Improving Wind Speed Uncertainty Forecasts Using Recurrent Neural Networks


  • Juri Backes Hamburg University of Applied Sciences
  • Wolfgang Renz Hamburg University of Applied Sciences



Uncertainty Quantification, Weather Forecasting, Recurrent Neural Network, Deep Learning


For integration of growing amounts of volatile renewable energy in the European electricity system, reliable weather prognosis gains importance. But, depending on weather conditions, forecast reliability of wind speed for predicting wind power can vary drastically with time. Thus, relevance of risk-aware system operation strategies is increasing based on wind speed uncertainty a measure of which is provided by the standard deviations of ensemble forecasts of the German Weather Service. However, lacking validity of this measure is known as a long-standing problem.
Therefore, this work investigates how machine learning based on a suitably selected set of physical quantities of weather ensemble data as well as historic wind data allows for a more realistic uncertainty quantification. A recurrent neural network (RNN) based sequence-to-sequence architecture is implemented and probabilistic wind speed forecasts are generated for a region in northern Germany.
The results are evaluated and compared with the forecasts of the German Weather Service thereby revealing improved validity of such deep-learning based uncertainty measures.


M. Abdar et al. A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information Fusion, 2021. doi: 10.1016/j.inffus.2021.05.008

J. A. Baars and C. F. Mass. Performance of national weather service forecasts compared to operational, consensus, and weighted model output statistics. Weather and Forecasting, 2005. doi: 10.1175/WAF896.1

S. L. Benedikt Schulz, Mehrez El Ayari and S. Baran. Post-processing numerical weather prediction ensembles for probabilistic solar irradiance forecasting. Solar Energy, 2021. doi: 10.1016/j.solener.2021.03.023

R. J. Bessa, C. M ̈ohrlen, V. Fundel, M. Siefert, J. Browell, S. Haglund El Gaidi, B.-M. Hodge, U. Cali, and G. Kariniotakis. Towards improved understanding of the applicability of uncertainty forecasts in the electric power industry. Energies, 2017. doi: 10.3390/en10091402

F. Chollet et al. Keras., 2015.

J. Chung, C ̧ . G ̈ul ̧cehre, K. Cho, and Y. Bengio. Empirical evaluation of gated recurrent neural networks on sequence modeling. CoRR, 2014. doi:

O. Eikeland, F. Hovem, T. Olsen, M. Chiesa, and F. M. Bianchi. Probabilistic forecasts of wind power generation in regions with complex topography using deep learning methods: An arctic case. Energy Conversion and Management: X, 2022. doi: 10.1016/j.ecmx.2022.100239

T. Gneiting and A. E. Raftery. Strictly proper scoring rules, prediction, and estimation. Journal of the American Statistical Association, 2007. doi: 10.1198/016214506000001437

P. Grönquist, T. Ben-Nun, N. Dryden, P. Dueben, L. Lavarini, S. Li, and T. Hoefler. Predicting weather uncertainty with deep convnets. CoRR, 2019. doi:

R. Hess. Statistical postprocessing of ensemble forecasts for severe weather at deutscher wetterdienst. Nonlinear Processes in Geophysics, 2020. doi: 10.5194/npg-27-473-2020

C. Junk, L. D. Monache, and S. Alessandrini. Analog-based ensemble model output statistics. Monthly Weather Review, 2015. doi: 10.1175/MWR-D-15-0095.1

H. M. D. Kabir, A. Khosravi, M. A. Hosen, and S. Nahavandi. Neural network-based uncertainty quantification: A survey of methodologies and applications. IEEE Access, 2018. doi: 10.1109/ACCESS.2018.2836917

A. Mashlakov, T. Kuronen, L. Lensu, A. Kaarna, and S. Honkapuro. Assessing the performance of deep learning models for multivariate probabilistic energy forecasting. Applied Energy, 2021. doi:

D. Reinert, F. Prill, H. Frank, M. Denhard, M. Baldauf, C. Schraff, C. Gebhardt, C. Marsigli, and G. Zängl. Dwd database reference for the global and regional icon and icon-eps forecasting system, 2021

W. Renz, J. O. Sudeikat, J. Backes, and K. Eger. Assessment of functional risks for engineering adaptive smart grid applications. In 2022 IEEE 10th International Conference on Smart Energy Grid Engineering (SEGE), 2022. doi: 10.1109/SEGE55279.2022.9889752

I. Sutskever, O. Vinyals, and Q. V. Le. Sequence to sequence learning with neural networks. NIPS’14. MIT Press, 2014. doi: 10.5555/2969033.2969173

B. Wang, J. Lu, Z. Yan, H. Luo, T. Li, Y. Zheng, and G. Zhang. Deep uncertainty quantification: A machine learning approach for weather forecasting. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’19. Association for Computing Machinery, 2019. doi: 10.1145/3292500.3330704

D. S. Wilks. Smoothing forecast ensembles with fitted probability distributions. Quarterly Journal of the Royal Meteorological Society, 2002. doi: