Articles | Volume 9, issue 1
https://doi.org/10.5194/soil-9-21-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/soil-9-21-2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Shapley values reveal the drivers of soil organic carbon stock prediction
Alexandre M. J.-C. Wadoux
CORRESPONDING AUTHOR
Sydney Institute of Agriculture & School of Life and Environmental Sciences, The University of Sydney, Sydney, Australia
Nicolas P. A. Saby
INRAE, Unité de Recherche Info&Sols, Orléans, France
Manuel P. Martin
INRAE, Unité de Recherche Info&Sols, Orléans, France
Viewed
Total article views: 3,216 (including HTML, PDF, and XML)
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
2,475 | 682 | 59 | 3,216 | 162 | 44 | 51 |
- HTML: 2,475
- PDF: 682
- XML: 59
- Total: 3,216
- Supplement: 162
- BibTeX: 44
- EndNote: 51
Cumulative views and downloads
(calculated since 18 Oct 2022)
Total article views: 2,763 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 11 Jan 2023)
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
2,148 | 570 | 45 | 2,763 | 131 | 41 | 48 |
- HTML: 2,148
- PDF: 570
- XML: 45
- Total: 2,763
- Supplement: 131
- BibTeX: 41
- EndNote: 48
Total article views: 453 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 18 Oct 2022)
HTML | XML | Total | Supplement | BibTeX | EndNote | |
---|---|---|---|---|---|---|
327 | 112 | 14 | 453 | 31 | 3 | 3 |
- HTML: 327
- PDF: 112
- XML: 14
- Total: 453
- Supplement: 31
- BibTeX: 3
- EndNote: 3
Viewed (geographical distribution)
Total article views: 3,216 (including HTML, PDF, and XML)
Thereof 3,032 with geography defined
and 184 with unknown origin.
Total article views: 2,763 (including HTML, PDF, and XML)
Thereof 2,583 with geography defined
and 180 with unknown origin.
Total article views: 453 (including HTML, PDF, and XML)
Thereof 449 with geography defined
and 4 with unknown origin.
Country | # | Views | % |
---|---|---|---|
United States of America | 1 | 676 | 21 |
China | 2 | 651 | 20 |
France | 3 | 219 | 6 |
Germany | 4 | 187 | 5 |
Australia | 5 | 158 | 4 |
Country | # | Views | % |
---|---|---|---|
China | 1 | 623 | 22 |
United States of America | 2 | 582 | 21 |
France | 3 | 188 | 6 |
Germany | 4 | 144 | 5 |
Netherlands | 5 | 90 | 3 |
Country | # | Views | % |
---|---|---|---|
United States of America | 1 | 94 | 20 |
Australia | 2 | 84 | 18 |
Germany | 3 | 43 | 9 |
France | 4 | 31 | 6 |
China | 5 | 28 | 6 |
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
- 676
1
676
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
- 623
1
623
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
- 94
1
94
Cited
15 citations as recorded by crossref.
- Assessing and mapping of soil organic carbon at multiple depths in the semi-arid Trans-Ural steppe zone S. Azamat et al. 10.1016/j.geodrs.2024.e00855
- Understanding the risks of peri-urbanization to food systems to help establish sustainable agriculture near cities X. Wang et al. 10.1016/j.eiar.2024.107777
- Insights into the prediction uncertainty of machine-learning-based digital soil mapping through a local attribution approach J. Rohmer et al. 10.5194/soil-10-679-2024
- Fine-resolution baseline maps of soil nutrients in farmland of Jiangxi Province using digital soil mapping and interpretable machine learning B. Hu et al. 10.1016/j.catena.2024.108635
- Mapping of cropland humus content of the Bryansk region using machine learning methods L. Konoplina et al. 10.55959/MSU0137-0944-17-2024-79-4-130-140
- Spatio-temporal feature attribution of European summer wildfires with Explainable Artificial Intelligence (XAI) H. Li et al. 10.1016/j.scitotenv.2024.170330
- Identifying compound weather drivers of forest biomass loss with generative deep learning M. Anand et al. 10.1017/eds.2024.2
- Impact of Updating Vegetation Information on Land Surface Model Performance M. Ruiz‐Vásquez et al. 10.1029/2023JD039076
- Modelling and prediction of major soil chemical properties with Random Forest: Machine learning as tool to understand soil-environment relationships in Antarctica R. Siqueira et al. 10.1016/j.catena.2023.107677
- Three-dimensional space and time mapping reveals soil organic matter decreases across anthropogenic landscapes in the Netherlands A. Helfenstein et al. 10.1038/s43247-024-01293-y
- Mapping of Cropland Humus Content of Bryansk Oblast Using Machine-Learning Methods L. Konoplina et al. 10.3103/S0147687424700479
- Combining machine learning and environmental covariates for mapping of organic carbon in soils of Russia A. Chinilin & I. Savin 10.1016/j.ejrs.2023.07.007
- Drivers of Soil Organic Carbon Spatial Distribution in the Southern Ural Mountains: A Machine Learning Approach A. Suleymanov et al. 10.1134/S1064229324602014
- Determination of soil organic carbon by conventional and spectral methods, including assessment of the use of biostimulants, N-fertilisers, and economic benefits J. Rukaitė et al. 10.1016/j.jafr.2024.101434
- Biplots for understanding machine learning predictions in digital soil mapping S. van der Westhuizen et al. 10.1016/j.ecoinf.2024.102892
15 citations as recorded by crossref.
- Assessing and mapping of soil organic carbon at multiple depths in the semi-arid Trans-Ural steppe zone S. Azamat et al. 10.1016/j.geodrs.2024.e00855
- Understanding the risks of peri-urbanization to food systems to help establish sustainable agriculture near cities X. Wang et al. 10.1016/j.eiar.2024.107777
- Insights into the prediction uncertainty of machine-learning-based digital soil mapping through a local attribution approach J. Rohmer et al. 10.5194/soil-10-679-2024
- Fine-resolution baseline maps of soil nutrients in farmland of Jiangxi Province using digital soil mapping and interpretable machine learning B. Hu et al. 10.1016/j.catena.2024.108635
- Mapping of cropland humus content of the Bryansk region using machine learning methods L. Konoplina et al. 10.55959/MSU0137-0944-17-2024-79-4-130-140
- Spatio-temporal feature attribution of European summer wildfires with Explainable Artificial Intelligence (XAI) H. Li et al. 10.1016/j.scitotenv.2024.170330
- Identifying compound weather drivers of forest biomass loss with generative deep learning M. Anand et al. 10.1017/eds.2024.2
- Impact of Updating Vegetation Information on Land Surface Model Performance M. Ruiz‐Vásquez et al. 10.1029/2023JD039076
- Modelling and prediction of major soil chemical properties with Random Forest: Machine learning as tool to understand soil-environment relationships in Antarctica R. Siqueira et al. 10.1016/j.catena.2023.107677
- Three-dimensional space and time mapping reveals soil organic matter decreases across anthropogenic landscapes in the Netherlands A. Helfenstein et al. 10.1038/s43247-024-01293-y
- Mapping of Cropland Humus Content of Bryansk Oblast Using Machine-Learning Methods L. Konoplina et al. 10.3103/S0147687424700479
- Combining machine learning and environmental covariates for mapping of organic carbon in soils of Russia A. Chinilin & I. Savin 10.1016/j.ejrs.2023.07.007
- Drivers of Soil Organic Carbon Spatial Distribution in the Southern Ural Mountains: A Machine Learning Approach A. Suleymanov et al. 10.1134/S1064229324602014
- Determination of soil organic carbon by conventional and spectral methods, including assessment of the use of biostimulants, N-fertilisers, and economic benefits J. Rukaitė et al. 10.1016/j.jafr.2024.101434
- Biplots for understanding machine learning predictions in digital soil mapping S. van der Westhuizen et al. 10.1016/j.ecoinf.2024.102892
Latest update: 21 Jan 2025
Short summary
We introduce Shapley values for machine learning model interpretation and reveal the local and global controlling factors of soil organic carbon (SOC) stocks. The method enables spatial analysis of the important variables. Vegetation and topography determine much of the SOC stock variation in mainland France. We conclude that SOC stock variation is complex and should be interpreted at multiple levels.
We introduce Shapley values for machine learning model interpretation and reveal the local and...