Biogeosciences
Biogeosciences
BG
Articles | Volume 22, issue 23
Articles | Volume 22, issue 23
https://doi.org/10.5194/bg-22-7845-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/bg-22-7845-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 22, issue 23
Research article
 | 
09 Dec 2025
Research article |  | 09 Dec 2025

Using explainable AI to diagnose the representation of environmental drivers in process-based soil organic carbon models

Lingfei Wang, Gab Abramowitz, Ying-Ping Wang, Andy Pitman, Philippe Ciais, and Daniel S. Goll

Viewed

Total article views: 2,007 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
1,595 330 82 2,007 94 68 94
  • HTML: 1,595
  • PDF: 330
  • XML: 82
  • Total: 2,007
  • Supplement: 94
  • BibTeX: 68
  • EndNote: 94
Views and downloads (calculated since 19 Jun 2025)
Cumulative views and downloads (calculated since 19 Jun 2025)

Viewed (geographical distribution)

Total article views: 2,007 (including HTML, PDF, and XML) Thereof 2,000 with geography defined and 7 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 10 Mar 2026
Download
Short summary
Accurate estimates of global soil organic carbon (SOC) content and its spatial pattern are critical for future climate change mitigation. However, the most advanced process-based SOC models struggle to do this task. Here we apply multiple explainable machine learning methods to identify missing variables and misrepresented relationships between environmental factors and SOC in these models, offering new insights to guide model development for more reliable SOC predictions.
Read more
Share
Altmetrics
Final-revised paper
Preprint