Preprints
https://doi.org/10.5194/esd-2024-30
https://doi.org/10.5194/esd-2024-30
06 Sep 2024
 | 06 Sep 2024
Status: a revised version of this preprint is currently under review for the journal ESD.

Potential for Equation Discovery with AI in the Climate Sciences

Chris Huntingford, Andrew J. Nicoll, Cornelia Klein, and Jawairia A. Ahmad

Abstract. Climate change and Artificial Intelligence (AI) are both attracting great interest across society. There is also substantial interest in merging the two sciences, with evidence already that AI can identify earlier precursors to extreme weather events. There are a range of AI algorithms, and selection of the most appropriate one maximizes the amount of additional understanding extractable for any dataset. However, most AI algorithms are statistically based and even with careful splitting between data for training and testing, they arguably remain as emulators. Emulators may make unreliable predictions when driven by out-of-sample forcing and climate change is an example of this, requiring understanding responses to atmospheric Greenhouse Gas (GHG) concentrations that may be substantially higher than present or the recent past. Notable, though, is the emerging AI technique of “equation discovery”. AI-derived equations from data also does not automatically guarantee good performance for new forcing regimes. However, access to equations rather than a statistical emulator guides system understanding, as their variables and parameters often have a better interpretation. Better process knowledge enables judgements as to whether equations are trusted under extrapolation. For many climate system attributes, descriptive equations are not yet fully available or may be unreliable. This uncertainty is hindering the development of Earth System Models (ESMs) which remain the main tool for projections of large-scale environmental change as GHGs rise. Here, we make the case for using AI-driven equation discovery in climate research, given that its outputs are more interpretable in terms of processes. As ESMs are based around the numerical discretisation of equations that describe climate components, equation discovery from new datasets provides a format amenable to direct inclusion into such models where representation of environmental systems is missing. We present three illustrative examples of how AI-led equation discovery may advance future climate science research. These are generating 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 (TP) risks.

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.
Chris Huntingford, Andrew J. Nicoll, Cornelia Klein, and Jawairia A. Ahmad

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Symbolic Regression, Cross-Validation, Examples comment on esd-2024-30', Paul Pukite, 11 Sep 2024
    • AC3: 'Reply on CC1', Chris Huntingford, 15 Nov 2024
  • RC1: 'Comment on esd-2024-30', Anonymous Referee #1, 27 Sep 2024
    • AC1: 'Reply on RC1', Chris Huntingford, 15 Nov 2024
  • RC2: 'Comment on esd-2024-30', Sebastian Scher, 03 Oct 2024
    • AC2: 'Reply on RC2', Chris Huntingford, 15 Nov 2024
Chris Huntingford, Andrew J. Nicoll, Cornelia Klein, and Jawairia A. Ahmad
Chris Huntingford, Andrew J. Nicoll, Cornelia Klein, and Jawairia A. Ahmad

Viewed

Total article views: 796 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
475 112 209 796 9 10
  • HTML: 475
  • PDF: 112
  • XML: 209
  • Total: 796
  • BibTeX: 9
  • EndNote: 10
Views and downloads (calculated since 06 Sep 2024)
Cumulative views and downloads (calculated since 06 Sep 2024)

Viewed (geographical distribution)

Total article views: 775 (including HTML, PDF, and XML) Thereof 775 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Dec 2024
Download
Short summary
AI is impacting science, providing key data insights, but most algorithms are statistical requiring cautious "out-of-sample" extrapolation. Yet climate research concerns predicting future climatic states. We consider a new method of AI-led equation discovery. Equations offer process interpretation and more robust predictions. We recommend this method for climate analysis, suggesting illustrative application to atmospheric convection, land-atmosphere CO2 flux and global ocean circulation models.
Altmetrics