Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation

<p>Proper scoring rules are an essential tool to assess the predictive performance of probabilistic forecasts. However, propriety alone does not ensure an informative characterization of predictive performance, and it is recommended to compare forecasts using multiple scoring rules. With that...

Full description

Saved in:
Bibliographic Details
Main Authors: R. Pic, C. Dombry, P. Naveau, M. Taillardat
Format: Article
Language:English
Published: Copernicus Publications 2025-03-01
Series:Advances in Statistical Climatology, Meteorology and Oceanography
Online Access:https://ascmo.copernicus.org/articles/11/23/2025/ascmo-11-23-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053751972298752
author R. Pic
C. Dombry
P. Naveau
M. Taillardat
author_facet R. Pic
C. Dombry
P. Naveau
M. Taillardat
author_sort R. Pic
collection DOAJ
description <p>Proper scoring rules are an essential tool to assess the predictive performance of probabilistic forecasts. However, propriety alone does not ensure an informative characterization of predictive performance, and it is recommended to compare forecasts using multiple scoring rules. With that in mind, interpretable scoring rules providing complementary information are necessary. We formalize a framework based on aggregation and transformation to build interpretable multivariate proper scoring rules. Aggregation-and-transformation-based scoring rules can target application-specific features of probabilistic forecasts, which improves the characterization of the predictive performance. This framework is illustrated through examples taken from the weather forecasting literature, and numerical experiments are used to showcase its benefits in a controlled setting. Additionally, the framework is tested on real-world data of postprocessed wind speed forecasts over central Europe. In particular, we show that it can help bridge the gap between proper scoring rules and spatial verification tools.</p>
format Article
id doaj-art-439b3123d78946dd97ce64d8d6abf690
institution DOAJ
issn 2364-3579
2364-3587
language English
publishDate 2025-03-01
publisher Copernicus Publications
record_format Article
series Advances in Statistical Climatology, Meteorology and Oceanography
spelling doaj-art-439b3123d78946dd97ce64d8d6abf6902025-08-20T02:52:27ZengCopernicus PublicationsAdvances in Statistical Climatology, Meteorology and Oceanography2364-35792364-35872025-03-0111235810.5194/ascmo-11-23-2025Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformationR. Pic0C. Dombry1P. Naveau2M. Taillardat3Université Marie et Louis Pasteur, CNRS, LmB (UMR 6623), 25000 Besançon, FranceUniversité Marie et Louis Pasteur, CNRS, LmB (UMR 6623), 25000 Besançon, FranceLaboratoire des Sciences du Climat et de l'Environnement, UMR 8212, CEA-CNRS-UVSQ, EstimR, IPSL & U Paris-Saclay, Gif-sur-Yvette, FranceCNRM, Université de Toulouse, Météo-France, CNRS, Toulouse, France<p>Proper scoring rules are an essential tool to assess the predictive performance of probabilistic forecasts. However, propriety alone does not ensure an informative characterization of predictive performance, and it is recommended to compare forecasts using multiple scoring rules. With that in mind, interpretable scoring rules providing complementary information are necessary. We formalize a framework based on aggregation and transformation to build interpretable multivariate proper scoring rules. Aggregation-and-transformation-based scoring rules can target application-specific features of probabilistic forecasts, which improves the characterization of the predictive performance. This framework is illustrated through examples taken from the weather forecasting literature, and numerical experiments are used to showcase its benefits in a controlled setting. Additionally, the framework is tested on real-world data of postprocessed wind speed forecasts over central Europe. In particular, we show that it can help bridge the gap between proper scoring rules and spatial verification tools.</p>https://ascmo.copernicus.org/articles/11/23/2025/ascmo-11-23-2025.pdf
spellingShingle R. Pic
C. Dombry
P. Naveau
M. Taillardat
Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation
Advances in Statistical Climatology, Meteorology and Oceanography
title Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation
title_full Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation
title_fullStr Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation
title_full_unstemmed Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation
title_short Proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation
title_sort proper scoring rules for multivariate probabilistic forecasts based on aggregation and transformation
url https://ascmo.copernicus.org/articles/11/23/2025/ascmo-11-23-2025.pdf
work_keys_str_mv AT rpic properscoringrulesformultivariateprobabilisticforecastsbasedonaggregationandtransformation
AT cdombry properscoringrulesformultivariateprobabilisticforecastsbasedonaggregationandtransformation
AT pnaveau properscoringrulesformultivariateprobabilisticforecastsbasedonaggregationandtransformation
AT mtaillardat properscoringrulesformultivariateprobabilisticforecastsbasedonaggregationandtransformation