EGU23-10692, updated on 26 Feb 2023
EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Machine learning for accelerating process-based computation of land biogeochemical cycles

Yan Sun1,2, Daniel S. Goll1, Yuanyuan Huang3, Philippe Ciais1, Ying-Ping Wang3, Vladislav Bastrikov1, and Yilong Wang4
Yan Sun et al.
  • 1Laboratoire des Sciences du Climat et de 1’Environnement, CEA-CNRS-UVSQ, Gif sur Yvette, France
  • 2College of Marine Life Sciences, Ocean University of China, Qingdao, China
  • 3CSIRO Oceans and Atmosphere, Aspendale 3195, Australia
  • 4Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographical Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing, China

Global change ecology nowadays embraces ever-growing large observational datasets (big-data) and complex mathematical models that track hundreds of ecological processes (big-model). The rapid advancement of the big-data-big-model has reached its bottleneck: high computational requirements prevent further development of models that need to be integrated over long time scales to simulate the distribution of ecosystems carbon and nutrient pools and fluxes. Here we introduce a machine-learning acceleration (MLA) tool to tackle this grand challenge. We focus on the most resource-consuming step in terrestrial biosphere models (TBMs): the equilibration of biogeochemical cycles (spin-up), a prerequisite that can take up to 98% of the computational time. Through three members of the ORCHIDEE TBM family part of the IPSL Earth System Model, including versions that describe the complex interactions between nitrogen, phosphorus and carbon that do not have any analytical solution for the spin-up, we show that MLA reduced the computation demand by 77-80%  for global studies via interpolating the equilibrated state of biogeochemical variables for a subset of model pixels. Despite small biases in the MLA-derived equilibrium, the resulting impact on the predicted regional carbon balance over recent decades is minor. Our tool is agnostic to gridded models (beyond TBMs), compatible with existing spin-up acceleration procedures, and opens the door to a wide variety of future applications, with complex non-linear models benefit most from the computational efficiency.

How to cite: Sun, Y., Goll, D. S., Huang, Y., Ciais, P., Wang, Y.-P., Bastrikov, V., and Wang, Y.: Machine learning for accelerating process-based computation of land biogeochemical cycles, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-10692,, 2023.