Surface Layer Flux Machine Learning Parameterizations

Surface layer parameterizations in numerical weather prediction models provide an interface between the land surface model and the lowest levels of the atmospheric model through the calculation of momentum, sensible heat, and latent heat fluxes. Current surface layer parameterizations are based on Monin-Obukhov similarity theory, which links the near surface vertical profiles of wind, temperature, and moisture to their relevant fluxes through the use of empirical functions conditioned on the stability of the surface layer. While these empirical functions agree closely with observations under homogeneous conditions, there are many situations in which observed fluxes do not match the estimates from similarity theory. Therefore, the goal of this project is to train a diverse set of machine learning approaches on multi-year time series of surface layer and flux observations. We have acquired surface layer observations from meteorological towers in Cabauw, Netherlands, and Idaho, United States. We train random forests, gradient boosted regression, dense neural networks, and generative adversarial networks to predict friction velocity and the temperature and moisture turbulent scale terms. These terms can be used to derive the surface momentum, sensible heat, and latent heat fluxes as well as calculating stability diagnostics. We evaluate each machine learning model and identify which approaches perform best under different stability regimes and weather conditions. The best performing models are then evaluated within the WRF single column model to check for any potential biases created during the numerical model integration process. These machine learning based methods are compared to the empirical method of surface layer parameterizations in WRF model.