Downscaling multi-model climate projection ensembles with deep learning (DeepESD): contribution to CORDEX EUR-44

Baño-Medina, Jorge; Manzanas, Rodrigo; Cimadevilla, Ezequiel; Fernández, Jesús; González-Abad, Jose; Cofiño, Antonio S.; Gutiérrez, José Manuel

doi:https://doi.org/10.5194/gmd-15-6747-2022

Articles | Volume 15, issue 17

Geosci. Model Dev., 15, 6747–6758, 2022

https://doi.org/10.5194/gmd-15-6747-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Geosci. Model Dev., 15, 6747–6758, 2022

https://doi.org/10.5194/gmd-15-6747-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 15, issue 17

Model evaluation paper

06 Sep 2022

Model evaluation paper | 06 Sep 2022

Downscaling multi-model climate projection ensembles with deep learning (DeepESD): contribution to CORDEX EUR-44

Jorge Baño-Medina et al.

Data sets

DeepESD Jorge Baño-Medina, Rodrigo Manzanas, Ezequiel Cimadevilla, Jesús Fernández, José González, Antonio Cofiño, José Manuel Gutiérrez https://data.meteo.unican.es/thredds/catalog/esgcet/catalog.html

Input data (predictors and predictands) Jorge Baño-Medina, Rodrigo Manzanas, Ezequiel Cimadevilla, Jesús Fernández, José González, Antonio Cofiño, José Manuel Gutiérrez https://doi.org/10.5281/zenodo.6823421

Model code and software

Explanatory notebook Jorge Baño-Medina, Rodrigo Manzanas, Ezequiel Cimadevilla, Jesús Fernández, José González, Antonio Cofiño, José Manuel Gutiérrez https://doi.org/10.5281/zenodo.6828303

Short summary

Deep neural networks are used to produce downscaled regional climate change projections over Europe for temperature and precipitation for the first time. The resulting dataset, DeepESD, is analyzed against state-of-the-art downscaling methodologies, reproducing more accurately the observed climate in the historical period and showing plausible future climate change signals with low computational requirements.