Articles | Volume 10, issue 2
https://doi.org/10.5194/esurf-10-349-2022
https://doi.org/10.5194/esurf-10-349-2022
Research article
 | 
27 Apr 2022
Research article |  | 27 Apr 2022

Convolutional neural networks for image-based sediment detection applied to a large terrestrial and airborne dataset

Xingyu Chen, Marwan A. Hassan, and Xudong Fu

Viewed

Total article views: 3,689 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,733 868 88 3,689 62 63
  • HTML: 2,733
  • PDF: 868
  • XML: 88
  • Total: 3,689
  • BibTeX: 62
  • EndNote: 63
Views and downloads (calculated since 15 Sep 2021)
Cumulative views and downloads (calculated since 15 Sep 2021)

Viewed (geographical distribution)

Total article views: 3,689 (including HTML, PDF, and XML) Thereof 3,480 with geography defined and 209 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 31 May 2025
Download
Short summary
We compiled a large image dataset containing more than 125 000 sediments and developed a model (GrainID) based on convolutional neural networks to measure individual grain size from images. The model was calibrated on flume and natural stream images covering a wide range of fluvial environments. The model showed high performance compared with other methods. Our model showed great potential for grain size measurements from a small patch of sediment in a flume to a watershed-scale drone survey.
Share