The skill of ERA5 has been assessed in relation to the prediction of the wind energy associated with 28 SYNOP stations located in Italy for a time span of 20 years (2001-2020). For comparison, a WRF-based high -resolution downscaling (3 km horizontally) was also produced for the same period. We found that simple predictions based on materialized past wind measures outperform the wind energy predictions from ERA5. This result can be ascribed to the particularly complex characteristics of the Italian territory. Motivated by this expected behavior, we have implemented a Quantile Random Forest (QRF) calibration which greatly alleviates the problems encountered in the ERA5 reanalysis dataset. This technique provides a calibrated ensemble prediction system for the wind speed at the station. Surprisingly, the calibrated ERA5 outperforms wind energy estimations from the high-resolution 3-km downscaling. Once properly calibrated, the high -resolution downscaling provides predictions very similar to the calibrated ERA5. Limiting our conclusions to the estimation of wind energy over a long time span (here 20 years), having at disposal a high-resolution wind-field dataset does not necessarily mean greater accuracy. A careful calibration of the original coarser wind-field dataset produces better results than the raw high-resolution dataset.

Ensemble Machine Learning greatly improves ERA5 skills for wind energy applications

Cavaiola M.;Tuju P. E.;Ferrari F.;Casciaro G.;Mazzino A.
2023-01-01

Abstract

The skill of ERA5 has been assessed in relation to the prediction of the wind energy associated with 28 SYNOP stations located in Italy for a time span of 20 years (2001-2020). For comparison, a WRF-based high -resolution downscaling (3 km horizontally) was also produced for the same period. We found that simple predictions based on materialized past wind measures outperform the wind energy predictions from ERA5. This result can be ascribed to the particularly complex characteristics of the Italian territory. Motivated by this expected behavior, we have implemented a Quantile Random Forest (QRF) calibration which greatly alleviates the problems encountered in the ERA5 reanalysis dataset. This technique provides a calibrated ensemble prediction system for the wind speed at the station. Surprisingly, the calibrated ERA5 outperforms wind energy estimations from the high-resolution 3-km downscaling. Once properly calibrated, the high -resolution downscaling provides predictions very similar to the calibrated ERA5. Limiting our conclusions to the estimation of wind energy over a long time span (here 20 years), having at disposal a high-resolution wind-field dataset does not necessarily mean greater accuracy. A careful calibration of the original coarser wind-field dataset produces better results than the raw high-resolution dataset.
File in questo prodotto:
File Dimensione Formato  
Ensemble Machine Learning greatly improves ERA5 skills for wind energy applications.pdf

accesso aperto

Tipologia: Altro materiale allegato
Dimensione 3.47 MB
Formato Adobe PDF
3.47 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11567/1213118
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 7
social impact