SC2.23 | Using Machine Learning to downscale climate scenarios
EDI
Using Machine Learning to downscale climate scenarios
Co-organized by AS6/CL6/CR8/ESSI6/HS11/NH15/SSS13
Convener: Christian Pagé | Co-conveners: Irida Lazic, Milica Tosic
Mon, 04 May, 08:30–10:15 (CEST)
 
Room -2.82
Mon, 08:30
This short course will train you how to use robust Machine Learning methods to do statistical downscaling of coarse climate model scenarios. A sample dataset will be used: daily surface temperature from one Global Climate Model of the CMIP6 database (historical and future climate time periods), along with a high resolution reanalysis.
Introduction on climate statistical downscaling
Methodology: classical and Machine-Learning based
Steps to perform downscaling
Sample datasets
Results
All material will be made available online, and a sample Jupyter Notebook will be provided.

Practical material for the short course is available online. Participants should begin with the session summary and session materials pages, which serve as the main entry points to the notebook and supporting resources. They include guidance for environment setup, data access, directory preparation, France-domain preprocessing, phase-by-phase workflow execution, and validation of intermediate and final results.
https://github.com/cerfacs-globc/idownscale/blob/master/docs/egu26_short_course/SESSION_SUMMARY.md
https://github.com/cerfacs-globc/idownscale/blob/master/docs/egu26_short_course/SESSION_MATERIALS.md

Session assets

Session materials Session summary
The oral presentations are given in a hybrid format supported by a Zoom meeting featuring on-site and virtual presentations. The button to access the Zoom meeting appears 15 minutes before the time block starts.