Assessing boundary condition and parametric uncertainty in numerical-weather-prediction-modeled, long-term offshore wind speed through machine learning and analog ensemble

Bodini, Nicola; Hu, Weiming; Optis, Mike; Cervone, Guido; Alessandrini, Stefano

doi:https://doi.org/10.5194/wes-6-1363-2021

Articles | Volume 6, issue 6

https://doi.org/10.5194/wes-6-1363-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/wes-6-1363-2021

© Author(s) 2021. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 6, issue 6

Research article

|

03 Nov 2021

Research article |

| 03 Nov 2021

Assessing boundary condition and parametric uncertainty in numerical-weather-prediction-modeled, long-term offshore wind speed through machine learning and analog ensemble

Nicola Bodini, Weiming Hu, Mike Optis, Guido Cervone, and Stefano Alessandrini

Supplement

https://doi.org/10.5194/wes-6-1363-2021-supplement

Data sets

US Offshore Wind Resource data for 2000-2019 Nicola Bodini, Mike Optis, Michael Rossol, and Alex Rybchuk https://doi.org/10.25984/1821404

Model code and software

Parallel Analog Ensemble Weiming Hu https://weiming-hu.github.io/AnalogsEnsemble

nbodini/ML_UQ_offshore: ML_UQ_offshore (Version v1) Nicola Bodini https://doi.org/10.5281/zenodo.5618470

Download

Article (5589 KB)
Full-text XML

Short summary

We develop two machine-learning-based approaches to temporally extrapolate uncertainty in hub-height wind speed modeled by a numerical weather prediction model. We test our approaches in the California Outer Continental Shelf, where a significant offshore wind energy development is currently being planned, and we find that both provide accurate results.