skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning

Abstract

Recent alluvial sediments in riverbeds play a significant role in controlling hydrologic exchange flows (HEFs) in river systems. The alluvial layer is usually associated with strong heterogeneity in physical properties (e.g., permeability and hydraulic conductivity), which affects local HEFs and therefore biogeochemical processes. The spatial distribution of these physical properties needs to be determined to inform the numerical models used to reveal the realistic hydro-biogeochemical behaviors. Such information can be obtained based on the intrinsic link between sediment grain-size distribution and hydraulic properties where sediment texture information is available. However, grain-size measurements are usually spatially sparse and do not have adequate coverage and resolution, particularly for a relatively large domain such as the Hanford Reach of the Columbia River. In this paper, we adopted machine learning (ML) approaches for categorizing and mapping the spatial distributions of riverbed substrate grain size and filling in missing areas of substrate data using the ML models along the reach. Such ML models for substrate size mapping were trained at 13,372 locations using measured substrate sizes along with observed and simulated attributes, including bathymetric attributes (e.g., elevation, slope, and aspect ratio) from LIDAR and bathymetric surveys, and hydrodynamic properties (e.g., water depth, velocity, shear stress,more » and their statistical moments). An ensemble bagging-based ML technique, Random Forest, was adopted to identify the most influential factors as predictors to develop the predictive models with over-fitting issues addressed. The models were evaluated with respect to each individual substrate size class and the lumped group, and then used to generate the final substrate size maps covering all the grid cells in the numerical modeling domain.« less

Authors:
ORCiD logo [1]; ORCiD logo [1];  [1];  [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Publication Date:
Research Org.:
Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Biological and Environmental Research (BER)
OSTI Identifier:
1755384
Report Number(s):
PNNL-SA-151819
Journal ID: ISSN 2624-9375
Grant/Contract Number:  
AC05-76RL01830
Resource Type:
Accepted Manuscript
Journal Name:
Frontiers in Water
Additional Journal Information:
Journal Volume: 2; Journal ID: ISSN 2624-9375
Publisher:
Frontiers
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES; machine learning; Random Forest; spatial heterogeneity; streambed sediment characteristics; grain-size distribution; hydrologic exchange flows

Citation Formats

Ren, Huiying, Hou, Zhangshuan, Duan, Zhuoran, Song, Xuehang, Perkins, William A., Richmond, Marshall C., Arntzen, Evan V., and Scheibe, Timothy D.. Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning. United States: N. p., 2020. Web. https://doi.org/10.3389/frwa.2020.551627.
Ren, Huiying, Hou, Zhangshuan, Duan, Zhuoran, Song, Xuehang, Perkins, William A., Richmond, Marshall C., Arntzen, Evan V., & Scheibe, Timothy D.. Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning. United States. https://doi.org/10.3389/frwa.2020.551627
Ren, Huiying, Hou, Zhangshuan, Duan, Zhuoran, Song, Xuehang, Perkins, William A., Richmond, Marshall C., Arntzen, Evan V., and Scheibe, Timothy D.. Mon . "Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning". United States. https://doi.org/10.3389/frwa.2020.551627. https://www.osti.gov/servlets/purl/1755384.
@article{osti_1755384,
title = {Spatial Mapping of Riverbed Grain-Size Distribution Using Machine Learning},
author = {Ren, Huiying and Hou, Zhangshuan and Duan, Zhuoran and Song, Xuehang and Perkins, William A. and Richmond, Marshall C. and Arntzen, Evan V. and Scheibe, Timothy D.},
abstractNote = {Recent alluvial sediments in riverbeds play a significant role in controlling hydrologic exchange flows (HEFs) in river systems. The alluvial layer is usually associated with strong heterogeneity in physical properties (e.g., permeability and hydraulic conductivity), which affects local HEFs and therefore biogeochemical processes. The spatial distribution of these physical properties needs to be determined to inform the numerical models used to reveal the realistic hydro-biogeochemical behaviors. Such information can be obtained based on the intrinsic link between sediment grain-size distribution and hydraulic properties where sediment texture information is available. However, grain-size measurements are usually spatially sparse and do not have adequate coverage and resolution, particularly for a relatively large domain such as the Hanford Reach of the Columbia River. In this paper, we adopted machine learning (ML) approaches for categorizing and mapping the spatial distributions of riverbed substrate grain size and filling in missing areas of substrate data using the ML models along the reach. Such ML models for substrate size mapping were trained at 13,372 locations using measured substrate sizes along with observed and simulated attributes, including bathymetric attributes (e.g., elevation, slope, and aspect ratio) from LIDAR and bathymetric surveys, and hydrodynamic properties (e.g., water depth, velocity, shear stress, and their statistical moments). An ensemble bagging-based ML technique, Random Forest, was adopted to identify the most influential factors as predictors to develop the predictive models with over-fitting issues addressed. The models were evaluated with respect to each individual substrate size class and the lumped group, and then used to generate the final substrate size maps covering all the grid cells in the numerical modeling domain.},
doi = {10.3389/frwa.2020.551627},
journal = {Frontiers in Water},
number = ,
volume = 2,
place = {United States},
year = {2020},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Rapid identification of transience in streambed conductance by inversion of floodwave responses: RAPID IDENTIFICATION OF TRANSIENCE IN STREAMBED CONDUCTANCE
journal, April 2016

  • Gianni, Guillaume; Richon, Julien; Perrochet, Pierre
  • Water Resources Research, Vol. 52, Issue 4
  • DOI: 10.1002/2015WR017154

Effects of Streambed Conductance on Stream Depletion
journal, January 2015

  • Lackey, Greg; Neupauer, Roseanna; Pitlick, John
  • Water, Vol. 7, Issue 12
  • DOI: 10.3390/w7010271

Conceptualization and Calibration of Anisotropic Alluvial Systems: Pitfalls and Biases
journal, July 2018

  • Gianni, Guillaume; Doherty, John; Brunner, Philip
  • Groundwater, Vol. 57, Issue 3
  • DOI: 10.1111/gwat.12802

Hyporheic flow and residence time distributions in heterogeneous cross-bedded sediment: HYPORHEIC FLOW IN HETEROGENEOUS SEDIMENT
journal, August 2009

  • Sawyer, Audrey Hucks; Cardenas, M. Bayani
  • Water Resources Research, Vol. 45, Issue 8
  • DOI: 10.1029/2008WR007632

An assessment of the effectiveness of a random forest classifier for land-cover classification
journal, January 2012


Conducting Slug Tests in Mini-Piezometers: B.G. Fritz Ground Water xx, no. x: x-xx
journal, March 2015

  • Fritz, Bradley G.; Mackley, Rob D.; Arntzen, Evan V.
  • Groundwater, Vol. 54, Issue 2
  • DOI: 10.1111/gwat.12335

Effects of fluctuating river flow on groundwater/surface water mixing in the hyporheic zone of a regulated, large cobble bed river
journal, January 2006

  • Arntzen, Evan V.; Geist, David R.; Dresel, P. Evan
  • River Research and Applications, Vol. 22, Issue 8
  • DOI: 10.1002/rra.947

Multiple classifiers applied to multisource remote sensing data
journal, January 2002

  • Briem, G. J.; Benediktsson, J. A.; Sveinsson, J. R.
  • IEEE Transactions on Geoscience and Remote Sensing, Vol. 40, Issue 10
  • DOI: 10.1109/TGRS.2002.802476

Hyporheic exchange with heterogeneous streambeds: Laboratory experiments and modeling: HYPORHEIC EXCHANGE WITH HETEROGENEOUS STREAMBEDS
journal, November 2004

  • Salehin, Mashfiqus; Packman, Aaron I.; Paradis, Matthew
  • Water Resources Research, Vol. 40, Issue 11
  • DOI: 10.1029/2003WR002567

Simulating Flood‐Induced Riverbed Transience Using Unmanned Aerial Vehicles, Physically Based Hydrological Modeling, and the Ensemble Kalman Filter
journal, November 2018

  • Tang, Qi; Schilling, Oliver S.; Kurtz, Wolfgang
  • Water Resources Research, Vol. 54, Issue 11
  • DOI: 10.1029/2018WR023067

Advances in understanding river-groundwater interactions: River-Groundwater Interactions
journal, September 2017

  • Brunner, Philip; Therrien, René; Renard, Philippe
  • Reviews of Geophysics, Vol. 55, Issue 3
  • DOI: 10.1002/2017RG000556

Predictive soil parent material mapping at a regional-scale: A Random Forest approach
journal, February 2014


River-aquifer interactions in a semiarid environment investigated using point and reach measurements
journal, April 2014

  • McCallum, Andrew M.; Andersen, Martin S.; Rau, Gabriel C.
  • Water Resources Research, Vol. 50, Issue 4
  • DOI: 10.1002/2012WR012922

Identification and mapping of riverbed sediment facies in the Columbia River through integration of field observations and numerical simulations
journal, February 2019

  • Hou, Zhangshuan; Scheibe, Timothy D.; Murray, Christopher J.
  • Hydrological Processes, Vol. 33, Issue 8
  • DOI: 10.1002/hyp.13396

Random forest classifier for remote sensing classification
journal, January 2005


Using Bayesian Networks for Sensitivity Analysis of Complex Biogeochemical Models
journal, April 2019

  • Dai, Heng; Chen, Xingyuan; Ye, Ming
  • Water Resources Research, Vol. 55, Issue 4
  • DOI: 10.1029/2018WR023589

Geomorphic controls on hyporheic exchange flow in mountain streams: GEOMORPHIC CONTROLS ON HYPORHEIC EXCHANGE
journal, January 2003

  • Kasahara, Tamao; Wondzell, Steven M.
  • Water Resources Research, Vol. 39, Issue 1
  • DOI: 10.1029/2002WR001386

Random forests as a tool for ecohydrological distribution modelling
journal, October 2007


The influence of riverbed heterogeneity patterns on river-aquifer exchange fluxes under different connection regimes
journal, November 2017


Application of Support Vector Machine, Random Forest, and Genetic Algorithm Optimized Random Forest Models in Groundwater Potential Mapping
journal, April 2017

  • Naghibi, Seyed Amir; Ahmadi, Kourosh; Daneshi, Alireza
  • Water Resources Management, Vol. 31, Issue 9
  • DOI: 10.1007/s11269-017-1660-3

Interactions between groundwater and surface water: the state of the science
journal, January 2002


Effect of Rapidly Changing River Stage on Uranium Flux through the Hyporheic Zone
journal, November 2007


An empirical comparison of selection measures for decision-tree induction
journal, March 1989


Hyporheic flow and transport processes: Mechanisms, models, and biogeochemical implications: HYPORHEIC FLOW AND TRANSPORT PROCESSES
journal, October 2014

  • Boano, F.; Harvey, J. W.; Marion, A.
  • Reviews of Geophysics, Vol. 52, Issue 4
  • DOI: 10.1002/2012RG000417

Statistical Distribution of Streambed Vertical Hydraulic Conductivity along the Platte River, Nebraska
journal, July 2010


Comparison of Instream Methods for Measuring Hydraulic Conductivity in Sandy Streambeds
journal, November 2001


Modulating factors of hydrologic exchanges in a large-scale river reach: Insights from three-dimensional computational fluid dynamics simulations
journal, October 2018

  • Bao, Jie; Zhou, Tian; Huang, Maoyi
  • Hydrological Processes, Vol. 32, Issue 23
  • DOI: 10.1002/hyp.13266

Measurement of streambed hydraulic conductivity and its anisotropy
journal, November 2000


Drought Conditions Maximize the Impact of High‐Frequency Flow Variations on Thermal Regimes and Biogeochemical Function in the Hyporheic Zone
journal, October 2018

  • Song, Xuehang; Chen, Xingyuan; Stegen, James
  • Water Resources Research, Vol. 54, Issue 10
  • DOI: 10.1029/2018WR022586

Effects of Ground Water Exchange on the Hydrology and Ecology of Surface Water
journal, May 2002


Impact of heterogeneity, bed forms, and stream curvature on subchannel hyporheic exchange: MODELING STUDY OF HYPORHEIC EXCHANGE
journal, August 2004

  • Cardenas, M. Bayani; Wilson, J. L.; Zlotnik, V. A.
  • Water Resources Research, Vol. 40, Issue 8
  • DOI: 10.1029/2004WR003008

River corridor science: Hydrologic exchange and ecological consequences from bedforms to basins: RIVER CORRIDORS FROM BEDFORMS TO BASINS
journal, September 2015

  • Harvey, Jud; Gooseff, Michael
  • Water Resources Research, Vol. 51, Issue 9
  • DOI: 10.1002/2015WR017617

Heterogeneous or homogeneous? Implications of simplifying heterogeneous streambeds in models of losing streams
journal, March 2012


The ecological significance of exchange processes between rivers and groundwater
journal, February 1997


The Functional Significance of the Hyporheic zone in Streams and Rivers
journal, November 1998


Predicting redox-sensitive contaminant concentrations in groundwater using random forest classification: PREDICTING CONTAMINANT CONCENTRATIONS
journal, August 2017

  • Tesoriero, Anthony J.; Gronberg, Jo Ann; Juckem, Paul F.
  • Water Resources Research, Vol. 53, Issue 8
  • DOI: 10.1002/2016WR020197

Geochemical and Microbial Community Attributes in Relation to Hyporheic Zone Geological Facies
journal, September 2017


Horizontal hydraulic conductivity of shallow streambed sediments and comparison with the grain-size analysis results
journal, May 2011

  • Lu, Chengpeng; Chen, Xunhong; Cheng, Cheng
  • Hydrological Processes, Vol. 26, Issue 3
  • DOI: 10.1002/hyp.8143

Correlations of Permeability and Grain Size
journal, September 1989


Random Forests
journal, January 2001


Random Forests for land cover classification
journal, March 2006

  • Gislason, Pall Oskar; Benediktsson, Jon Atli; Sveinsson, Johannes R.
  • Pattern Recognition Letters, Vol. 27, Issue 4
  • DOI: 10.1016/j.patrec.2005.08.011

Heterogeneity in ground water-surface water interactions in the hyporheic zone of a salmonid spawning stream
journal, January 2003

  • Malcolm, I. A.; Soulsby, C.; Youngson, A. F.
  • Hydrological Processes, Vol. 17, Issue 3
  • DOI: 10.1002/hyp.1156

Estimating the Spatial Extent of Unsaturated Zones in Heterogeneous River-Aquifer Systems: ESTIMATING UNSATURATED ZONES
journal, December 2017

  • Schilling, Oliver S.; Irvine, Dylan J.; Hendricks Franssen, Harrie-Jan
  • Water Resources Research, Vol. 53, Issue 12
  • DOI: 10.1002/2017WR020409