Articles | Volume 10, issue 2
https://doi.org/10.5194/esurf-10-349-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/esurf-10-349-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
27 Apr 2022
Research article |
| 27 Apr 2022
| 27 Apr 2022
Convolutional neural networks for image-based sediment detection applied to a large terrestrial and airborne dataset
Xingyu Chen
Department of Hydraulic Engineering, State Key Laboratory of
Hydroscience and Engineering, Tsinghua University, Beijing, China
Department of Geography, The University of British Columbia,
Vancouver, BC, Canada
Marwan A. Hassan
Department of Geography, The University of British Columbia,
Vancouver, BC, Canada
Department of Hydraulic Engineering, State Key Laboratory of
Hydroscience and Engineering, Tsinghua University, Beijing, China
Viewed
Total article views: 5,233 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 15 Sep 2021)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 3,687 | 1,424 | 122 | 5,233 | 131 | 155 |
- HTML: 3,687
- PDF: 1,424
- XML: 122
- Total: 5,233
- BibTeX: 131
- EndNote: 155
Total article views: 3,878 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 27 Apr 2022)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 2,763 | 1,018 | 97 | 3,878 | 116 | 144 |
- HTML: 2,763
- PDF: 1,018
- XML: 97
- Total: 3,878
- BibTeX: 116
- EndNote: 144
Total article views: 1,355 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 15 Sep 2021)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 924 | 406 | 25 | 1,355 | 15 | 11 |
- HTML: 924
- PDF: 406
- XML: 25
- Total: 1,355
- BibTeX: 15
- EndNote: 11
Viewed (geographical distribution)
Total article views: 5,233 (including HTML, PDF, and XML)
Thereof 5,015 with geography defined
and 218 with unknown origin.
Total article views: 3,878 (including HTML, PDF, and XML)
Thereof 3,788 with geography defined
and 90 with unknown origin.
Total article views: 1,355 (including HTML, PDF, and XML)
Thereof 1,227 with geography defined
and 128 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
28 citations as recorded by crossref.
- Study on the automated characterization of particle size and shape of stacked gravelly soils via deep learning J. Gong et al. https://doi.org/10.1007/s11440-024-02493-8
- Stage–discharge relationship in an erodible compound channel with overbank floods H. Fu et al. https://doi.org/10.1016/j.jhydrol.2024.131181
- The influence of coarse particle abundance and spatial distribution on sediment transport and cluster evolution in steep channels under sediment-starved conditions W. Li et al. https://doi.org/10.1016/j.catena.2023.107199
- Distributed estimation of surface sediment size in paraglacial and periglacial environments using drone photogrammetry G. Zegers et al. https://doi.org/10.1002/esp.70093
- Improved Faster R-CNN for the Detection Method of Industrial Control Logic Graph Recognition S. Wu et al. https://doi.org/10.3389/fbioe.2022.944944
- Spatial distribution and transport characteristics of debris flow sediment using high resolution UAV images in the Ohya debris flow fan S. Yousefi et al. https://doi.org/10.1016/j.geomorph.2024.109533
- Coarse sediment grain size variability along gravel-bed rivers via automatic grain size detection (a case study of the Ondava River, Slovakia) A. MD et al. https://doi.org/10.1080/19475705.2025.2582752
- Grain size of fluvial gravel bars from close-range UAV imagery – uncertainty in segmentation-based data D. Mair et al. https://doi.org/10.5194/esurf-10-953-2022
- Deep Learning and Histogram-Based Grain Size Analysis of Images W. Wei et al. https://doi.org/10.3390/s24154923
- Different methods of estimating riverbed sediment grain size diverge at the basin scale P. Regier et al. https://doi.org/10.3389/feart.2025.1529503
- Gravel automatic sieving method fusing macroscopic and microscopic characteristics S. Gao et al. https://doi.org/10.1016/j.ijsrc.2024.05.002
- Quantification of particle size and shape of sands based on the combination of GAN and CNN J. Gong et al. https://doi.org/10.1016/j.powtec.2024.120122
- Influence of Sediment Supply Timing on Bedload Transport and Bed Surface Texture During a Single Experimental Hydrograph in Gravel Bed Rivers M. Hassan et al. https://doi.org/10.1029/2023WR035406
- A CNN-Based Framework for Automatic Extraction of High-Resolution River Bankfull Width W. Li et al. https://doi.org/10.3390/rs16234614
- Sediment shape as a proxy for fluvial processes: A factorial analysis in the Yarlung Tsangpo Grand Canyon K. Li et al. https://doi.org/10.1111/sed.70108
- Back-analysis of the 2000 Yigong dam breach flood morphodynamics: Challenges and promises Y. Lei et al. https://doi.org/10.1016/j.geomorph.2024.109588
- Automated detecting, segmenting and measuring of grains in images of fluvial sediments: The potential for large and precise data from specialist deep learning models and transfer learning D. Mair et al. https://doi.org/10.1002/esp.5755
- Quantifying particle morphology via lightweight object detection and generative data augmentation Z. Liu et al. https://doi.org/10.1007/s11440-026-02949-z
- POSSIBILITIES OF USING FIJIIMAGEJ2, WIPFRAG AND BASEGRAIN PROGRAMS FOR MORPHOMETRIC AND GRANULOMETRIC SOIL ANALYSIS Y. Tsytsiura https://doi.org/10.1590/1809-4430-eng.agric.v43n6e20230101/2023
- La mesure granulométrique par imagerie en contexte torrentiel : apports et perspectives des nouvelles méthodes par intelligence artificielle J. Berthet et al. https://doi.org/10.4000/15pwo
- Robust estimations of areal grain size distribution from geometric surface roughness in a proglacial outwash area C. Hiller et al. https://doi.org/10.1016/j.geomorph.2023.108857
- Automated mapping of the mean particle diameter characteristics from UAV-imagery using the CNN-based GRAINet model T. Lendzioch et al. https://doi.org/10.2166/hydro.2023.079
- Classification of Lakebed Geologic Substrate in Autonomously Collected Benthic Imagery Using Machine Learning J. Geisz et al. https://doi.org/10.3390/rs16071264
- Mind the information gap: How sampling and clustering impact the predictability of reach‐scale channel types in California (USA) H. Guillon et al. https://doi.org/10.1002/esp.5984
- Automated grain sizing from uncrewed aerial vehicles imagery of a gravel‐bed river: Benchmarking of three object‐based methods R. Miazza et al. https://doi.org/10.1002/esp.5782
- Application of deep learning in magnetic spherule detection: a combined method of YOLOv8 and U-Net models Z. Cui & Y. Wang https://doi.org/10.1007/s12145-025-01901-1
- Characterizing segregation in blast rock piles: A deep-learning approach leveraging aerial image analysis C. Liu et al. https://doi.org/10.1016/j.powtec.2025.121244
- Curvature-based pebble segmentation for reconstructed surface meshes A. Rheinwalt et al. https://doi.org/10.5194/esurf-13-923-2025
28 citations as recorded by crossref.
- Study on the automated characterization of particle size and shape of stacked gravelly soils via deep learning J. Gong et al. https://doi.org/10.1007/s11440-024-02493-8
- Stage–discharge relationship in an erodible compound channel with overbank floods H. Fu et al. https://doi.org/10.1016/j.jhydrol.2024.131181
- The influence of coarse particle abundance and spatial distribution on sediment transport and cluster evolution in steep channels under sediment-starved conditions W. Li et al. https://doi.org/10.1016/j.catena.2023.107199
- Distributed estimation of surface sediment size in paraglacial and periglacial environments using drone photogrammetry G. Zegers et al. https://doi.org/10.1002/esp.70093
- Improved Faster R-CNN for the Detection Method of Industrial Control Logic Graph Recognition S. Wu et al. https://doi.org/10.3389/fbioe.2022.944944
- Spatial distribution and transport characteristics of debris flow sediment using high resolution UAV images in the Ohya debris flow fan S. Yousefi et al. https://doi.org/10.1016/j.geomorph.2024.109533
- Coarse sediment grain size variability along gravel-bed rivers via automatic grain size detection (a case study of the Ondava River, Slovakia) A. MD et al. https://doi.org/10.1080/19475705.2025.2582752
- Grain size of fluvial gravel bars from close-range UAV imagery – uncertainty in segmentation-based data D. Mair et al. https://doi.org/10.5194/esurf-10-953-2022
- Deep Learning and Histogram-Based Grain Size Analysis of Images W. Wei et al. https://doi.org/10.3390/s24154923
- Different methods of estimating riverbed sediment grain size diverge at the basin scale P. Regier et al. https://doi.org/10.3389/feart.2025.1529503
- Gravel automatic sieving method fusing macroscopic and microscopic characteristics S. Gao et al. https://doi.org/10.1016/j.ijsrc.2024.05.002
- Quantification of particle size and shape of sands based on the combination of GAN and CNN J. Gong et al. https://doi.org/10.1016/j.powtec.2024.120122
- Influence of Sediment Supply Timing on Bedload Transport and Bed Surface Texture During a Single Experimental Hydrograph in Gravel Bed Rivers M. Hassan et al. https://doi.org/10.1029/2023WR035406
- A CNN-Based Framework for Automatic Extraction of High-Resolution River Bankfull Width W. Li et al. https://doi.org/10.3390/rs16234614
- Sediment shape as a proxy for fluvial processes: A factorial analysis in the Yarlung Tsangpo Grand Canyon K. Li et al. https://doi.org/10.1111/sed.70108
- Back-analysis of the 2000 Yigong dam breach flood morphodynamics: Challenges and promises Y. Lei et al. https://doi.org/10.1016/j.geomorph.2024.109588
- Automated detecting, segmenting and measuring of grains in images of fluvial sediments: The potential for large and precise data from specialist deep learning models and transfer learning D. Mair et al. https://doi.org/10.1002/esp.5755
- Quantifying particle morphology via lightweight object detection and generative data augmentation Z. Liu et al. https://doi.org/10.1007/s11440-026-02949-z
- POSSIBILITIES OF USING FIJIIMAGEJ2, WIPFRAG AND BASEGRAIN PROGRAMS FOR MORPHOMETRIC AND GRANULOMETRIC SOIL ANALYSIS Y. Tsytsiura https://doi.org/10.1590/1809-4430-eng.agric.v43n6e20230101/2023
- La mesure granulométrique par imagerie en contexte torrentiel : apports et perspectives des nouvelles méthodes par intelligence artificielle J. Berthet et al. https://doi.org/10.4000/15pwo
- Robust estimations of areal grain size distribution from geometric surface roughness in a proglacial outwash area C. Hiller et al. https://doi.org/10.1016/j.geomorph.2023.108857
- Automated mapping of the mean particle diameter characteristics from UAV-imagery using the CNN-based GRAINet model T. Lendzioch et al. https://doi.org/10.2166/hydro.2023.079
- Classification of Lakebed Geologic Substrate in Autonomously Collected Benthic Imagery Using Machine Learning J. Geisz et al. https://doi.org/10.3390/rs16071264
- Mind the information gap: How sampling and clustering impact the predictability of reach‐scale channel types in California (USA) H. Guillon et al. https://doi.org/10.1002/esp.5984
- Automated grain sizing from uncrewed aerial vehicles imagery of a gravel‐bed river: Benchmarking of three object‐based methods R. Miazza et al. https://doi.org/10.1002/esp.5782
- Application of deep learning in magnetic spherule detection: a combined method of YOLOv8 and U-Net models Z. Cui & Y. Wang https://doi.org/10.1007/s12145-025-01901-1
- Characterizing segregation in blast rock piles: A deep-learning approach leveraging aerial image analysis C. Liu et al. https://doi.org/10.1016/j.powtec.2025.121244
- Curvature-based pebble segmentation for reconstructed surface meshes A. Rheinwalt et al. https://doi.org/10.5194/esurf-13-923-2025
Saved (final revised paper)
Latest update: 09 Jun 2026
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.
We compiled a large image dataset containing more than 125 000 sediments and developed a model...
