BIS-4D: mapping soil properties and their uncertainties at 25&thinsp;m resolution in the Netherlands

Helfenstein, Anatol; Mulder, Vera L.; Hack-ten Broeke, Mirjam J. D.; van Doorn, Maarten; Teuling, Kees; Walvoort, Dennis J. J.; Heuvelink, Gerard B. M.

doi:https://doi.org/10.5194/essd-16-2941-2024

Articles | Volume 16, issue 6

https://doi.org/10.5194/essd-16-2941-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/essd-16-2941-2024

© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 16, issue 6

Data description paper

|

25 Jun 2024

Data description paper |

| 25 Jun 2024

BIS-4D: mapping soil properties and their uncertainties at 25 m resolution in the Netherlands

Anatol Helfenstein, Vera L. Mulder, Mirjam J. D. Hack-ten Broeke, Maarten van Doorn, Kees Teuling, Dennis J. J. Walvoort, and Gerard B. M. Heuvelink

Supplement

https://doi.org/10.5194/essd-16-2941-2024-supplement

Data sets

BIS-4D: Maps of soil properties and their uncertainties at 25 m resolution in the Netherlands Anatol Helfenstein et al. https://doi.org/10.4121/0c934ac6-2e95-4422-8360-d3a802766c71

Georeferenced point data of soil properties in the Netherlands Anatol Helfenstein et al. https://doi.org/10.4121/c90215b3-bdc6-4633-b721-4c4a0259d6dc

Spatially explicit environmental variables at 25 m resolution for spatial modelling in the Netherlands Anatol Helfenstein et al. https://doi.org/10.4121/6af610ed-9006-4ac5-b399-4795c2ac01ec

Model code and software

BIS-4D. In Earth System Science Data Anatol Helfenstein https://doi.org/10.5281/zenodo.12238785

Video supplement

4 Dimensional Information About the Skin of the Earth Anatol Helfenstein https://www.youtube.com/watch?v=ENCYUnqc-wo

Download

Article (8428 KB)
Full-text XML

Short summary

Earth system models and decision support systems greatly benefit from high-resolution soil information with quantified accuracy. Here we introduce BIS-4D, a statistical modeling platform that predicts nine essential soil properties and their uncertainties at 25 m resolution in surface 2 m across the Netherlands. Using machine learning informed by up to 856 000 soil observations coupled with 366 spatially explicit environmental variables, prediction accuracy was the highest for clay, sand and pH.