Journal cover Journal topic
Geoscientific Model Development An interactive open-access journal of the European Geosciences Union
Journal topic

Journal metrics

Journal metrics

  • IF value: 4.252 IF 4.252
  • IF 5-year value: 4.890 IF 5-year 4.890
  • CiteScore value: 4.49 CiteScore 4.49
  • SNIP value: 1.539 SNIP 1.539
  • SJR value: 2.404 SJR 2.404
  • IPP value: 4.28 IPP 4.28
  • h5-index value: 40 h5-index 40
  • Scimago H index value: 51 Scimago H index 51
Discussion papers
https://doi.org/10.5194/gmd-2018-263
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-2018-263
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Development and technical paper 21 Nov 2018

Development and technical paper | 21 Nov 2018

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Geoscientific Model Development (GMD).

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

Lukas Hubert Leufen1,a and Gerd Schädler1 Lukas Hubert Leufen and Gerd Schädler
  • 1Institute of Meteorology and Climate Research – Department Troposphere Research, Karlsruhe Institute of Technology, Karlsruhe, Germany
  • anow at: Forschungszentrum Jülich GmbH, Jülich, Germany

Abstract. The turbulent fluxes of momentum, heat and water vapour link the Earth's surface with the atmosphere. The correct modelling of the flux interactions between these two systems with very different time scales is therefore vital for climate (resp. Earth system) models. Conventionally, these fluxes are modelled using Monin–Obukhov similarity theory (MOST) with stability functions derived from a small number of field experiments; this results in a range of formulations of these functions and thus also in the flux calculations; furthermore, the underlying equations are non-linear and have to be solved iteratively at each time step of the model. For these reasons, we tried here a different approach, namely using an artificial neural network (ANN) to calculate the fluxes resp. the scaling quantities u* and θ*, thus avoiding explicit formulas for the stability functions. The network was trained and validated with multi-year datasets from seven grassland, forest and wetland sites worldwide using the Broyden–Fletcher–Goldfarb–Shanno (BFGS) quasi-Newton backpropagation algorithm and six-fold cross validation. Extensive sensitivity tests showed that an ANN with six input variables and one hidden layer gave results comparable to (and in some cases even slightly better than) the standard method. Similar satisfying results were obtained when the ANN routine was implemented in a one-dimensional stand alone land surface model (LSM), opening the way to implementation in three-dimensional climate models. In case of the one-dimensional LSM, no CPU time was saved when using the ANN version, since the small time step of the standard version required only one iteration in most cases. This could be different in models with longer time steps, e.g. global climate models.

Lukas Hubert Leufen and Gerd Schädler
Interactive discussion
Status: open (until 16 Jan 2019)
Status: open (until 16 Jan 2019)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Lukas Hubert Leufen and Gerd Schädler
Model code and software

Calculating the turbulent fluxes in the atmospheric surface layer with neural networks - Example workflow L. Leufen https://doi.org/10.23728/b2share.36ef510c515c4a00bb963113647e44a9

Lukas Hubert Leufen and Gerd Schädler
Viewed  
Total article views: 216 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
163 49 4 216 3 4
  • HTML: 163
  • PDF: 49
  • XML: 4
  • Total: 216
  • BibTeX: 3
  • EndNote: 4
Views and downloads (calculated since 21 Nov 2018)
Cumulative views and downloads (calculated since 21 Nov 2018)
Viewed (geographical distribution)  
Total article views: 215 (including HTML, PDF, and XML) Thereof 215 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 10 Dec 2018
Publications Copernicus
Download
Short summary
An artificial neural network was used to calculate the scaling quantities u* and θ*. 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.
An artificial neural network was used to calculate the scaling quantities u* and θ*. To train...
Citation
Share