Regional Climate Model Emulator Based on Deep Learning: Concept and First Evaluation of a Novel Hybrid Downscaling Approach

Sébastien Gadat (), Lola Corre, Antoine Doury, Aurélien Ribes and Samuel Somot

No 21-1233, TSE Working Papers from Toulouse School of Economics (TSE)

Abstract: Providing reliable information on climate change at local scale remains a challenge of first importance for impact studies and policymakers. Here, we propose a novel hybrid downscaling method combining the strengths of both empirical statistical downscaling methods and Regional Climate Models (RCMs). The aim of this tool is to enlarge the size of high-resolution RCM simulation ensembles at low cost. We build a statistical RCM-emulator by estimating the downscaling function included in the RCM. This framework allows us to learn the relationship between large-scale predictors and a local surface variable of interest over the RCM domain in present and future climate. Furthermore, the emulator relies on a neural network architecture, which grants computational efficiency. The RCM-emulator developed in this study is trained to produce daily maps of the near-surface temperature at the RCM resolution (12km). The emulator demonstrates an excellent ability to reproduce the complex spatial structure and daily variability simulated by the RCM and in particular the way the RCM refines locally the low-resolution climate patterns. Training in future climate appears to be a key feature of our emulator. Moreover, there is a huge computational benefit in running the emulator rather than the RCM, since training the emulator takes about 2 hours on GPU, and the prediction is nearly instantaneous. However, further work is needed to improve the way the RCM-emulator reproduces some of the temperature extremes, the intensity of climate change, and to extend the proposed methodology to different regions, GCMs, RCMs, and variables of interest.

Keywords: Emulator; Hybrid downscaling; Regional Climate Modeling; Statistical Downscaling; Deep Neural Network; Machine Learning. (search for similar items in EconPapers)
Date: 2021-07-21
New Economics Papers: this item is included in nep-big, nep-cmp and nep-env
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.tse-fr.eu/sites/default/files/TSE/docu ... 2021/wp_tse_1233.pdf Full Text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:tse:wpaper:125808

Access Statistics for this paper

More papers in TSE Working Papers from Toulouse School of Economics (TSE) Contact information at EDIRC.
Bibliographic data for series maintained by ().