Application of Deep Learning to Estimate Mean River Cross-Sectional Depth

Show simple item record

dc.contributor Keellings, David
dc.contributor Moftakhari, Hamed
dc.contributor.advisor Cohen, Sagy Raney, Arthur Austin
dc.contributor.other University of Alabama Tuscaloosa 2021-11-23T14:33:50Z 2021-11-23T14:33:50Z 2021
dc.identifier.other u0015_0000001_0003892
dc.identifier.other Raney_alatus_0004M_14616
dc.description Electronic Thesis or Dissertation en_US
dc.description.abstract Estimates of riverine channel geometry play a vital role in the physical representation of stream networks in models used to predict flood and drought conditions, manage water resources, and increase our knowledge of fluvial conditions under a changing climate. A well established body of literature exists that explains the relationship between channel geometry parameters width, depth, and velocity to instantaneous river discharge using a log-log linear power-law regression. In this study, a state-of-the-art deep learning regression model is presented and compared against the power-law method to evaluate their abilities to estimate cross-sectional mean river depth. Results reveal three key findings, the neural network: (1) decreases RMSE by 22% verse a CONUS scale power-law equation, (2) reduces prediction variance across Strahler stream orders, and (3) generally outperforms regional power-law equations with an average decrease in RMSE of 8.7%. Lastly, a reach-level CONUS dataset of estimated mean river depth is delivered. en_US
dc.format.medium electronic
dc.format.mimetype application/pdf
dc.language English
dc.language.iso en_US
dc.publisher University of Alabama Libraries
dc.relation.ispartof The University of Alabama Electronic Theses and Dissertations
dc.relation.ispartof The University of Alabama Libraries Digital Collections
dc.relation.hasversion born digital
dc.rights All rights reserved by the author unless otherwise indicated. en_US
dc.subject Deep learning
dc.subject Hydraulic Geometry
dc.subject Hydrology
dc.subject Neural Network
dc.title Application of Deep Learning to Estimate Mean River Cross-Sectional Depth en_US
dc.type thesis
dc.type text University of Alabama. Department of Geography Geography The University of Alabama master's M.S.

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


My Account