Articles | Volume 11, issue 2
https://doi.org/10.5194/soil-11-553-2025
© Author(s) 2025. 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-11-553-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Original research article
| 
22 Jul 2025
Original research article |
| 22 Jul 2025
| 22 Jul 2025
Using Monte Carlo conformal prediction to evaluate the uncertainty of deep-learning soil spectral models
Yin-Chung Huang
CORRESPONDING AUTHOR
School of Life and Environmental Science & Sydney Institute of Agriculture, The University of Sydney, Sydney, NSW, Australia
José Padarian
School of Life and Environmental Science & Sydney Institute of Agriculture, The University of Sydney, Sydney, NSW, Australia
Budiman Minasny
School of Life and Environmental Science & Sydney Institute of Agriculture, The University of Sydney, Sydney, NSW, Australia
Alex B. McBratney
School of Life and Environmental Science & Sydney Institute of Agriculture, The University of Sydney, Sydney, NSW, Australia
Viewed
Total article views: 6,828 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Jan 2025)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 5,005 | 1,614 | 209 | 6,828 | 213 | 296 |
- HTML: 5,005
- PDF: 1,614
- XML: 209
- Total: 6,828
- BibTeX: 213
- EndNote: 296
Total article views: 3,398 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 22 Jul 2025)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,672 | 614 | 112 | 3,398 | 126 | 133 |
- HTML: 2,672
- PDF: 614
- XML: 112
- Total: 3,398
- BibTeX: 126
- EndNote: 133
Total article views: 3,430 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 07 Jan 2025)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,333 | 1,000 | 97 | 3,430 | 87 | 163 |
- HTML: 2,333
- PDF: 1,000
- XML: 97
- Total: 3,430
- BibTeX: 87
- EndNote: 163
Viewed (geographical distribution)
Total article views: 6,828 (including HTML, PDF, and XML)
Thereof 6,486 with geography defined
and 342 with unknown origin.
Total article views: 3,398 (including HTML, PDF, and XML)
Thereof 3,095 with geography defined
and 303 with unknown origin.
Total article views: 3,430 (including HTML, PDF, and XML)
Thereof 3,391 with geography defined
and 39 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
16 citations as recorded by crossref.
- Quantifying spatial uncertainty to improve soil predictions in data-sparse regions K. Rau et al. https://doi.org/10.5194/soil-11-833-2025
- Digital twin-assisted next-generation ceramic membranes for sustainable heavy metal remediation N. Omar et al. https://doi.org/10.1016/j.cep.2026.110805
- Zero-shot inference with Tabular Prior-data Fitted Network (TabPFN) for soil MIR spectral analysis Y. Huang et al. https://doi.org/10.1016/j.geoderma.2026.117880
- Integrating Deep Generative AI and Hyperspectral–Multispectral Data Fusion for Enhancing Digital Soil Mapping S. Nawar et al. https://doi.org/10.3390/rs18142320
- Geospatial modeling and mapping of soil organic carbon in arid and semi-arid agricultural lands of Khuzestan, Iran using remote sensing, machine learning, and SHAP analysis Z. Zaheri Abdehvand et al. https://doi.org/10.1016/j.asr.2026.05.100
- Uncertainty quantification in water quality prediction using Optuna-optimized machine learning: A case study in the Quan Lo-Phung Hiep irrigation system, Vietnamese Mekong Delta H. Thi et al. https://doi.org/10.1016/j.jwpe.2026.109858
- Kriging prior regression: A case for kriging-based spatial features with TabPFN in soil mapping J. Schmidinger et al. https://doi.org/10.1016/j.compag.2025.111352
- Modern Neural Networks for Small Tabular Datasets: The New Default for Field‐Scale Digital Soil Mapping? V. Barkov et al. https://doi.org/10.1111/ejss.70299
- Drift-Aware causal transformer for slag iron prediction in nickel laterite smelting under evolving manufacturing conditions J. Bae & J. Yoo https://doi.org/10.1016/j.knosys.2026.116788
- Self-supervised and multi-fidelity learning for extended predictive soil spectroscopy L. Sun et al. https://doi.org/10.1016/j.geoderma.2026.117764
- A review of artificial intelligence in materials screening: Data, models, and applications in forensic science S. Datta et al. https://doi.org/10.1016/j.nxmate.2026.102756
- Integrating multi-source remote sensing and UAV data for landscape-scale soil carbon mapping: uncertainty hotspots at ecotone boundaries in forest-steppe ecosystems D. Bardashov et al. https://doi.org/10.1080/01431161.2026.2676255
- Mapping soil carbon content in two contrasting pedoclimatic regions using a deep learning approach with remote sensing imagery and laboratory spectral datasets H. Zayani et al. https://doi.org/10.1016/j.geoderma.2025.117513
- Spatiotemporal modelling of soil organic carbon: integrating process-based and machine learning approaches Y. Du et al. https://doi.org/10.1016/j.geoderma.2026.117967
- Enhancing Influenza-Like Illness forecasting: An ensemble approach combining mathematical and deep learning models amidst the COVID-19 pandemic G. Yoon et al. https://doi.org/10.1016/j.epidem.2026.100901
- Improved Kriging-based Spatial Interpolation Technique for Mapping Soil Organic Carbon using Categorical Auxiliary Information in Forest Ecosystems V. Ho et al. https://doi.org/10.1007/s42729-026-03163-2
16 citations as recorded by crossref.
- Quantifying spatial uncertainty to improve soil predictions in data-sparse regions K. Rau et al. https://doi.org/10.5194/soil-11-833-2025
- Digital twin-assisted next-generation ceramic membranes for sustainable heavy metal remediation N. Omar et al. https://doi.org/10.1016/j.cep.2026.110805
- Zero-shot inference with Tabular Prior-data Fitted Network (TabPFN) for soil MIR spectral analysis Y. Huang et al. https://doi.org/10.1016/j.geoderma.2026.117880
- Integrating Deep Generative AI and Hyperspectral–Multispectral Data Fusion for Enhancing Digital Soil Mapping S. Nawar et al. https://doi.org/10.3390/rs18142320
- Geospatial modeling and mapping of soil organic carbon in arid and semi-arid agricultural lands of Khuzestan, Iran using remote sensing, machine learning, and SHAP analysis Z. Zaheri Abdehvand et al. https://doi.org/10.1016/j.asr.2026.05.100
- Uncertainty quantification in water quality prediction using Optuna-optimized machine learning: A case study in the Quan Lo-Phung Hiep irrigation system, Vietnamese Mekong Delta H. Thi et al. https://doi.org/10.1016/j.jwpe.2026.109858
- Kriging prior regression: A case for kriging-based spatial features with TabPFN in soil mapping J. Schmidinger et al. https://doi.org/10.1016/j.compag.2025.111352
- Modern Neural Networks for Small Tabular Datasets: The New Default for Field‐Scale Digital Soil Mapping? V. Barkov et al. https://doi.org/10.1111/ejss.70299
- Drift-Aware causal transformer for slag iron prediction in nickel laterite smelting under evolving manufacturing conditions J. Bae & J. Yoo https://doi.org/10.1016/j.knosys.2026.116788
- Self-supervised and multi-fidelity learning for extended predictive soil spectroscopy L. Sun et al. https://doi.org/10.1016/j.geoderma.2026.117764
- A review of artificial intelligence in materials screening: Data, models, and applications in forensic science S. Datta et al. https://doi.org/10.1016/j.nxmate.2026.102756
- Integrating multi-source remote sensing and UAV data for landscape-scale soil carbon mapping: uncertainty hotspots at ecotone boundaries in forest-steppe ecosystems D. Bardashov et al. https://doi.org/10.1080/01431161.2026.2676255
- Mapping soil carbon content in two contrasting pedoclimatic regions using a deep learning approach with remote sensing imagery and laboratory spectral datasets H. Zayani et al. https://doi.org/10.1016/j.geoderma.2025.117513
- Spatiotemporal modelling of soil organic carbon: integrating process-based and machine learning approaches Y. Du et al. https://doi.org/10.1016/j.geoderma.2026.117967
- Enhancing Influenza-Like Illness forecasting: An ensemble approach combining mathematical and deep learning models amidst the COVID-19 pandemic G. Yoon et al. https://doi.org/10.1016/j.epidem.2026.100901
- Improved Kriging-based Spatial Interpolation Technique for Mapping Soil Organic Carbon using Categorical Auxiliary Information in Forest Ecosystems V. Ho et al. https://doi.org/10.1007/s42729-026-03163-2
Saved (final revised paper)
Latest update: 30 Sep 2026
Short summary
Uncertainty quantification plays a crucial role in reporting machine learning models in soil spectroscopy. This study introduces Monte Carlo conformal prediction (MC-CP), a novel method for uncertainty quantification in deep-learning soil spectral models. MC-CP outperformed two established methods, providing the most reliable results. Its efficiency and robustness make it a practical choice for implementing soil spectral models in decision making.
Uncertainty quantification plays a crucial role in reporting machine learning models in soil...
