Physically-constrained ML projections

From Climate Change AI Wiki
Revision as of 18:02, 25 January 2021 by Kasia tokarska (talk | contribs) (create page)

(diff) ← Older revision | Approved revision (diff) | Latest revision (diff) | Newer revision → (diff)
Jump to navigation Jump to search

🌎 This article is a stub, and is currently under construction. You can help by adding to it!

This page is part of the Climate Change AI Wiki, which aims provide resources at the intersection of climate change and machine learning.

Hybrid modelling[1], by incorporating physical-constraints into data-driven ML or deep learning models is a promising field of leveraging the large amounts of data available from observational products, while making use of physical constraints present in the climate system, to ensure robust projections and extrapolating well outside of the training data. The output from physics-driven GCM climate models can be used for a "perfect model test" of the ML models, before the ML model is applied to make projections based on the observations[2].

Background Readings

Conferences, Journals, and Professional Organizations

Libraries and Tools


Future Directions

Relevant Groups and Organizations


  1. Reichstein, Markus; Camps-Valls, Gustau; Stevens, Bjorn; Jung, Martin; Denzler, Joachim; Carvalhais, Nuno; Prabhat (2019-02). "Deep learning and process understanding for data-driven Earth system science". Nature. 566 (7743): 195–204. doi:10.1038/s41586-019-0912-1. ISSN 1476-4687. Check date values in: |date= (help)
  2. Schlund, Manuel; Eyring, Veronika; Camps‐Valls, Gustau; Friedlingstein, Pierre; Gentine, Pierre; Reichstein, Markus (2020). "Constraining Uncertainty in Projected Gross Primary Production With Machine Learning". Journal of Geophysical Research: Biogeosciences. 125 (11): e2019JG005619. doi:10.1029/2019JG005619. ISSN 2169-8961.