The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine Learning

Abstract Hydraulic geometry parameters describing river hydrogeomorphic relationships are critical for determining a channel's capacity to convey water and sediment which is important for flood forecasting. Although well‐established, power‐law hydraulic geometry curves have been widely used to...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuyu Y. Chang, Zahra Ghahremani, Laura Manuel, Seyed Mohammad Hassan Erfani, Chaopeng Shen, Sagy Cohen, Kimberly J. Van Meter, Jennifer L. Pierce, Ehab A. Meselhe, Erfan Goharian
Format: Article
Language:English
Published: Wiley 2024-10-01
Series:Water Resources Research
Subjects:
Online Access:https://doi.org/10.1029/2023WR036733
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422710633922560
author Shuyu Y. Chang
Zahra Ghahremani
Laura Manuel
Seyed Mohammad Hassan Erfani
Chaopeng Shen
Sagy Cohen
Kimberly J. Van Meter
Jennifer L. Pierce
Ehab A. Meselhe
Erfan Goharian
author_facet Shuyu Y. Chang
Zahra Ghahremani
Laura Manuel
Seyed Mohammad Hassan Erfani
Chaopeng Shen
Sagy Cohen
Kimberly J. Van Meter
Jennifer L. Pierce
Ehab A. Meselhe
Erfan Goharian
author_sort Shuyu Y. Chang
collection DOAJ
description Abstract Hydraulic geometry parameters describing river hydrogeomorphic relationships are critical for determining a channel's capacity to convey water and sediment which is important for flood forecasting. Although well‐established, power‐law hydraulic geometry curves have been widely used to understand riverine systems and mapping flooding inundation worldwide for the past 70 years, we have become increasingly aware of their limitations. In the present study, we have moved beyond these traditional power‐law relationships, testing the ability of machine‐learning models to provide improved predictions of river width and depth. For this work, we have used an unprecedentedly large river measurement data set (HYDRoSWOT) as well as a suite of watershed predictor data to develop novel data‐driven approaches to better estimate river geometries over the contiguous United States (CONUS). Our Random Forest, XGBoost, and neural network models out‐performed the traditional, regionalized power law‐based hydraulic geometry equations for both width and depth, providing R‐squared values of as high as 0.75 for width and as high as 0.67 for depth, compared with R‐squared values of 0.45 for width and 0.18 for depth from the regional hydraulic geometry equations. Our results also show diverse performance outcomes across stream orders and geographical regions for the different machine‐learning models, demonstrating the value of using multi‐model approaches to maximize the predictability of river geometry. The developed models have been used to create the newly publicly available STREAM‐geo data set, which provides river width, depth, width/depth ratio, and river and stream surface area (%RSSA) for nearly 2.7 million NHDPlus stream reaches across the contiguous US.
format Article
id doaj-art-c69bb7dcabb24327b8deb648d9bea80a
institution Kabale University
issn 0043-1397
1944-7973
language English
publishDate 2024-10-01
publisher Wiley
record_format Article
series Water Resources Research
spelling doaj-art-c69bb7dcabb24327b8deb648d9bea80a2025-08-20T03:30:57ZengWileyWater Resources Research0043-13971944-79732024-10-016010n/an/a10.1029/2023WR036733The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine LearningShuyu Y. Chang0Zahra Ghahremani1Laura Manuel2Seyed Mohammad Hassan Erfani3Chaopeng Shen4Sagy Cohen5Kimberly J. Van Meter6Jennifer L. Pierce7Ehab A. Meselhe8Erfan Goharian9Department of Geography Pennsylvania State University University Park PA USADepartment of Geoscience Boise State University Boise ID USADepartment of River‐Coastal Science and Engineering Tulane University New Orleans LA USADepartment of Civil and Environmental Engineering University of South Carolina Columbia SC USADepartment of Civil and Environmental Engineering Pennsylvania State University University Park PA USADepartment of Geography University of Alabama Tuscaloosa AL USADepartment of Geography Pennsylvania State University University Park PA USADepartment of Geoscience Boise State University Boise ID USADepartment of River‐Coastal Science and Engineering Tulane University New Orleans LA USADepartment of Civil and Environmental Engineering University of South Carolina Columbia SC USAAbstract Hydraulic geometry parameters describing river hydrogeomorphic relationships are critical for determining a channel's capacity to convey water and sediment which is important for flood forecasting. Although well‐established, power‐law hydraulic geometry curves have been widely used to understand riverine systems and mapping flooding inundation worldwide for the past 70 years, we have become increasingly aware of their limitations. In the present study, we have moved beyond these traditional power‐law relationships, testing the ability of machine‐learning models to provide improved predictions of river width and depth. For this work, we have used an unprecedentedly large river measurement data set (HYDRoSWOT) as well as a suite of watershed predictor data to develop novel data‐driven approaches to better estimate river geometries over the contiguous United States (CONUS). Our Random Forest, XGBoost, and neural network models out‐performed the traditional, regionalized power law‐based hydraulic geometry equations for both width and depth, providing R‐squared values of as high as 0.75 for width and as high as 0.67 for depth, compared with R‐squared values of 0.45 for width and 0.18 for depth from the regional hydraulic geometry equations. Our results also show diverse performance outcomes across stream orders and geographical regions for the different machine‐learning models, demonstrating the value of using multi‐model approaches to maximize the predictability of river geometry. The developed models have been used to create the newly publicly available STREAM‐geo data set, which provides river width, depth, width/depth ratio, and river and stream surface area (%RSSA) for nearly 2.7 million NHDPlus stream reaches across the contiguous US.https://doi.org/10.1029/2023WR036733river geomorphologyriver geometryriver widthriver depthhydrologymachine learning
spellingShingle Shuyu Y. Chang
Zahra Ghahremani
Laura Manuel
Seyed Mohammad Hassan Erfani
Chaopeng Shen
Sagy Cohen
Kimberly J. Van Meter
Jennifer L. Pierce
Ehab A. Meselhe
Erfan Goharian
The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine Learning
Water Resources Research
river geomorphology
river geometry
river width
river depth
hydrology
machine learning
title The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine Learning
title_full The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine Learning
title_fullStr The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine Learning
title_full_unstemmed The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine Learning
title_short The Geometry of Flow: Advancing Predictions of River Geometry With Multi‐Model Machine Learning
title_sort geometry of flow advancing predictions of river geometry with multi model machine learning
topic river geomorphology
river geometry
river width
river depth
hydrology
machine learning
url https://doi.org/10.1029/2023WR036733
work_keys_str_mv AT shuyuychang thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT zahraghahremani thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT lauramanuel thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT seyedmohammadhassanerfani thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT chaopengshen thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT sagycohen thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT kimberlyjvanmeter thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT jenniferlpierce thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT ehabameselhe thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT erfangoharian thegeometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT shuyuychang geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT zahraghahremani geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT lauramanuel geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT seyedmohammadhassanerfani geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT chaopengshen geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT sagycohen geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT kimberlyjvanmeter geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT jenniferlpierce geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT ehabameselhe geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning
AT erfangoharian geometryofflowadvancingpredictionsofrivergeometrywithmultimodelmachinelearning