Articles | Volume 10, issue 2
https://doi.org/10.5194/soil-10-679-2024
© Author(s) 2024. 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-10-679-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Original research article
| 
30 Sep 2024
Original research article |
| 30 Sep 2024
| 30 Sep 2024
Insights into the prediction uncertainty of machine-learning-based digital soil mapping through a local attribution approach
BRGM, 3 Av. C. Guillemin, 45060 Orléans Cedex 2, France
Stephane Belbeze
BRGM, 3 Av. C. Guillemin, 45060 Orléans Cedex 2, France
Dominique Guyonnet
BRGM, 3 Av. C. Guillemin, 45060 Orléans Cedex 2, France
Viewed
Total article views: 6,113 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 21 Feb 2024)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 4,361 | 1,436 | 316 | 6,113 | 173 | 242 | 346 |
- HTML: 4,361
- PDF: 1,436
- XML: 316
- Total: 6,113
- Supplement: 173
- BibTeX: 242
- EndNote: 346
Total article views: 3,669 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 30 Sep 2024)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,668 | 790 | 211 | 3,669 | 173 | 123 | 170 |
- HTML: 2,668
- PDF: 790
- XML: 211
- Total: 3,669
- Supplement: 173
- BibTeX: 123
- EndNote: 170
Total article views: 2,444 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 21 Feb 2024)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 1,693 | 646 | 105 | 2,444 | 119 | 176 |
- HTML: 1,693
- PDF: 646
- XML: 105
- Total: 2,444
- BibTeX: 119
- EndNote: 176
Viewed (geographical distribution)
Total article views: 6,113 (including HTML, PDF, and XML)
Thereof 5,935 with geography defined
and 178 with unknown origin.
Total article views: 3,669 (including HTML, PDF, and XML)
Thereof 3,493 with geography defined
and 176 with unknown origin.
Total article views: 2,444 (including HTML, PDF, and XML)
Thereof 2,442 with geography defined
and 2 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
18 citations as recorded by crossref.
- A seventeen-year soil analysis dataset for ecosystem management M. Collinet et al. https://doi.org/10.1038/s41597-026-07254-8
- An interpretable surrogate modeling framework for rice husk ash concrete using copula-based virtual sampling V. Huynh et al. https://doi.org/10.1038/s41598-026-55368-1
- Uncertainty in broad-scale coastal flood damage cost assessments under sea-level rise: critical needs for more accurate protection data J. Rohmer et al. https://doi.org/10.1088/2515-7620/aea67b
- Evaluating the Impact of Multi-Source Digital Elevation Model Quality on Archeological Predictive Modeling: An Integrated Framework Based on Machine Learning and SHAP-Based Interpretability Analysis J. Yang et al. https://doi.org/10.3390/rs18060961
- pH-Dependent Responses and Thresholds of Cadmium Fractionation in Two Soil Types with Different Contamination Origins Y. Li et al. https://doi.org/10.3390/agriculture16192119
- Machine learning for monitoring and assessment of potentially toxic elements in soils: a synthesis of spatial validation, explainability, and uncertainty K. Hawrami https://doi.org/10.1007/s10661-026-15837-6
- Artificial Intelligence in Soil Management: Implications for Climate Resilience—A Comprehensive Review M. Barbosa & P. Rodrigues https://doi.org/10.3390/su181910057
- Global determinants of yield variability under sustainable farming approaches across climate, soil, and topography. A meta-analysis K. Hounkpatin et al. https://doi.org/10.1007/s13593-026-01133-7
- Uncertainty quantification for digital soil mapping: An overview A. ZHU et al. https://doi.org/10.1016/j.pedsph.2025.12.011
- Fine-scale mapping and nonlinear attribution of heavy metal(loid)s in urban soils using spatially enhanced machine learning algorithms H. Wang et al. https://doi.org/10.1016/j.jenvman.2026.131206
- Beyond the source baseline: Model-scale conditional re-expression of soil metal signals across environmental contexts Z. Chen et al. https://doi.org/10.1016/j.jhazmat.2026.143391
- Updating a legacy soil map to the WRB: diagnostic conflicts and taxonomic shifts in tropical volcanic soils of Réunion F. Feder https://doi.org/10.1016/j.catena.2026.110363
- Applicability-aware inference of salinisation-metal risk associations from sparse soil data Q. Ma et al. https://doi.org/10.1016/j.geoderma.2026.118057
- Mapping and modelling land degradation vulnerability in a semi-arid region: a case study from Battalgazi District, Turkiye M. Kılıç https://doi.org/10.7717/peerj.20606
- Multi-Scale Driving Mechanisms of the Spatiotemporal Distribution of Soil pH in High-Standard Farmland Within the Hilly Regions of Southern China Z. Zeng et al. https://doi.org/10.3390/agriculture16151685
- Importance ranking of data and model uncertainties in quantile regression forest-based spatial predictions when data are sparse, imprecise and clustered J. Rohmer https://doi.org/10.1016/j.ecoinf.2025.103459
- Explainable machine learning models for predicting topsoil metals and oxides A. Suleymanov et al. https://doi.org/10.1007/s11368-025-04143-2
- Evaluation of spatial effects on hydrogeochemical interactions in nitrate pollution using machine learning and explainable artificial intelligence J. Mogaraju https://doi.org/10.1007/s44288-026-00404-w
18 citations as recorded by crossref.
- A seventeen-year soil analysis dataset for ecosystem management M. Collinet et al. https://doi.org/10.1038/s41597-026-07254-8
- An interpretable surrogate modeling framework for rice husk ash concrete using copula-based virtual sampling V. Huynh et al. https://doi.org/10.1038/s41598-026-55368-1
- Uncertainty in broad-scale coastal flood damage cost assessments under sea-level rise: critical needs for more accurate protection data J. Rohmer et al. https://doi.org/10.1088/2515-7620/aea67b
- Evaluating the Impact of Multi-Source Digital Elevation Model Quality on Archeological Predictive Modeling: An Integrated Framework Based on Machine Learning and SHAP-Based Interpretability Analysis J. Yang et al. https://doi.org/10.3390/rs18060961
- pH-Dependent Responses and Thresholds of Cadmium Fractionation in Two Soil Types with Different Contamination Origins Y. Li et al. https://doi.org/10.3390/agriculture16192119
- Machine learning for monitoring and assessment of potentially toxic elements in soils: a synthesis of spatial validation, explainability, and uncertainty K. Hawrami https://doi.org/10.1007/s10661-026-15837-6
- Artificial Intelligence in Soil Management: Implications for Climate Resilience—A Comprehensive Review M. Barbosa & P. Rodrigues https://doi.org/10.3390/su181910057
- Global determinants of yield variability under sustainable farming approaches across climate, soil, and topography. A meta-analysis K. Hounkpatin et al. https://doi.org/10.1007/s13593-026-01133-7
- Uncertainty quantification for digital soil mapping: An overview A. ZHU et al. https://doi.org/10.1016/j.pedsph.2025.12.011
- Fine-scale mapping and nonlinear attribution of heavy metal(loid)s in urban soils using spatially enhanced machine learning algorithms H. Wang et al. https://doi.org/10.1016/j.jenvman.2026.131206
- Beyond the source baseline: Model-scale conditional re-expression of soil metal signals across environmental contexts Z. Chen et al. https://doi.org/10.1016/j.jhazmat.2026.143391
- Updating a legacy soil map to the WRB: diagnostic conflicts and taxonomic shifts in tropical volcanic soils of Réunion F. Feder https://doi.org/10.1016/j.catena.2026.110363
- Applicability-aware inference of salinisation-metal risk associations from sparse soil data Q. Ma et al. https://doi.org/10.1016/j.geoderma.2026.118057
- Mapping and modelling land degradation vulnerability in a semi-arid region: a case study from Battalgazi District, Turkiye M. Kılıç https://doi.org/10.7717/peerj.20606
- Multi-Scale Driving Mechanisms of the Spatiotemporal Distribution of Soil pH in High-Standard Farmland Within the Hilly Regions of Southern China Z. Zeng et al. https://doi.org/10.3390/agriculture16151685
- Importance ranking of data and model uncertainties in quantile regression forest-based spatial predictions when data are sparse, imprecise and clustered J. Rohmer https://doi.org/10.1016/j.ecoinf.2025.103459
- Explainable machine learning models for predicting topsoil metals and oxides A. Suleymanov et al. https://doi.org/10.1007/s11368-025-04143-2
- Evaluation of spatial effects on hydrogeochemical interactions in nitrate pollution using machine learning and explainable artificial intelligence J. Mogaraju https://doi.org/10.1007/s44288-026-00404-w
Saved (final revised paper)
Latest update: 07 Nov 2026
Short summary
Machine learning (ML) models have become key ingredients for digital soil mapping. To explain why the ML model is reliable, we apply a popular method from explainable artificial intelligence to the uncertainty prediction, with an application to the mapping of hydrocarbon pollutants on urban soil. We show the benefit of a joint analysis of the influence on the best estimate and the uncertainty to improve communication with end users and support decisions regarding covariates’ characterisation.
Machine learning (ML) models have become key ingredients for digital soil mapping. To explain...
Altmetrics
Final-revised paper
Preprint