Downscaling Multi-Model Climate Projection Ensembles with Deep Learning (DeepESD): Contribution to CORDEX EUR-44

Abstract

Abstract. Deep Learning (DL) has recently emerged as an innovative tool to downscale climate variables from large-scale atmospheric fields under the perfect prognosis (PP) approach. Different Convolutional Neural Networks (CNN) have been applied under present-day conditions with promising results, but little is known about their suitability for extrapolating future climate change conditions. Here, we analyze this problem from a multi-model perspective, developing and evaluating an ensemble of CNN-based downscaled projections (DeepESD) for temperature and precipitation over the European EUR-44i (0.5º) domain, based on eight GCMs from the Coupled Model Intercomparison Project Phase 5 (CMIP5). To our knowledge, this is the first time that CNNs have been used to produce multi-model ensembles of downscaled projections, allowing to quantify inter-model uncertainty in climate change signals. The results are compared with those corresponding to an EUR-44 ensemble of regional climate models (RCMs) showing that DeepESD reduces distributional biases in the historical period. Moreover, the resulting climate change signals are broadly comparable to those obtained with the RCMs, with similar spatial structures. As for the uncertainty of the climate change signal (measured on the basis of inter-model spread), DeepESD yields a smaller uncertainty for precipitation, but a similar uncertainty for temperature. To facilitate further studies of this downscaling approach we follow FAIR principles and make publicly available the code (a Jupyter notebook) and the DeepESD dataset. In particular, DeepESD is published at the Earth System Grid Federation (ESGF), as the first continental-wide PP dataset contributing to CORDEX (EUR-44).

Using Explainability to Inform Statistical Downscaling Based on Deep Learning Beyond Standard Validation Approaches

“…We divide the future scenario into three different periods (2006-2040, 2041-2070 and 2071-2100) and use the predictors to test the downscaling model in historical and future conditions. Taking into account the PP assumption and following (Baño-Medina et al, 2022) we perform a bias adjustment of the GCM predictors to increase the distributional similarity with their counterpart ERA-Interim reanalysis predictor fields. In particular, we perform a signal-preserving adjustment of the monthly mean and variance of the GCM predictors working on a calendar month basis.…”

“…To test the extrapolation capability of the models under future climate change conditions (when applied to predictors from GCM projections; see Section 2.1), we follow previous work (Baño-Medina et al, 2022;Vrac et al, 2007) and use the "raw" GCM projections as pseudo-reality or ground truth with the objective of identifying large deviations, which could suggest implausible projections. We divide the future scenario into three different periods (2006-2040, 2041-2070, and 2071-2100) and compute the delta change between the future and historical scenarios for the GCM and the downscaling models.…”

“…A second group of studies have examined the performance of CNNs for PP downscaling in present (Baño-Medina et al, 2020;Pan et al, 2019;Rampal et al, 2022;Sun & Lan, 2021;Vaughan et al, 2022) and future climate conditions (Baño-Medina et al, 2021, with successful results when compared with more traditional techniques. Moreover, these advances have led to the production of continental-wide projections following the CORDEX protocol constituting the first continental-wide CORDEX contribution with PP statistical downscaling methods (Baño-Medina et al, 2022).…”