TY - JOUR
T1 - Assessing observational constraints on future European climate in an out-of-sample framework
AU - O’Reilly, Christopher H.
AU - Brunner, Lukas
AU - Qasmi, Saïd
AU - Nogherotto, Rita
AU - Ballinger, Andrew P.
AU - Booth, Ben
AU - Befort, Daniel J.
AU - Knutti, Reto
AU - Schurer, Andrew P.
AU - Ribes, Aurélien
AU - Weisheimer, Antje
AU - Coppola, Erika
AU - McSweeney, Carol
PY - 2024/4/26
Y1 - 2024/4/26
N2 - Observations are increasingly used to constrain multi-model projections for future climate assessments. This study assesses the performance of five constraining methods, which have previously been applied to attempt to improve regional climate projections from CMIP5-era models. We employ an out-of-sample testing approach to assess the efficacy of these constraining methods when applied to “pseudo-observational” datasets to constrain future changes in the European climate. These pseudo-observations are taken from CMIP6 simulations, for which future changes were withheld and used for verification. The constrained projections are more accurate and broadly more reliable for regional temperature projections compared to the unconstrained projections, especially in the summer season, which was not clear prior to this study. However, the constraining methods do not improve regional precipitation projections. We also analysed the performance of multi-method projections by combining the constrained projections, which are found to be competitive with the best-performing individual methods and demonstrate improvements in reliability for some temperature projections. The performance of the multi-method projection highlights the potential of combining constraints for the development of constraining methods.
AB - Observations are increasingly used to constrain multi-model projections for future climate assessments. This study assesses the performance of five constraining methods, which have previously been applied to attempt to improve regional climate projections from CMIP5-era models. We employ an out-of-sample testing approach to assess the efficacy of these constraining methods when applied to “pseudo-observational” datasets to constrain future changes in the European climate. These pseudo-observations are taken from CMIP6 simulations, for which future changes were withheld and used for verification. The constrained projections are more accurate and broadly more reliable for regional temperature projections compared to the unconstrained projections, especially in the summer season, which was not clear prior to this study. However, the constraining methods do not improve regional precipitation projections. We also analysed the performance of multi-method projections by combining the constrained projections, which are found to be competitive with the best-performing individual methods and demonstrate improvements in reliability for some temperature projections. The performance of the multi-method projection highlights the potential of combining constraints for the development of constraining methods.
UR - http://www.scopus.com/inward/record.url?scp=85191687613&partnerID=8YFLogxK
U2 - https://doi.org/10.1038/s41612-024-00648-8
DO - https://doi.org/10.1038/s41612-024-00648-8
M3 - Article
AN - SCOPUS:85191687613
VL - 7
JO - npj Climate and Atmospheric Science
JF - npj Climate and Atmospheric Science
SN - 2397-3722
IS - 1
M1 - 95
ER -