Enhancing wind field resolution in complex terrain through a knowledge-driven machine learning approach
This work addresses the challenge of real-time wind field prediction for wind farms in complex terrain, representing an incremental improvement by adapting existing super-resolution methods with domain knowledge.
The study tackled the problem of computationally intractable high-resolution wind field modeling in complex terrain by developing a neural network approach to upscale low-resolution wind fields, successfully reconstructing fully resolved 3D velocity fields that outperform trilinear interpolation.
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.