Enhancing wind field resolution in complex terrain through a knowledge-driven machine learning approach

TL;DR

This paper presents a neural network method inspired by super-resolution GANs to upscale low-resolution wind fields into high-resolution data in complex terrains, outperforming traditional interpolation methods.

Contribution

The study introduces a knowledge-driven neural network model that effectively reconstructs high-resolution wind fields from coarse data, reducing reliance on adversarial training.

Findings

Successfully reconstructs 3D wind velocity fields in complex terrain.

Outperforms trilinear interpolation in accuracy.

Alleviates adversarial training with domain knowledge-based cost functions.

Abstract

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.