Abstract
AbstractWe analyze the applicability of convolutional neural network (CNN) architectures for downscaling of short‐range forecasts of near‐surface winds on extended spatial domains. Short‐range wind forecasts (at the 100 m level) from European Centre for Medium Range Weather Forecasts ERA5 reanalysis initial conditions at 31 km horizontal resolution are downscaled to mimic high resolution (HRES) (deterministic) short‐range forecasts at 9 km resolution. We evaluate the downscaling quality of four exemplary CNN architectures and compare these against a multilinear regression model. We conduct a qualitative and quantitative comparison of model predictions and examine whether the predictive skill of CNNs can be enhanced by incorporating additional atmospheric variables, such as geopotential height and forecast surface roughness, or static high‐resolution fields, like land–sea mask and topography. We further propose DeepRU, a novel U‐Net‐based CNN architecture, which is able to infer situation‐dependent wind structures that cannot be reconstructed by other models. Inferring a target 9 km resolution wind field from the low‐resolution input fields over the Alpine area takes less than 10 ms on our graphics processing unit target architecture, which compares favorably to an overhead in simulation time of minutes or hours between low‐ and high‐resolution forecast simulations.
Highlights
INTRODUCTION AND CONTRIBUTIONAccurate prediction of near-surface wind fields is a topic of central interest in various fields of science and industry
We propose LinearCNN, an efficient two-layer convolutional neural network (CNN) which is composed of two branches for processing low-resolution and highresolution inputs separately
In the original fast super-resolution CNN (FSRCNN) architecture, batch normalization was not used. We found it beneficial to regularize the feature representations through batch normalization, since the increased depth of our FSRCNN variant may lead to instabilities in training due to, for example, internal covariate shifts (Ioffe and Szegedy, 2015)
Summary
INTRODUCTION AND CONTRIBUTIONAccurate prediction of near-surface wind fields is a topic of central interest in various fields of science and industry. Meteorologically relevant factors such as the vertical stability, snow cover or the presence of nearby lakes, river beds or sea can strongly influence local wind conditions (e.g., McQueen et al, 1995; Holtslag et al, 2013). In these regions, finer-resolution regional numerical models with grid spacings of the order of kilometers or less need to be applied in order to obtain reliable low-level winds (e.g., Salvador et al, 1999; Mass et al, 2002)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
