Potential for equation discovery with AI in the climate sciences

Huntingford, Chris ORCID: https://orcid.org/0000-0002-5941-7770; Nicoll, Andrew J. ORCID: https://orcid.org/0009-0005-4510-1256; Klein, Cornelia ORCID: https://orcid.org/0000-0001-6686-0458; Ahmad, Jawairia A.. 2025 Potential for equation discovery with AI in the climate sciences. Earth System Dynamics, 16 (2). 475-495. 10.5194/esd-16-475-2025

Before downloading, please read NORA policies.

Preview

Text N539201JA.pdf - Published Version Available under License Creative Commons Attribution 4.0. Download (4MB) | Preview

Abstract/Summary

Climate change and artificial intelligence (AI) are increasingly linked sciences, with AI already showing capability in identifying early precursors to extreme weather events. There are many AI methods, and a selection of the most appropriate maximizes additional understanding extractable for any dataset. However, most AI algorithms are statistically based, so even with careful splitting between data for training and testing, they arguably remain emulators. Emulators may make unreliable predictions when driven by out-of-sample forcing, of which climate change is an example, requiring understanding responses to atmospheric greenhouse gas (GHG) concentrations potentially much higher than for the present or recent past. The emerging AI technique of “equation discovery” also does not automatically guarantee good performance for new forcing regimes. However, equations rather than statistical emulators guide better system understanding, as more interpretable variables and parameters may yield informed judgements as to whether models are trusted under extrapolation. Furthermore, for many climate system attributes, descriptive equations are not yet fully available or may be unreliable, hindering the important development of Earth system models (ESMs), which remain the main tool for projecting environmental change as GHGs rise. Here, we argue for AI-driven equation discovery in climate research, given that its outputs are more amenable to linking to processes. As the foundation of ESMs is the numerical discretization of equations that describe climate components, equation discovery from datasets provides a format capable of direct inclusion into such models where system component representation is poor. We present three illustrative examples of how AI-led equation discovery may help generate new equations related to atmospheric convection, parameter derivation for existing equations of the terrestrial carbon cycle, and (additional to ESM improvement) the creation of simplified models of large-scale oceanic features to assess tipping point risks.

Item Type:	Publication - Article
Digital Object Identifier (DOI):	10.5194/esd-16-475-2025
UKCEH and CEH Sections/Science Areas:	Water and Climate Science (2025-)
ISSN:	2190-4987
Additional Information. Not used in RCUK Gateway to Research.:	Open Access paper - full text available via Official URL link.
NORA Subject Terms:	Meteorology and Climatology Computer Science Data and Information
Related URLs:	Other
Date made live:	02 Apr 2025 09:38 +0 (UTC)
URI:	https://nora.nerc.ac.uk/id/eprint/539201

Actions (login required)

View Item

Document Downloads

More statistics for this item...