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

Chen, Xingyu; Hassan, Marwan A.; Fu, Xudong

doi:https://doi.org/10.5194/esurf-10-349-2022

Articles | Volume 10, issue 2

Earth Surf. Dynam., 10, 349–366, 2022

https://doi.org/10.5194/esurf-10-349-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Earth Surf. Dynam., 10, 349–366, 2022

https://doi.org/10.5194/esurf-10-349-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 10, issue 2

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 et al.

Data sets

CNN for image-based sediment detection applied to a large terrestrial and airborne dataset X. Chen, M. Hassan, and X. Fu https://doi.org/10.5281/zenodo.5240906

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.