4-9 September 2022, Bonn, Germany
EMS Annual Meeting Abstracts
Vol. 19, EMS2022-472, 2022
EMS Annual Meeting 2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Using artificial neural network to better evaluate surface turbulent heat fluxes in weather and climate numerical models

maurin Zouzoua1, Sophie Bastin1, Marjolaine Chiriaco1, Marie Lothon2, Fabienne Lohou2, Laurent Barthès1, Cécile Mallet1, Solène Derrien2, Frédérique Cheruy3, Eric Bazile4, Jan Polcher3, Romain Roehrig4, and Guylaine Canut4
maurin Zouzoua et al.
  • 1Laboratoire Atmosphères, Milieux, Observations Spatiales, Guyancourt, France
  • 2Laboratoire d’Aérologie, Toulouse, France
  • 3Laboratoire de Météorologie Dynamique, École Polytechnique, Palaiseau France
  • 4Centre National de Recherches Météorologiques, Toulouse, France

The surface turbulent fluxes, namely sensible and latent heat fluxes, are keys factors governing the boundary layer processes. Therefore, their correct representation in numerical models is crucial for accurate weather forecasts and climate projections. However, the formulation of these fluxes in such models is the second source of uncertainty, leading to incorrect surface-atmosphere interactions in the simulations. Model evaluation is essential to draw development perspectives. Existing methods mostly consist of direct comparison between observed and modelled fluxes, blending other sources of errors such as incoherent grid-scale representation (soil and vegetation types) and inaccurate environmental forcing (radiative fluxes, temperature, moisture and wind speed). Thus, quantifying errors solely due to fluxes formulation is still challenging. This study, within the framework of the French project MOSAI (Model and Observation for Surface-Atmosphere Interactions), aims at proposing a novel evaluation approach to better identify the weakness of numerical models in surface turbulent fluxes formulation. The concept is to freeze the errors due to other sources by using a machine-learning model, notably a multi-layer perceptron, trained to estimate the fluxes from variables describing the conditions in the surface layer. Hourly data collected over several years at three operational instrumented sites of ACTRIS-France research infrastructure (SIRTA in Paris, Météo-pole in Toulouse and P2OA in Lannemezan), are used. Then, after adaptation to the outputs of numerical models involved in the MOSAI project (RegIPSL, LMDZ, AROME and ARPEGE), the trained-perception will be applied to assess their surface turbulent fluxes.

How to cite: Zouzoua, M., Bastin, S., Chiriaco, M., Lothon, M., Lohou, F., Barthès, L., Mallet, C., Derrien, S., Cheruy, F., Bazile, E., Polcher, J., Roehrig, R., and Canut, G.: Using artificial neural network to better evaluate surface turbulent heat fluxes in weather and climate numerical models, EMS Annual Meeting 2022, Bonn, Germany, 5–9 Sep 2022, EMS2022-472, https://doi.org/10.5194/ems2022-472, 2022.

Supporters & sponsors