Abstract
Abstract. Image-based grain sizing has been used to measure grain size more
efficiently compared with traditional methods (e.g., sieving and Wolman pebble
count). However, current methods to automatically detect individual grains
are largely based on detecting grain interstices from image intensity which
not only require a significant level of expertise for parameter tuning but
also underperform when they are applied to suboptimal environments (e.g.,
dense organic debris, various sediment lithology). We proposed a model
(GrainID) based on convolutional neural networks to measure grain size in a
diverse range of fluvial environments. A dataset of more than 125 000
grains from flume and field measurements were compiled to develop GrainID.
Tests were performed to compare the predictive ability of GrainID with
sieving, manual labeling, Wolman pebble counts (Wolman, 1954) and
BASEGRAIN (Detert and Weitbrecht, 2012). When compared with the sieving
results for a sandy-gravel bed, GrainID yielded high predictive accuracy
(comparable to the performance of manual labeling) and outperformed
BASEGRAIN and Wolman pebble counts (especially for small grains). For the
entire evaluation dataset, GrainID once again showed fewer predictive errors
and significantly lower variation in results in comparison with BASEGRAIN and
Wolman pebble counts and maintained this advantage even in uncalibrated
rivers with drone images. Moreover, the existence of vegetation and noise
have little influence on the performance of GrainID. Analysis indicated that
GrainID performed optimally when the image resolution is higher than 1.8 mm pixel−1, the image tile size is 512×512 pixels and the grain area
truncation values (the area of smallest detectable grains) were equal to 18–25 pixels.
Funder
China Scholarship Council
National Natural Science Foundation of China
Natural Sciences and Engineering Research Council of Canada
Subject
Earth-Surface Processes,Geophysics
Reference46 articles.
1. Adams, J.: Gravel Size Analysis from Photographs, J. Hydr. Eng. Div.-ASCE, 105, 1247–1255, https://doi.org/10.1061/JYCEAJ.0005283, 1979.
2. An, C., Hassan, M. A., Ferrer-Boix, C., and Fu, X.: Effect of stress history on sediment transport and channel adjustment in graded gravel-bed rivers, Earth Surf. Dynam., 9, 333–350, https://doi.org/10.5194/esurf-9-333-2021, 2021.
3. Brayshaw, D.: Bankfull and effective discharge in small mountain streams of
British Columbia, The University of British Columbia, Vancouver, Canada,
70–71, https://doi.org/10.14288/1.0072555, 2012.
4. Bunte, K. and Abt, S. R.: Sampling frame for Improving pebble Count Accuracy
in Coarse Gravel-bed streams, J. Am. Water Resour., 37, 1001–1014,
https://doi.org/10.1111/j.1752-1688.2001.tb05528.x, 2001.
5. Buscombe, D.: SediNet: a configurable deep learning model for mixed
qualitative and quantitative optical granulometry, Earth Surf. Proc.
Land., 45, 638–651, https://doi.org/10.1002/esp.4760,
2020.
Cited by
9 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献