (VAE) in approximating downscaled wind speed and direction using real-world reanalysis data and reference geo- and vegetation data. The AE model was trained for 2000 epochs and demonstrates the ability to replicate wind patterns with a mean absolute error (MAE) of approximately −0.9. However, the AE model exhibited a consistent underestimation of wind speeds and a directional shift of approximately 10 degrees compared to CFD reference simulations. The VAE model produced visually improved results, capturing complex wind flow structures more accurately than the AE model. It mainly achieves better local accuracy and a reduced variance of the results. The overall result suggests that while autoencoders can approximate wind flow patterns, challenges remain in capturing the full variability of wind speeds and directions with sufficient precision. The study highlights the importance of balancing reconstruction accuracy and latent space regularization in VAE models. Future work should focus on optimizing model architecture and training strategies to enhance accuracy, prediction reliability and generalizability across diverse wind conditions and various locations.

Förderung

  • Federal Ministry of Transport and Digital Infrastructure

Zitieren

APA

Rösch, B., Zacharias, K., Schlaug, L. F., Westerfeld, D., Geißelsöder, S., & Buchele, A. (2026). Variational Autoencoder to Obtain High Resolution Wind Fields from Reanalysis Data. Wind, 6(1), 13. https://doi.org/10.3390/wind6010013

Vancouver

Rösch B, Zacharias K, Schlaug LF, Westerfeld D, Geißelsöder S, Buchele A. Variational Autoencoder to Obtain High Resolution Wind Fields from Reanalysis Data. Wind. 2026;6(1):13. doi:10.3390/wind6010013

BibTeX
@article{Rsch2026,
  author = {Rösch, Bernhard and Zacharias, Konstantin and Schlaug, Luca Fabian and Westerfeld, Daniel and Geißelsöder, Stefan and Buchele, Alexander},
  title = {Variational Autoencoder to Obtain High Resolution Wind Fields from Reanalysis Data},
  journal = {Wind},
  year = {2026},
  volume = {6},
  number = {1},
  pages = {13},
  doi = {10.3390/wind6010013}
}
Kostenlos starten →