Articles | Volume 12, issue 5
https://doi.org/10.5194/gmd-12-2033-2019
https://doi.org/10.5194/gmd-12-2033-2019
Development and technical paper
 | 
24 May 2019
Development and technical paper |  | 24 May 2019

Calculating the turbulent fluxes in the atmospheric surface layer with neural networks

Lukas Hubert Leufen and Gerd Schädler

Related authors

Representing chemical history in ozone time-series predictions – a model experiment study building on the MLAir (v1.5) deep learning framework
Felix Kleinert, Lukas H. Leufen, Aurelia Lupascu, Tim Butler, and Martin G. Schultz
Geosci. Model Dev., 15, 8913–8930, https://doi.org/10.5194/gmd-15-8913-2022,https://doi.org/10.5194/gmd-15-8913-2022, 2022
Short summary
MLAir (v1.0) – a tool to enable fast and flexible machine learning on air data time series
Lukas Hubert Leufen, Felix Kleinert, and Martin G. Schultz
Geosci. Model Dev., 14, 1553–1574, https://doi.org/10.5194/gmd-14-1553-2021,https://doi.org/10.5194/gmd-14-1553-2021, 2021
Short summary
IntelliO3-ts v1.0: a neural network approach to predict near-surface ozone concentrations in Germany
Felix Kleinert, Lukas H. Leufen, and Martin G. Schultz
Geosci. Model Dev., 14, 1–25, https://doi.org/10.5194/gmd-14-1-2021,https://doi.org/10.5194/gmd-14-1-2021, 2021
Short summary

Related subject area

Climate and Earth system modeling
Baseline Climate Variables for Earth System Modelling
Martin Juckes, Karl E. Taylor, Fabrizio Antonio, David Brayshaw, Carlo Buontempo, Jian Cao, Paul J. Durack, Michio Kawamiya, Hyungjun Kim, Tomas Lovato, Chloe Mackallah, Matthew Mizielinski, Alessandra Nuzzo, Martina Stockhause, Daniele Visioni, Jeremy Walton, Briony Turner, Eleanor O'Rourke, and Beth Dingley
Geosci. Model Dev., 18, 2639–2663, https://doi.org/10.5194/gmd-18-2639-2025,https://doi.org/10.5194/gmd-18-2639-2025, 2025
Short summary
PaleoSTeHM v1.0: a modern, scalable spatiotemporal hierarchical modeling framework for paleo-environmental data
Yucheng Lin, Robert E. Kopp, Alexander Reedy, Matteo Turilli, Shantenu Jha, and Erica L. Ashe
Geosci. Model Dev., 18, 2609–2637, https://doi.org/10.5194/gmd-18-2609-2025,https://doi.org/10.5194/gmd-18-2609-2025, 2025
Short summary
The Tropical Basin Interaction Model Intercomparison Project (TBIMIP)
Ingo Richter, Ping Chang, Ping-Gin Chiu, Gokhan Danabasoglu, Takeshi Doi, Dietmar Dommenget, Guillaume Gastineau, Zoe E. Gillett, Aixue Hu, Takahito Kataoka, Noel S. Keenlyside, Fred Kucharski, Yuko M. Okumura, Wonsun Park, Malte F. Stuecker, Andréa S. Taschetto, Chunzai Wang, Stephen G. Yeager, and Sang-Wook Yeh
Geosci. Model Dev., 18, 2587–2608, https://doi.org/10.5194/gmd-18-2587-2025,https://doi.org/10.5194/gmd-18-2587-2025, 2025
Short summary
ZEMBA v1.0: an energy and moisture balance climate model to investigate Quaternary climate
Daniel F. J. Gunning, Kerim H. Nisancioglu, Emilie Capron, and Roderik S. W. van de Wal
Geosci. Model Dev., 18, 2479–2508, https://doi.org/10.5194/gmd-18-2479-2025,https://doi.org/10.5194/gmd-18-2479-2025, 2025
Short summary
Development and evaluation of a new 4DEnVar-based weakly coupled ocean data assimilation system in E3SMv2
Pengfei Shi, L. Ruby Leung, and Bin Wang
Geosci. Model Dev., 18, 2443–2460, https://doi.org/10.5194/gmd-18-2443-2025,https://doi.org/10.5194/gmd-18-2443-2025, 2025
Short summary

Cited articles

Andersen, T. and Martinez, T.: Cross validation and MLP architecture selection, in: IJCNN'99. International Joint Conference on Neural Networks. Proceedings, Washington, DC, USA, 10–16 July 1999, IEEE, 3, 1614–1619, 1999. a
Arya, P. S.: Introduction to micrometeorology, in: International Geophysics Series, San Diego, Calif., Academic Press, vol. 79, 2001. a, b, c, d
Braun, F. and Schädler, G.: Comparison of Soil Hydraulic Parameterizations for Mesoscale Meteorological Models., J. Appl. Meteorol., 44, 1116–1132, 2005. a
Broyden, C. G.: The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations, IMA J. Appl. Math., 6, 76–90, https://doi.org/10.1093/imamat/6.1.76, 1970.  a
Businger, J. A., Wyngaard, J. C., Izumi, Y., and Bradley, E. F.: Flux-Profile Relationships in the Atmospheric Surface Layer, J. Atmos. Sci., 28, 181–189, https://doi.org/10.1175/1520-0469(1971)028<0181:FPRITA>2.0.CO;2, 1971. a
Download
Short summary
An artificial neural network was used to calculate the scaling quantities u* and T*. To train and test the network, a large set of worldwide observations was used. Extensive sensitivity studies showed that a relatively small 6–3–2 network with six input parameters and one hidden layer yields satisfying results. An implementation of this network in a stand-alone land surface model showed that the neural network gives results equivalent to and sometimes better than the standard implementation.
Share