This Flagship Pilot Study will start during the second part of 2025
Southeastern South America (SESA) was the focus of a former CORDEX-FPS that addressed the study of extreme
precipitation events and their impacts based on a coordinated ensemble of convection permitting RCM (CPRCM) and ESD simulations for the present day climate that covered Subtropical South America (SSA). The need for further research to explore the combination of different downscaling sources for future climate scenarios was one of
the main outcomes that emerged from this exercise.
Relying on observational data, statistical downscaling models (ESD) relate large-scale predictors and regional climate variables. In turn, emulators are hybrid downscaling models based on machine learning techniques that are trained using regional climate model (RCM) simulations to learn the physical relationships between low resolution predictors and high resolution predictant as much as is done in the classical dynamical downscaling. The varied nature of ESD and the relatively new emulation approach based on more sophisticated machine learning techniques, requires the improvement of our understanding of how well new machine learning techniques are able to represent local climate and produce cost-effective future projections.
The main aim of the present initiative is to comprehensively assess machine learning-based ESD models and CPRCM
emulators to obtain high resolution climate projections over the SSA region where the understanding of changes in
extreme climate events in a climate change context is still an open question. In this framework, this project builds up
on taking full advantage of the available CPRCM evaluation simulations that cover the complete subtropical South
America sector; designates SSA as a core region for coordinated CPRCM simulations for future climate change
scenarios; and proposes the development of an evaluation framework of machine learning-based ESD and CPRCM
emulators.
