Accelerating climate models
🌎 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.
Physical constraints are key ingredients for different components of climate models, including cloud parametrization, convection, aerosols, dynamic vegetation changes, among many other components of GCMs. Traditional solutions to representation of these processes in GCMs are computationally expensive, and sometimes need to be approximated (i.e., parametrized). ML can help with emulating some of these sub-grid processes[1], such as vegetation changes[2], and clouds parametrization and convection [3][4].
Background Readings
Conferences, Journals, and Professional Organizations
Libraries and Tools
Data
Future Directions
Relevant Groups and Organizations
References
- ↑ Rasp, Stephan; Pritchard, Michael S.; Gentine, Pierre (2018-09-25). "Deep learning to represent subgrid processes in climate models". Proceedings of the National Academy of Sciences. 115 (39): 9684–9689. doi:10.1073/pnas.1810286115. ISSN 0027-8424. PMC 6166853. PMID 30190437.CS1 maint: PMC format (link)
- ↑ Dagon, Katherine; Sanderson, Benjamin M.; Fisher, Rosie A.; Lawrence, David M. (2020-12-22). "A machine learning approach to emulation and biophysical parameter estimation with the Community Land Model, version 5". Advances in Statistical Climatology, Meteorology and Oceanography. 6 (2): 223–244. doi:10.5194/ascmo-6-223-2020. ISSN 2364-3579.
- ↑ Beucler, T. et al., (2020). "Towards physically-consistent, data-driven models of convection" (PDF).CS1 maint: extra punctuation (link)
- ↑ Seifert, Axel; Rasp, Stephan (2020). "Potential and Limitations of Machine Learning for Modeling Warm-Rain Cloud Microphysical Processes". Journal of Advances in Modeling Earth Systems. 12 (12): e2020MS002301. doi:10.1029/2020MS002301. ISSN 1942-2466.