A Comparative Study of Convolutional Neural Network Models for Wind Field Downscaling

by   Kevin Höhlein, et al.

We 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 field forecasts (at the 100 m level) from ECMWF ERA5 reanalysis initial conditions at 31 km horizontal resolution are downscaled to mimic HRES (deterministic) short-range forecasts at 9 km resolution. We evaluate the downscaling quality of four exemplary model architectures and compare these against a multi-linear 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 milliseconds on our GPU target architecture, which compares favorably to an overhead in simulation time of minutes or hours between low- and high-resolution forecast simulations.


Machine Learning for enhancing Wind Field Resolution in Complex Terrain

Atmospheric flows are governed by a broad variety of spatio-temporal sca...

Prediction of solar wind speed by applying convolutional neural network to potential field source surface (PFSS) magnetograms

An accurate solar wind speed model is important for space weather predic...

FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

FourCastNet, short for Fourier Forecasting Neural Network, is a global d...

Real-World Oceanographic Simulations on the GPU using a Two-Dimensional Finite-Volume Scheme

In this work, we take a modern high-resolution finite-volume scheme for ...

Multi-Output Artificial Neural Network for Storm Surge Prediction in North Carolina

During hurricane seasons, emergency managers and other decision makers n...

Deep Learning Hydrodynamic Forecasting for Flooded Region Assessment in Near-Real-Time (DL Hydro-FRAN)

Hydrodynamic flood modeling improves hydrologic and hydraulic prediction...

Please sign up or login with your details

Forgot password? Click here to reset