The reviewed record of science sign in
Pith

arxiv: 2309.04452 · v2 · pith:YN2L2OML · submitted 2023-09-08 · stat.ML · cs.LG· physics.ao-ph

Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:YN2L2OMLrecord.jsonopen to challenge →

classification stat.ML cs.LGphysics.ao-ph
keywords ensemblepostprocessingforecastforecastsnetworksneuraldesigndistributions
0
0 comments X
read the original abstract

Statistical postprocessing is used to translate ensembles of raw numerical weather forecasts into reliable probabilistic forecast distributions. In this study, we examine the use of permutation-invariant neural networks for this task. In contrast to previous approaches, which often operate on ensemble summary statistics and dismiss details of the ensemble distribution, we propose networks that treat forecast ensembles as a set of unordered member forecasts and learn link functions that are by design invariant to permutations of the member ordering. We evaluate the quality of the obtained forecast distributions in terms of calibration and sharpness and compare the models against classical and neural network-based benchmark methods. In case studies addressing the postprocessing of surface temperature and wind gust forecasts, we demonstrate state-of-the-art prediction quality. To deepen the understanding of the learned inference process, we further propose a permutation-based importance analysis for ensemble-valued predictors, which highlights specific aspects of the ensemble forecast that are considered important by the trained postprocessing models. Our results suggest that most of the relevant information is contained in a few ensemble-internal degrees of freedom, which may impact the design of future ensemble forecasting and postprocessing systems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.