Revealing the Drivers of Turbulence Anisotropy over Flat and Complex Terrain: An Interpretable Machine Learning Approach

Turbulence anisotropy was recently integrated into Monin-Obukhov Similarity Theory (MOST), extending its applicability to complex terrain and diverse surface conditions. Understanding which processes drive anisotropy over a variety of surfaces and stability conditions still remains a challenge. This study therefore employed random forest models trained on measurement data from both flat and complex terrain and including upstream terrain features, to understand the drivers of turbulence anisotropy. Two approaches were compared: using dimensional variables directly or employing non-dimensional groups as model input. To address correlation among features, we developed a new feature selection method, Recursive Effect Elimination. Finally, interpretability methods were used to identify the most influential variables. Contrary to expectations, variables directly related to terrain influence were not found to significantly impact turbulence anisotropy. Instead, non-dimensional groups of common turbulence length, time and velocity scales proved more robust than dimensional variables in isolating anisotropy drivers, enhancing model performance over complex terrain and reducing location dependence. A ratio of integral and turbulence memory length scales was found to correlate well with turbulence anisotropy in both daytime and nighttime conditions, both over flat and complex terrain. During the day, a refined stability parameter incorporating both the surface and mixed layer scaling emerged as the dominant driver of anisotropy, while at night, parameters related to rapid distortion were strong predictors.