Physically-constrained ML projections
đ 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[2]. 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[3].
Background Readings Edit
Conferences, Journals, and Professional Organizations Edit
Libraries and Tools Edit
Data Edit
Future Directions Edit
Relevant Groups and Organizations Edit
References Edit
- â 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): 195â204. doi:10.1038/s41586-019-0912-1. ISSNÂ 1476-4687. Check date values in:
|date=
(help) - â Zhao, Wen Li; Gentine, Pierre; Reichstein, Markus; Zhang, Yao; Zhou, Sha; Wen, Yeqiang; Lin, Changjie; Li, Xi; Qiu, Guo Yu (2019). "Physics-Constrained Machine Learning of Evapotranspiration". Geophysical Research Letters. 46 (24): 14496â14507. doi:10.1029/2019GL085291. ISSNÂ 1944-8007.
- â Schlund, Manuel; Eyring, Veronika; CampsâValls, 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. ISSNÂ 2169-8961.