Deep learning to represent subgrid processes in climate models
Abstract
Current climate models are too coarse to resolve many of the atmosphere's most important processes. Traditionally, these subgrid processes are heuristically approximated in so-called parameterizations. However, imperfections in these parameterizations, especially for clouds, have impeded progress toward more accurate climate predictions for decades. Cloud-resolving models alleviate many of the gravest issues of their coarse counterparts but will remain too computationally demanding for climate change predictions for the foreseeable future. Here we use deep learning to leverage the power of short-term cloud-resolving simulations for climate modeling. Our data-driven model is fast and accurate, thereby showing the potential of machine-learning-based approaches to climate model development.
- Publication:
-
Proceedings of the National Academy of Science
- Pub Date:
- September 2018
- DOI:
- 10.1073/pnas.1810286115
- arXiv:
- arXiv:1806.04731
- Bibcode:
- 2018PNAS..115.9684R
- Keywords:
-
- Physics - Atmospheric and Oceanic Physics;
- Computer Science - Machine Learning;
- Statistics - Machine Learning
- E-Print:
- View official PNAS version at https://doi.org/10.1073/pnas.1810286115