12 Jul 2022
12 Jul 2022
Status: this preprint is open for discussion.

An adapted deep convolutional RNN model for spatio-temporal prediction of wind speed extremes in the short-to-medium range for wind energy applications

Daan R. Scheepens1, Irene Schicker2, Kateřina Hlaváčková-Schindler1, and Claudia Plant1 Daan R. Scheepens et al.
  • 1Research Group Data Mining and Machine Learning, Faculty of Computer Science, University of Vienna, Währingerstrasse 29, 1090 Vienna, Austria
  • 2Zentralanstalt für Meteorologie und Geodynamik (ZAMG), Hohe Warte 38, 1190 Vienna, Austria

Abstract. The amount of wind farms and wind power production in Europe, both on- and off-shore, has increased rapidly in the past years. To ensure grid stability, on-time (re)scheduling of maintenance tasks and mitigate fees in energy trading, accurate predictions of wind speed and wind power are needed. It has become particularly important to improve wind speed predictions in the short range of one to six hours as wind speed variability in this range has been found to pose the largest operational challenges. Furthermore, accurate predictions of extreme wind events are of high importance to wind farm operators as timely knowledge of these can both prevent damages and offer economic preparedness. In this work we propose a deep convolutional recurrent neural network (RNN) based regression model, for the spatio-temporal prediction of extreme wind speed events over Europe in the short-to-medium range (12 hour lead-time in one hour intervals). This is achieved by training a multi-layered convolutional long short-term memory (ConvLSTM) network with so-called imbalanced regression loss. To this end we investigate three different loss functions: the inversely weighted mean absolute error (W-MAE) loss, the inversely weighted mean squared error (W-MSE) loss and the squared error-relevance area (SERA) loss. We investigate forecast performance for various high-threshold extreme events and for various numbers of network layers, and compare the imbalanced regression loss functions to the commonly used mean squared error (MSE) and mean absolute error (MAE) loss. The results indicate superior performance of an ensemble of networks trained with either W-MAE, W-MSE or SERA loss, showing substantial improvements on high intensity extreme events. We conclude that the ConvLSTM trained with imbalanced regression loss provides an effective way to adapt deep learning to the task of imbalanced spatio-temporal regression and its application to the forecasting of extreme wind events in the short-to-medium range, and may be best utilised as an ensemble. This work was performed as a part of the MEDEA project, which is funded by the Austrian Climate Research Program to further research on renewable energy and meteorologically induced extreme events.

Daan R. Scheepens et al.

Status: open (until 06 Sep 2022)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2022-599', Anonymous Referee #1, 14 Jul 2022 reply
  • RC2: 'Comment on egusphere-2022-599', Anonymous Referee #2, 07 Aug 2022 reply

Daan R. Scheepens et al.

Data sets

ERA5 hourly data on pressure levels from 1979 to present Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Horányi, A., Muñoz Sabater, J., Nicolas, J., Peubey, C., Radu, R., Rozum, I., Schepers, D., Simmons, A., Soci, C., Dee, D., Thépaut, J.-N.

Model code and software

Deep-RNN-for-extreme-wind-speed-prediction Daan R. Scheepens

Daan R. Scheepens et al.


Total article views: 241 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
193 41 7 241 17 2 4
  • HTML: 193
  • PDF: 41
  • XML: 7
  • Total: 241
  • Supplement: 17
  • BibTeX: 2
  • EndNote: 4
Views and downloads (calculated since 12 Jul 2022)
Cumulative views and downloads (calculated since 12 Jul 2022)

Viewed (geographical distribution)

Total article views: 198 (including HTML, PDF, and XML) Thereof 198 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
Latest update: 08 Aug 2022
Short summary
The production of wind energy is increasing rapidly and relies heavily on the atmospheric conditions. To ensure power grid stability accurate predictions of wind speed is needed, especially in the short range and for extreme wind speed ranges. In this work, we demonstrate the forecasting skills of a data-driven deep learning model with model adaptations to suit higher wind speed ranges. The resulting model can be applied to other data and parameters, too, to improve nowcasting predictions.