Deep Learning Regional Climate Model Emulators: A Comparison of Two Downscaling Training Frameworks ...

Regional climate models (RCMs) have a high computational cost due to their higher spatial resolution compared to global climate models (GCMs). Therefore, various downscaling approaches have been developed as a surrogate for the dynamical downscaling of GCMs. This study assesses the potential of usin...

Full description

Bibliographic Details
Main Authors: van der Meer, Marijn, de Roda Husman, Sophie, Lhermitte, Stef
Format: Article in Journal/Newspaper
Language:English
Published: ETH Zurich 2023
Subjects:
machine learning
RCM-emulator
GCM downscaling
Antarctica
Antarc*
Antarctic
Antarctic Peninsula
Online Access:https://dx.doi.org/10.3929/ethz-b-000617206
http://hdl.handle.net/20.500.11850/617206
Description
Summary:Regional climate models (RCMs) have a high computational cost due to their higher spatial resolution compared to global climate models (GCMs). Therefore, various downscaling approaches have been developed as a surrogate for the dynamical downscaling of GCMs. This study assesses the potential of using a cost-efficient machine learning alternative to dynamical downscaling by using the example case study of emulating surface mass balance (SMB) over the Antarctic Peninsula. More specifically, we determine the impact of the training framework by comparing two training scenarios: (a) a perfect and (b) an imperfect model framework. In the perfect model framework, the RCM-emulator learns only the downscaling function; therefore, it was trained with upscaled RCM (UPRCM) features at GCM resolution. This emulator accurately reproduced SMB when evaluated on UPRCM, but its predictions on GCM data conserved RCM-GCM inconsistencies and led to underestimation. In the imperfect model framework, the RCM-emulator was trained ... : Journal of Advances in Modeling Earth Systems, 15 (6) ...

Similar Items