Sensible and Latent Heat Flux Diagnosis with Multilayer Perceptrons on Multi-Year Falkenberg Tower Data

The vertical fluxes of sensible and latent heat represent a major contribution to the exchange of energy between the land surface and the atmosphere. Their adequate description in numerical weather prediction and climate models is essential to realistically simulate near-surface weather conditions. Traditionally, these heat fluxes are parameterized relying on Monin-Obukhov Similarity Theory (MOST) or the use of the Bulk-Richardson number. These parameterizations are based on differences in wind speed, air temperature, and humidity between adjacent measurement or model levels. Wulfmeyer et al. (2022) estimated the heat fluxes with machine learning approaches and achieved a higher accuracy compared to MOST. However, their analysis is based on a rather short data period in August 2017 at three nearby locations in Oklahoma, USA, which limits the generalizability of the results. In our study we replicate and expand the findings from Wulfmeyer et al. (2022) on a dataset from the boundary layer field site (GM) Falkenberg of the German Meteorological Service over a period of twelve years, covering various seasons and synoptic weather situations. Our findings support the role of radiation (which is not considered in MOST) as a dominant predictor for both the latent and sensible heat fluxes. We also studied the performance of the machine learning algorithm for datasets of different length (one month as in Wulfmeyer et al., 2022, the same month over twelve years, and complete annual data sets) and the impact of removing redundancy in the selection of the predictor variables. In future research we intend to investigate the role of other predictor variables, such as soil moisture, to assess the generalizability of the relations, to judge their performance under extreme conditions, and to derive simple but universally applicable parameterizations.