Super Resolution for Renewable Energy Resource Data With Wind From
Reanalysis Data (Sup3rWind) and Application to Ukraine
Abstract
With an increasing share of the electricity grid relying on wind to
provide generating capacity and energy, there is an expanding global
need for historically accurate high-resolution wind data. Conventional
downscaling methods for generating these data based on numerical weather
prediction have a high computational burden and require extensive tuning
for historical accuracy. In this work, we present a novel deep
learning-based spatiotemporal downscaling method, using generative
adversarial networks (GANs), for generating historically accurate
high-resolution wind resource data from the European Centre for
Medium-Range Weather Forecasting Reanalysis version 5 data (ERA5). We
show that by training a GAN model with ERA5 low-resolution input and
Wind Integration National Dataset Toolkit (WTK;
[[1]](#ref-0001)) data as the high-resolution target, we
achieved results comparable in historical accuracy and spatiotemporal
variability to conventional dynamical downscaling. This GAN-based
downscaling method additionally reduces computational costs over
dynamical downscaling by two orders of magnitude. GANs are trained on
data sampled from the contiguous United States (CONUS), selected to
provide a diverse sampling of terrain conditions, and validated on data
held out from training, as well as observational data. This
cross-validation shows low error and high correlations with observations
and excellent agreement with holdout data across distributions of
physical metrics. We additionally downscaled the members of the European
Centre for Medium-Range Weather Forecasting Ensemble of Data
Assimilations (EDA) for 2012–2015 and 2019–2023 to estimate
uncertainty over the period for which we have observational data. We
applied this approach to downscale 30-km hourly ERA5 data to 2-km
5-minute wind data for January 2000 through December 2023 at multiple
hub heights over Ukraine, Moldova, and part of Romania. The geographic
extent was motivated by the urgent need for planners in Ukraine to
rebuild and decentralize the grid, which has been severely damaged by
the conflict between Russia and Ukraine. Comparisons against
observational data from the Meteorological Assimilation Data Ingest
System (MADIS) and multiple wind farms show comparable performance to
the CONUS validation. This 24-year data record is the first member of
the super resolution for renewable energy resource data with wind from
reanalysis data dataset (Sup3rWind).