Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Höhlein, Kevin, Schulz, Benedikt, Westermann, Rüdiger, Lerch, Sebastian
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910302057005056
author Höhlein, Kevin
Schulz, Benedikt
Westermann, Rüdiger
Lerch, Sebastian
author_facet Höhlein, Kevin
Schulz, Benedikt
Westermann, Rüdiger
Lerch, Sebastian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2309_04452
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks
Höhlein, Kevin
Schulz, Benedikt
Westermann, Rüdiger
Lerch, Sebastian
Machine Learning
Atmospheric and Oceanic Physics
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.
title Postprocessing of Ensemble Weather Forecasts Using Permutation-invariant Neural Networks
topic Machine Learning
Atmospheric and Oceanic Physics
url https://arxiv.org/abs/2309.04452