Super-Resolution for Renewable Energy Resource Data with Wind from Reanalysis (Sup3rWind)

Description

The Super-Resolution for Renewable Energy Resource Data with Wind from Reanalysis (Sup3rWind) data is a collection of high-resolution historical wind, temperature, humidity, and pressure fields. Sup3rWind data is produced by downscaling ECMWF Reanalysis Version 5 data (ERA5) to 2-km spatial and 5-minute temporal resolution (hourly for temperature, humidity, and pressure). The downscaling process was performed using a generative machine learning approach called sup3r: Super-Resolution for Renewable Energy Resource Data (linked below as "Sup3r GitHub Repo"). It improves the representation of terrain driven wind flows, extreme wind events, and preserves important spatiotemporal patterns for use in energy system planning and operations. Coverage: ------------- Ukraine, Moldova, and part of Romania: This data is accessed through the "ukraine" folder in the "Sup3rWind Data and Models in S3" resource below. Sup3r software v0.1.2, phygnn v0.0.28, and the models in "models/sup3rwind_models_202401", were used to generate this data.

Resources

Name Format Description Link
21 Gives instructions for downloading and using the Sup3rWind Ukraine Data API. This API allows users to create large downloadable data archives via a data request. The data available covers Ukraine, Moldova, and part of Romania for the years 2000 to 2023. https://developer.nrel.gov/docs/wind/wind-toolkit/sup3rwind-ukraine-download/
21 Journal publication detailing the Sup3rWind Ukraine project. https://www.mdpi.com/1996-1073/18/14/3769
21 The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial networks to create synthetic high-resolution wind and solar spatiotemporal data from coarse low-resolution inputs. https://github.com/NREL/sup3r
21 The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial networks to create synthetic high-resolution wind and solar spatiotemporal data from coarse low-resolution inputs. https://github.com/NREL/sup3r/tree/main/examples/sup3rwind
21 The Super-Resolution for Renewable Energy Resource Data with Wind from Reanalysis (Sup3rWind) data is a collection of high-resolution historical wind, temperature, humidity, and pressure fields. Sup3rWind data is produced by downscaling ECMWF Reanalysis Version 5 data (ERA5) to 2-km spatial and 5-minute temporal resolution (hourly for temperature, humidity, and pressure). The downscaling process was performed using a generative machine learning approach called sup3r: Super-Resolution for Renewable Energy Resource Data (linked below as "Sup3r GitHub Repo"). It improves the representation of terrain driven wind flows, extreme wind events, and preserves important spatiotemporal patterns for use in energy system planning and operations. https://data.openei.org/s3_viewer?bucket=nrel-pds-wtk&prefix=sup3rwind%2F
21 A registry of the NREL Wind Integration National Dataset. References the "WIND AWS S3 Bucket" data link. Released to the public as part of the Department of Energy's Open Energy Data Initiative, the Wind Integration National Dataset (WIND) is an update and expansion of the Eastern Wind Integration Data Set and Western Wind Integration Data Set. It supports the next generation of wind integration studies. https://registry.opendata.aws/nrel-pds-wtk/

Tags

  • power-systems
  • data
  • generative-adversarial-learning
  • high-resolution
  • processed-data
  • weather
  • energy-systems
  • data-assimilation
  • ukraine
  • energy-planning
  • ml
  • downscaling
  • generative
  • gan
  • renewable-energy
  • wind
  • era5
  • power
  • model
  • sup3r
  • temperature
  • resource-data
  • windspeed
  • sup3rwind
  • machine-learning
  • energy

Topics

Categories