Process‐Based Machine Learning Observationally Constrains Future Regional Warming Projections

Abstract We present the results of a novel process‐based machine learning method to constrain climate model uncertainty in future regional temperature projections. Ridge‐ERA5—a ridge regression model—learns coefficients to represent observed relationships between daily near‐surface temperature anoma...

Full description

Saved in:
Bibliographic Details
Main Authors: Sophie Wilkinson, Peer Nowack, Manoj Joshi
Format: Article
Language:English
Published: Wiley 2025-06-01
Series:Journal of Geophysical Research: Machine Learning and Computation
Online Access:https://doi.org/10.1029/2025JH000698
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849431507832143872
author Sophie Wilkinson
Peer Nowack
Manoj Joshi
author_facet Sophie Wilkinson
Peer Nowack
Manoj Joshi
author_sort Sophie Wilkinson
collection DOAJ
description Abstract We present the results of a novel process‐based machine learning method to constrain climate model uncertainty in future regional temperature projections. Ridge‐ERA5—a ridge regression model—learns coefficients to represent observed relationships between daily near‐surface temperature anomalies and predictor variables from ERA5 reanalysis in Northern Hemisphere land regions. Combining the historically constrained Ridge‐ERA5 coefficients with inputs from CMIP6 future projections enables a derivation of observational constraints on regional warming. Although the multi‐model mean falls within the constrained range of temperatures in all tested regions, a subset of models which predict the greatest degree of warming tend to be excluded and decomposition of the constraint into predictor variable contributions suggests error‐cancellation of feedbacks in some models and regions.
format Article
id doaj-art-da86ab39c9c14566bf75ac7dca5bba0d
institution Kabale University
issn 2993-5210
language English
publishDate 2025-06-01
publisher Wiley
record_format Article
series Journal of Geophysical Research: Machine Learning and Computation
spelling doaj-art-da86ab39c9c14566bf75ac7dca5bba0d2025-08-20T03:27:37ZengWileyJournal of Geophysical Research: Machine Learning and Computation2993-52102025-06-0122n/an/a10.1029/2025JH000698Process‐Based Machine Learning Observationally Constrains Future Regional Warming ProjectionsSophie Wilkinson0Peer Nowack1Manoj Joshi2Climatic Research Unit School of Environmental Sciences University of East Anglia Norwich UKInstitute of Theoretical Informatics Karlsruhe Institute of Technology Karlsruhe GermanyClimatic Research Unit School of Environmental Sciences University of East Anglia Norwich UKAbstract We present the results of a novel process‐based machine learning method to constrain climate model uncertainty in future regional temperature projections. Ridge‐ERA5—a ridge regression model—learns coefficients to represent observed relationships between daily near‐surface temperature anomalies and predictor variables from ERA5 reanalysis in Northern Hemisphere land regions. Combining the historically constrained Ridge‐ERA5 coefficients with inputs from CMIP6 future projections enables a derivation of observational constraints on regional warming. Although the multi‐model mean falls within the constrained range of temperatures in all tested regions, a subset of models which predict the greatest degree of warming tend to be excluded and decomposition of the constraint into predictor variable contributions suggests error‐cancellation of feedbacks in some models and regions.https://doi.org/10.1029/2025JH000698
spellingShingle Sophie Wilkinson
Peer Nowack
Manoj Joshi
Process‐Based Machine Learning Observationally Constrains Future Regional Warming Projections
Journal of Geophysical Research: Machine Learning and Computation
title Process‐Based Machine Learning Observationally Constrains Future Regional Warming Projections
title_full Process‐Based Machine Learning Observationally Constrains Future Regional Warming Projections
title_fullStr Process‐Based Machine Learning Observationally Constrains Future Regional Warming Projections
title_full_unstemmed Process‐Based Machine Learning Observationally Constrains Future Regional Warming Projections
title_short Process‐Based Machine Learning Observationally Constrains Future Regional Warming Projections
title_sort process based machine learning observationally constrains future regional warming projections
url https://doi.org/10.1029/2025JH000698
work_keys_str_mv AT sophiewilkinson processbasedmachinelearningobservationallyconstrainsfutureregionalwarmingprojections
AT peernowack processbasedmachinelearningobservationallyconstrainsfutureregionalwarmingprojections
AT manojjoshi processbasedmachinelearningobservationallyconstrainsfutureregionalwarmingprojections