Publications of Torsten Hoefler

Torsten Hoefler:

Deep Learning for Post-Processing Ensemble Weather Forecasts

(Presentation - presented in virtual, Jun. 2020)
Invited talk at the 2020 ESIWACE Workshop

Abstract

Quantifying uncertainty in weather forecasts typically employs ensemble prediction systems, which consist of many perturbed trajectories run in parallel. These systems are associated with a high computational cost and often include statistical post-processing steps to inexpensively improve their raw prediction qualities. We propose a mixed prediction and post-processing model based on a subset of the original trajectories. In the model, we implement methods from deep learning to account for non-linear relationships that are not captured by current numerical models or other post-processing methods. Applied to global data, our mixed models achieve a relative improvement of the ensemble forecast skill of over 13%. We demonstrate that this is especially the case for extreme weather events on selected case studies, where we see an improvement in predictions by up to 26%. In addition, by using only half the trajectories, the computational costs of ensemble prediction systems can potentially be reduced, allowing weather forecasting pipelines to run higher resolution trajectories, and resulting in even more accurate raw ensemble forecasts.

Documents

download slides:

BibTeX

@misc{hoefler-esiwace20,
  author={Torsten Hoefler},
  title={{Deep Learning for Post-Processing Ensemble Weather Forecasts}},
  year={2020},
  month={Jun.},
  location={virtual},
  source={http://www.unixer.de/~htor/publications/},
}


serving: 3.144.122.20:63029	© Torsten Hoefler