SOIL
SOIL
SOIL
Articles | Volume 12, issue 1
Articles | Volume 12, issue 1
https://doi.org/10.5194/soil-12-321-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/soil-12-321-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 12, issue 1
Original research article
 | 
30 Mar 2026
Original research article |  | 30 Mar 2026

Assessing the potential of complex artificial neural networks for modelling small-scale soil erosion by water

Nils Barthel, Simone Ott, Benjamin Burkhard, and Bastian Steinhoff-Knopp

Viewed

Total article views: 1,631 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,341 240 50 1,631 59 76
  • HTML: 1,341
  • PDF: 240
  • XML: 50
  • Total: 1,631
  • BibTeX: 59
  • EndNote: 76
Views and downloads (calculated since 08 Aug 2025)
Cumulative views and downloads (calculated since 08 Aug 2025)

Viewed (geographical distribution)

Total article views: 1,631 (including HTML, PDF, and XML) Thereof 1,575 with geography defined and 56 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 20 Apr 2026
Download
Short summary

This study compares neural networks and a random forest model for predicting soil erosion in agricultural cropland using long-term data from northern Germany. All models captured general erosion patterns, while more complex neural networks slightly improved the distinction between soil loss classes. A permutation importance analysis identified slope and machine direction vs. aspect as the most influential predictors across all models.

Read more
Share