Preprints
https://doi.org/10.5194/egusphere-2024-4064
https://doi.org/10.5194/egusphere-2024-4064
03 Feb 2025
 | 03 Feb 2025
Status: this preprint is open for discussion and under review for Geoscientific Model Development (GMD).

Emulating grid-based forest carbon dynamics using machine learning: an LPJ-GUESS v4.1.1 application

Carolina Natel, David Martin Belda, Peter Anthoni, Neele Haß, Sam Rabin, and Almut Arneth

Abstract. The assessment of forest-based climate change mitigation strategies relies on computationally intensive scenario analyses, particularly when dynamic vegetation models are coupled with socio-economic models in multi-model frameworks. In this study, we developed surrogate models for the LPJ-GUESS dynamic global vegetation model to accelerate the prediction of carbon stocks and fluxes, enabling quicker scenario optimization within a multi-model coupling framework. We trained two machine learning methods: random forest and neural network. We assessed and compared the emulators using performance metrics and Shapley-based explanations. Our emulation approach accurately captured global and biome-specific forest carbon dynamics, closely replicating the outputs of LPJ-GUESS for both historical (1850–2014) and future (2015–2100) periods under various climate scenarios. Among the two trained emulators, the neural network extrapolated better at the end of the century for carbon stocks and fluxes, and provided more physically consistent predictions, as verified by Shapley values. Overall, the emulators reduced the simulation execution time by 97 %, bridging the gap between complex process-based models and the need for scalable and fast simulations. This offers a valuable tool for scenario analysis in the context of climate change mitigation, forest management, and policy development.

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
Carolina Natel, David Martin Belda, Peter Anthoni, Neele Haß, Sam Rabin, and Almut Arneth

Status: open (until 31 Mar 2025)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
Carolina Natel, David Martin Belda, Peter Anthoni, Neele Haß, Sam Rabin, and Almut Arneth
Carolina Natel, David Martin Belda, Peter Anthoni, Neele Haß, Sam Rabin, and Almut Arneth

Viewed

Total article views: 35 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
28 5 2 35 6 0 0
  • HTML: 28
  • PDF: 5
  • XML: 2
  • Total: 35
  • Supplement: 6
  • BibTeX: 0
  • EndNote: 0
Views and downloads (calculated since 03 Feb 2025)
Cumulative views and downloads (calculated since 03 Feb 2025)

Viewed (geographical distribution)

Total article views: 27 (including HTML, PDF, and XML) Thereof 27 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 06 Feb 2025
Download
Short summary
Complex models predict forest carbon responses to future climate change but are slow and computationally intensive, limiting large-scale analyses. We used machine learning to accelerate predictions from the LPJ-GUESS vegetation model. Our emulators, based on random forests and neural networks, achieved 97 % faster simulations. This approach enables rapid exploration of climate mitigation strategies and supports informed policy decisions.
Share