Preprints
https://doi.org/10.5194/gmd-2023-230
https://doi.org/10.5194/gmd-2023-230
Submitted as: development and technical paper
 | 
02 Feb 2024
Submitted as: development and technical paper |  | 02 Feb 2024
Status: this preprint is currently under review for the journal GMD.

Using Deep Learning to integrate paleoclimate and global biogeochemistry over Phanerozoic time

Dongyu Zheng, Andrew Merdith, Yves Goddéris, Yannick Donnadieu, Khushboo Gurung, and Benjamin J. W. Mills

Abstract. Databases of 3D paleoclimate model simulations are increasingly used within global biogeochemical models for the Phanerozoic Eon. This improves the accuracy of the surface processes within the biogeochemical models, but the approach is limited by the availability of large numbers of paleoclimate simulations at different pCO2 levels and for different continental configurations. In this paper we apply the Frame Interpolation for Large Motion (FILM) Deep Learning method to a set of paleoclimate model simulations to upscale their time resolution from one model run every ~25 million years to one model run every 1 million year (Myr).

Testing the method on a 5 Myr time-resolution set of continental configurations confirms the accuracy of our approach when reconstructing intermediate frames from configurations separated by up to 40 Myrs. We then apply the method to upscale the paleoclimate datastructure in the SCION climate-biogeochemical model and demonstrate that upscaled outputs for global distributions of surface temperature and runoff follow a logical progression between the original keyframes.

When updated to use the high-time-resolution climate datastructure, the SCION model predicts climate shifts that were not present in the original model outputs due to its previous use of wide-spaced datasets and simple linear interpolation. We conclude that a time resolution of ~10 Myr in paleoclimate simulations is likely sufficient for investigating the long-term carbon cycle, and that Deep Learning methods may be critical in attaining this time-resolution at a reasonable computational expense, as well as for developing new fully-continuous methods in which 3D continental processes—such as species distribution—are able to translate over a moving continental surface in deep time. Nonetheless, the efficacy of Deep Learning methods in interpolating runoff data, compared to that of paleogeography and temperature, is diminished by the heterogeneous distribution of runoff. Consequently, interpolated climates should be confirmed by running a paleoclimate model for any sound scientific conclusions.

Dongyu Zheng, Andrew Merdith, Yves Goddéris, Yannick Donnadieu, Khushboo Gurung, and Benjamin J. W. Mills

Status: open (until 02 Apr 2024)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Dongyu Zheng, Andrew Merdith, Yves Goddéris, Yannick Donnadieu, Khushboo Gurung, and Benjamin J. W. Mills
Dongyu Zheng, Andrew Merdith, Yves Goddéris, Yannick Donnadieu, Khushboo Gurung, and Benjamin J. W. Mills

Viewed

Total article views: 216 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
179 32 5 216 5 3
  • HTML: 179
  • PDF: 32
  • XML: 5
  • Total: 216
  • BibTeX: 5
  • EndNote: 3
Views and downloads (calculated since 02 Feb 2024)
Cumulative views and downloads (calculated since 02 Feb 2024)

Viewed (geographical distribution)

Total article views: 208 (including HTML, PDF, and XML) Thereof 208 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 02 Mar 2024
Download
Short summary
This study uses a deep learning method to enhance the time resolution of paleoclimate simulations to 1 million years. This improved resolution allows a climate-biogeochemical model for more accurate predictions of climate shifts. The method may be critical in developing new fully-continuous methods that are able to translate over a moving continental surface in deep time with high-resolution at a reasonable computational expense.