Local-scale valley wind retrieval using an artificial neural network applied to routine weather observations - Archive ouverte HAL Access content directly
Journal Articles Journal of Applied Meteorology and Climatology Year : 2018

Local-scale valley wind retrieval using an artificial neural network applied to routine weather observations

(1) , (2) , (2) , (1) , (1) , (3)
1
2
3
Florian Dupuy
• Function : Author
• PersonId : 765895
• IdRef : 159218969
Gert-Jan Duine
• Function : Author
Pierre Durand
• Function : Author
• PersonId : 849573
Thierry Hedde
• Function : Correspondent author
• PersonId : 1058695

Connectez-vous pour contacter l'auteur
Eric Pardyjak

Abstract

We hereby present a new method with which to nowcast a thermally driven, downvalley wind using an artificial neural network (ANN) based on remote observations. The method allows the retrieval of wind speed and direction. The ANN was trained and evaluated using a 3-month winter-period dataset of routine weather observations made in and above the valley. The targeted valley winds feature two main directions (91% of the total dataset) that are aligned with the valley axis. They result from downward momentum transport, channeling mechanisms, and thermally driven flows. A selection procedure of the most pertinent ANN input variables, among the routine observations, highlighted three key variables: a potential temperature difference between the top and the bottom of the valley and the two wind components above the valley. These variables are directly related to the mechanisms that generate the valley winds. The performance of the ANN method improves on an earlier-proposed nowcasting method, based solely on a vertical temperature difference, as well as a multilinear regression model. The assessment of the wind speed and direction indicates good performance (i.e., wind speed bias of −0.28 m s$^{−1}$ and 84percent of calculated directions stray from observations by less than 45°). Major sources of error are due to the misrepresentation of cross-valley winds and very light winds. The validated method was then successfully applied to a 1-yr period with a similar performance. Potentially, this method could be used to downscale valley wind characteristics for unresolved valleys in mesoscale simulations.

Dates and versions

cea-02339415 , version 1 (26-03-2020)

Identifiers

• HAL Id : cea-02339415 , version 1
• DOI :

Cite

Florian Dupuy, Gert-Jan Duine, Pierre Durand, Thierry Hedde, Pierre Roubin, et al.. Local-scale valley wind retrieval using an artificial neural network applied to routine weather observations. Journal of Applied Meteorology and Climatology, 2018, 58 (5), pp.1007-1022. ⟨10.1175/JAMC-D-18-0175.1⟩. ⟨cea-02339415⟩

36 View