Modeling Bankfull Channel Geometry Based on Watershed and Precipitation Characteristics Using Dimensionless Parameters

Bastola, Hridaya; Diplas, Panayiotis

doi:10.1029/2022wr032688

Cited by 2 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All variables undergo logarithmic transformation to fulfill the manuscript submitted to Water Resources Research assumptions inherent to regression modeling due to the skewness observed (Holder, 1986). This methodology has been used widely in developing prediction and forecasting models in waterrelated sciences (J et al, 2020;Bastola & Diplas, 2023). In this research, optimized models are developed for each specific target variable by implementing forward stepwise regression, which aids in identifying significant variables for modeling efficacy.…”

Section: Multi-linear Regression (Mlr)mentioning

confidence: 99%

Bankfull and Mean-flow Channel Geometry Estimation through a Hybrid Multi-Regression and Machine Learning Algorithms across the CONtiguous United States (CONUS)

Zarrabi,

McDermott,

Erfani

et al. 2024

Preprint

View full text Add to dashboard Cite

Widely adopted models for estimating channel geometry attributes rely on simplistic power-law (hydraulic geometry) equations. This study presents a new generation of channel geometry models based on a hybrid approach combining traditional statistical methods (Multi-Linear Regression (MLR)) and advanced tree-based Machine Learning (ML) algorithms (Random Forest Regression (RFR) and eXtreme Gradient Boosting Regression (XGBR)), utilizing novel datasets. To achieve this, a new preprocessing method was applied to refine an extensive observational dataset, namely the HYDRoacoustic dataset supporting Surface Water Oceanographic Topography (HYDRoSWOT). This process improved data quality and identified observations representing bankfull and mean-flow conditions. A compiled dataset, combining the preprocessed dataset with datasets containing additional catchment attributes like the National Hydrography Dataset Plus (NHDplusv2.1), was then used to train a suite of models to predict channel width and depth under bankfull and mean-flow conditions. The analysis shows that tree-based ML algorithms outperform traditional statistical methods in accuracy and handling the data but face limitations in prediction capabilities for streams with characteristics outside the training range. Consequently, a hybrid method was selected, combining XGBR for streams within the dataset range and MLR for those outside it. Two tiers of models were developed for each attribute using discharges derived from distinct sources (HYDRoSWOT and NHDPlusV2.1, respectively), where the second tier of models offers applicability across approximately 2.6 million streams within NHDplusv2.1. Comprehensive independent evaluations are conducted to assess the capability of the developed models in providing stream/reach-averaged (rather than at-a-station) predictions for locations outside the training and testing datasets.

show abstract

Section: Multi-linear Regression (Mlr)mentioning

confidence: 99%

Bankfull and Mean-flow Channel Geometry Estimation through a Hybrid Multi-Regression and Machine Learning Algorithms across the CONtiguous United States (CONUS)

Zarrabi,

McDermott,

Erfani

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Is the ordinary high water mark ordinarily at bankfull? Applying a weight‐of‐evidence approach to stream delineation

David,

Hamill

2024

J American Water Resour Assoc

View full text Add to dashboard Cite

The ordinary high water mark (OHWM) is a regulatory boundary essential to identifying the lateral jurisdictional limits of rivers and streams in the United States (U.S.). Bankfull is a scientific concept that has been defined and identified in a multitude of ways by scientists. Geomorphologist and hydrologist have long recognized that there can be variability in the identification of bankfull depending on how bankfull is defined. Furthermore, this variability is only increased by the inherent variability in stream characteristics that occurs along a reach of channel. Because of the overlap in the regulatory definition of OHWM and the scientific definitions of bankfull, one of the primary purposes of the study is to apply the definition of OHWM and compare it to bankfull in a variety of channel types in different climatic, hydrologic, and geologic settings. Our results show that there is a clear overlap between the identification of the OHWM and bankfull elevations. Regulatory practitioners are generally not specialized in fluvial geomorphology and yet are tasked with consistently and accurately identifying the OHWM in a variety of stream types throughout the U.S. Therefore, we also present how to apply a weight‐of‐evidence approach through a clear step‐by‐step process to potentially improve consistency and accuracy in identification of OHWM and bankfull by both scientists and non‐scientists.

show abstract

Modeling Bankfull Channel Geometry Based on Watershed and Precipitation Characteristics Using Dimensionless Parameters

Cited by 2 publications

References 57 publications

Bankfull and Mean-flow Channel Geometry Estimation through a Hybrid Multi-Regression and Machine Learning Algorithms across the CONtiguous United States (CONUS)

Bankfull and Mean-flow Channel Geometry Estimation through a Hybrid Multi-Regression and Machine Learning Algorithms across the CONtiguous United States (CONUS)

Is the ordinary high water mark ordinarily at bankfull? Applying a weight‐of‐evidence approach to stream delineation

Contact Info

Product

Resources

About