Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Quantifying Streambed Grain Size, Uncertainty, and Hydrobiogeochemical Parameters Using Machine Learning Model YOLO

Journal Article · · Water Resources Research
DOI:https://doi.org/10.1029/2023WR036456· OSTI ID:2478183
 [1];  [1];  [2];  [1];  [3];  [1];  [1];  [1];  [1];  [4];  [1];  [1];  [1];  [1];  [1];  [1];  [5]
  1. Pacific Northwest National Laboratory Richland WA USA
  2. School of Petroleum Engineering Yangtze University Wuhan China
  3. Center for Western Weather and Water Extremes Scripps Institution of Oceanography University of California San Diego San Diego CA USA
  4. Department of Geoscience University of Wisconsin ‐ Madison Madison WI USA
  5. Pacific Northwest National Laboratory Richland WA USA, School of the Environment Washington State University Pullman WA USA
+ Show Author Affiliations

Abstract

Streambed grain sizes control river hydro‐biogeochemical (HBGC) processes and functions. However, measuring their quantities, distributions, and uncertainties is challenging due to the diversity and heterogeneity of natural streams. This work presents a photo‐driven, artificial intelligence (AI)‐enabled, and theory‐based workflow for extracting the quantities, distributions, and uncertainties of streambed grain sizes from photos. Specifically, we first trained You Only Look Once, an object detection AI, using 11,977 grain labels from 36 photos collected from nine different stream environments. We demonstrated its accuracy with a coefficient of determination of 0.98, a Nash–Sutcliffe efficiency of 0.98, and a mean absolute relative error of 6.65% in predicting the median grain size of 20 ground‐truth photos representing nine typical stream environments. The AI is then used to extract the grain size distributions and determine their characteristic grain sizes, including the 10th, 50th, 60th, and 84th percentiles, for 1,999 photos taken at 66 sites within a watershed in the Northwest US. The results indicate that the 10th, median, 60th, and 84th percentiles of the grain sizes follow log‐normal distributions, with most likely values of 2.49, 6.62, 7.68, and 10.78 cm, respectively. The average uncertainties associated with these values are 9.70%, 7.33%, 9.27%, and 11.11%, respectively. These data allow for the computation of the quantities, distributions, and uncertainties of streambed HBGC parameters, including Manning's coefficient, Darcy‐Weisbach friction factor, top layer interstitial velocity magnitude, and nitrate uptake velocity. Additionally, major sources of uncertainty in grain sizes and their impact on HBGC parameters are examined.

Sponsoring Organization:
USDOE
Grant/Contract Number:
NONE; AC05-76RL01830
OSTI ID:
2478183
Alternate ID(s):
OSTI ID: 2530471
OSTI ID: 2479107
Journal Information:
Water Resources Research, Journal Name: Water Resources Research Journal Issue: 11 Vol. 60; ISSN 0043-1397
Publisher:
American Geophysical Union (AGU)Copyright Statement
Country of Publication:
United States
Language:
English

References (63)

Subsurface flow in lowland river gravel bars: SUBSURFACE FLOW GRAVEL BARS journal September 2017
Equations for hydraulic conductivity estimation from particle size distribution: A dimensional analysis journal September 2017
Texture‐based image segmentation applied to the quantification of superficial sand in salmonid river gravels journal January 2005
Time to abandon the Manning equation? journal October 2010
GRADISTAT: a grain size distribution and statistics package for the analysis of unconsolidated sediments journal September 2001
Photo-sieving: A method for grain-size analysis of coarse-grained, unconsolidated bedding surfaces journal January 1986
Quantifying flow resistance in mountain streams using computational fluid dynamics modeling over structure‐from‐motion photogrammetry‐derived microtopography journal June 2019
SediNet: a configurable deep learning model for mixed qualitative and quantitative optical granulometry journal March 2020
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 journal December 2023
Automated grain sizing from uncrewed aerial vehicles imagery of a gravel‐bed river: Benchmarking of three object‐based methods journal January 2024
Heterogeneous characteristics of streambed saturated hydraulic conductivity of the Touchet River, south eastern Washington, USA journal April 2009
A heat pulse technique for the determination of small-scale flow directions and flow velocities in the streambed of sand-bed streams journal March 2011
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition book January 2014
Flow resistance in gravel-bed rivers: Progress in research journal September 2014
The clogging of riverbeds: A review of the physical processes journal April 2023
High-resolution grain-size characterisation of gravel bars using imagery analysis and geo-statistics journal December 2005
Using UAS optical imagery and SfM photogrammetry to characterize the surface grain size of gravel bars in a braided river (Vénéon River, French Alps) journal May 2017
A 3D analysis algorithm to improve interpretation of heat pulse sensor results for the determination of small-scale flow directions and velocities in the hyporheic zone journal December 2012
Quantification of uncertainty in estimated nitrate-N loads in agricultural watersheds journal November 2014
The deep challenge of nitrate pollution in river water of China journal May 2021
Comparison of three grain size measuring methods applied to coarse-grained gravel deposits journal March 2023
Nitrate concentrations predominantly driven by human, climate, and soil properties in US rivers journal November 2022
Pore-resolved investigation of turbulent open channel flow over a randomly packed permeable sediment bed journal September 2023
Catchment‐scale mapping of surface grain size in gravel bed rivers using airborne digital imagery journal July 2004
Automated grain size measurements from airborne remote sensing for long profile measurements of fluvial grain sizes: SIZE MEASUREMENTS OF FLUVIAL GRAIN SIZES journal November 2005
Flow resistance equations for gravel‐ and boulder‐bed streams journal May 2007
A universal approximation of grain size from images of noncohesive sediment journal June 2010
Evaluation of flow resistance in gravel-bed rivers through a large field data set: EVALUATION OF FLOW RESISTANCE EQUATIONS journal July 2011
Advances in the simulation and automated measurement of well‐sorted granular material: 2. Direct measures of particle properties journal April 2012
Combined Effects of Stream Hydrology and Land Use on Basin‐Scale Hyporheic Zone Denitrification in the Columbia River Basin journal December 2022
A comparison of surface sampling methods for coarse fluvial sediments journal October 1996
Transfer of nonsorbing solutes to a streambed with bed forms: Laboratory experiments journal January 1997
Transfer of nonsorbing solutes to a streambed with bed forms: Theory journal January 1997
A method of sampling coarse river-bed material journal January 1954
An Improved Method for Size Distribution of Stream Bed Gravel journal October 1970
Stream denitrification across biomes and its response to anthropogenic nitrate loading journal March 2008
Denitrification in the Mississippi River network controlled by flow through river bedforms journal October 2015
Sampling Procedures for Coarse Fluvial Sediments journal August 1971
Gravel Size Analysis from Photographs journal October 1979
Automated extraction of grain-size data from gravel surfaces using digital image processing journal November 2001
A review of empirical equations for estimating stream roughness and their application to four streams in Victoria journal January 2004
You Only Look Once: Unified, Real-Time Object Detection conference June 2016
CSPNet: A New Backbone that can Enhance Learning Capability of CNN conference June 2020
Mask R-CNN conference October 2017
Geomorphological Analysis Using Unpiloted Aircraft Systems, Structure from Motion, and Deep Learning conference October 2020
Transferable wavelet method for grain‐size distribution from images of sediment surfaces and thin sections, and other natural granular patterns journal June 2013
Mapping sub‐pixel fluvial grain sizes with hyperspatial imagery journal December 2013
Factoring stream turbulence into global assessments of nitrogen pollution journal March 2018
A Simple Autocorrelation Algorithm for Determining Grain Size from Digital Images of Sediment journal January 2004
Parallel distributed processing model with local space-invariant interconnections and its optical architecture journal January 1990
Spatial Study 2021: Sample-Based Surface Water Chemistry and Organic Matter Characterization across Watersheds in the Yakima River Basin, Washington, USA (v2)
  • Grieger, Samantha; Barnes, Morgan; Borton, Mikayla A.
  • Environmental System Science Data Infrastructure for a Virtual Ecosystem https://doi.org/10.15485/1898914
dataset January 2022
Spatial Study 2022: Surface Water Samples, Cotton Strip Degradation, and Hydrologic Sensor Data across the Yakima River Basin, Washington, USA (v3)
  • Delgado, Dillman; Barnes, Morgan; Boehnke, Brandon T.
  • Environmental System Science Data Infrastructure for a Virtual Ecosystem https://doi.org/10.15485/1969566
dataset January 2023
Spatial Study 2022: Water Column, Sediment, and Total Ecosystem Respiration Rates across the Yakima River Basin, Washington, USA
  • Kaufman, Matthew H.; Delgado, Dillman; Barnes, Morgan
  • Environmental System Science Data Infrastructure for a Virtual Ecosystem https://doi.org/10.15485/1987520
dataset January 2023
Artificial intelligence models, photos, and data associated with the manuscript “Quantifying streambed grain sizes and hydro-biogeochemistry using YOLO and photos” dataset January 2023
Selection and Application of Manning's Roughness Values in Two-Dimensional Hydraulic Models book March 2024
Modelling the effect of oxygen concentration on nitrite accumulation in a biofilm airlift suspension reactor journal July 1997
Sampling surface and subsurface particle-size distributions in wadable gravel-and cobble-bed streams for analyses in sediment transport, hydraulics, and streambed monitoring report January 2001
Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning journal November 2020
A Deep Learning-Based Method for Quantifying and Mapping the Grain Size on Pebble Beaches journal November 2020
Dissolved oxygen transfer to sediments by sweep and eject motions in aquatic environments journal March 2008
Nitrate removal in stream ecosystems measured by 15N addition experiments: Denitrification journal May 2009
Dataset and model weights for ImageGrains dataset January 2023
Notes on the use of propagation of error formulas journal October 1966

Similar Records

Related Subjects