Loading [MathJax]/jax/output/HTML-CSS/fonts/TeX/fontdata.js
Preprints
https://doi.org/10.5194/egusphere-2024-20
https://doi.org/10.5194/egusphere-2024-20
24 Jan 2024
 | 24 Jan 2024

Opinion: Optimizing climate models with process-knowledge, resolution, and AI

Tapio Schneider, L. Ruby Leung, and Robert C. J. Wills

Abstract. Accelerating progress in climate modeling is urgent for proactive and effective climate change adaptation. The central challenge lies in accurately representing processes that are small in scale yet are climatically important, such as turbulence and cloud formation. These processes  are not explicitly resolvable, necessitating the use of parameterizations. We propose a balanced approach that leverages the strengths of traditional process-based parameterizations and contemporary AI-based data-driven methods to model subgrid-scale processes. This strategy focuses on employing AI to derive data-driven closure functions from both observational and simulated data, integrated within parameterizations that encode system knowledge and conservation laws. Increasing resolution to resolve a larger fraction of small-scale processes can aid progress toward improved and interpretable climate predictions outside the observed climate distributions, but it must still allow the generation of large ensembles for model calibration and the broad exploration of possible climate outcomes – currently O(10 km) horizontal resolutions are feasible.  By synergizing decades of scientific development with advanced AI techniques, this approach aims to significantly boost the accuracy, interpretability, and trustworthiness of climate predictions.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Share

Journal article(s) based on this preprint

19 Jun 2024
| Highlight paper
Opinion: Optimizing climate models with process knowledge, resolution, and artificial intelligence
Tapio Schneider, L. Ruby Leung, and Robert C. J. Wills
Atmos. Chem. Phys., 24, 7041–7062, https://doi.org/10.5194/acp-24-7041-2024,https://doi.org/10.5194/acp-24-7041-2024, 2024
Short summary Executive editor
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

This article was solicited for the ACP 20th Anniversary collection. It received positive...
Short summary
This paper lays out an approach to achieve substantial progress in climate modeling, balancing...
Share