Imperial College London
Alternate

ProfessorMatthewPiggott

Faculty of Engineering, Department of Earth Science & Engineering

Professor of Computational Geoscience and Engineering
 
 
 
//

Contact

 

m.d.piggott Website

 
 
//

Location

 

4.82Royal School of MinesSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Clare:2023:10.1201/9781003360773-61,
author = {Clare, MCA and Piggott, MD},
doi = {10.1201/9781003360773-61},
journal = {Trends in Renewable Energies Offshore - Proceedings of the 5th International Conference on Renewable Energies Offshore, RENEW 2022},
pages = {533--540},
title = {Bayesian neural networks for the probabilistic forecasting of wind direction and speed using ocean data},
url = {http://dx.doi.org/10.1201/9781003360773-61},
year = {2023}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Neural networks are increasingly used to predict wind direction and speed, two important factors for estimating a wind farm’s potential power output. However classical neural networks lack the ability to express uncertainty and hence here we apply Bayesian Neural Networks (BNNs) to the problem of offshore wind resource prediction. For BNNs, the weights and outputs are distributions leading to well-calibrated probabilistic forecasts which add considerable value to the results. In particular, probabilistic forecasts inform on the network’s ability to make predictions of out-of-sample datapoints. We use this property to conclude that the accuracy and uncertainty of our BNN is unaffected by the construction of a nearby wind farm. For our dataset, we use observations from the FINO1 research platform and ocean data as the predictors. We thus show that at this site, networks trained on pre-farm ocean data can accurately predict wind field information post construction of a wind farm.
AU  - Clare,MCA
AU  - Piggott,MD
DO  - 10.1201/9781003360773-61
EP  - 540
PY  - 2023///
SP  - 533
TI  - Bayesian neural networks for the probabilistic forecasting of wind direction and speed using ocean data
T2  - Trends in Renewable Energies Offshore - Proceedings of the 5th International Conference on Renewable Energies Offshore, RENEW 2022
UR  - http://dx.doi.org/10.1201/9781003360773-61
ER  -
Download