Valley Winds at the Local Scale: Correcting Routine Weather Forecast Using Artificial Neural Networks

Abstract

In regions of complex topography, local flows are difficult to forecast on a routine basis, especially in stable conditions, due to the coarse resolution of operational models. The Cadarache valley (southeastern France) features this sort of complex topography. The Weather Research and Forecasting (WRF) model is run daily to forecast the weather in this region with a horizontal resolution of 3 km. Such a resolution cannot resolve all topography details of the small Cadarache valley, and therefore its local wind patterns. Other variables, however, that are less dependent on the subgrid topography, are satisfactorily forecasted, and used as inputs to an artificial neural network (ANN) designed to reproduce wind observations inside the valley from WRF forecasts. A variable selection procedure identified 5 key input variables that best drive the ANN. With respect to the WRF output, the ANN significantly improves forecasted low-level winds, both for speed and direction. This study demonstrates the potential for the ANN technique to be used as a correcting tool to forecast weather conditions at the local scale when numerical modeling is performed at a resolution too coarse to take into account the effect of local topography.

Fine-Resolution WRF Simulation of Stably Stratified Flows in Shallow Pre-Alpine Valleys: A Case Study of the KASCADE-2017 Campaign

“…WRF is routinely run in an operational forecast mode in southeast France by CEA with a horizontal resolution of 3 km. This resolution is too coarse to solve the thermally driven flows in the local valleys such as those observed during IOP07 [25]. Focusing on specific situations of KASCADE-2013, [31,36] have shown that WRF simulations with a kilometric horizontal resolution, though unable to resolve CV flows during stable conditions, are quite successful for the representation of the Durance down valley flow which develops in the lowest hundreds of meters above the ground some hours after sunset.…”

“…Dupuy et al [24] used artificial neural networks (ANNs) in order to estimate the wind speed and direction in a small valley from routine observations representative of a larger scale. Finally, [25] extended this ANN technique to forecast the valley wind from operational weather simulations performed with a resolution which was too coarse to represent the fine-scale flows.…”

An ANN Model Trained on Regional Data in the Prediction of Particular Weather Conditions

“…As a measure of network accuracy, the Mean Absolute Error (MAE) was taken [34]. The satisfactory results obtained by the authors confirmed the usefulness of this tool in weather condition prediction.…”

“…Another difficulty encountered when using MLPs for weather forecasting is because ANNs are good interpolators but poor extrapolators. The dataset used to train the ANN must, therefore, contain numerous and heterogeneous examples to cover the widest range of cases that the ANN is expected to predict [34].…”

“…Our conclusion is that it is worthwhile to build models of machine learning for the prediction of time series with values that are strongly correlated with each other because then there is a high probability of obtaining an accurate prediction. These models will be useful, for example, as a correcting tool to forecast the weather conditions at the local scale when numerical modeling is insufficient due to specific local conditions-for instance, as described earlier in the paper, where numerical modeling is performed at a resolution too high to account for the influence of the local topography of the Cadarache valley localized in southeastern France) [34].…”