Comparison of short-term streamflow forecasting using stochastic time series, neural networks, process-based, and Bayesian models

Simple item page
dc.contributor.authorWagena, Moges B.en
dc.contributor.authorGoering, Dustinen
dc.contributor.authorCollick, Amy S.en
dc.contributor.authorBock, Emilyen
dc.contributor.authorFuka, Daniel R.en
dc.contributor.authorBuda, Anthony R.en
dc.contributor.authorEaston, Zachary M.en
dc.contributor.departmentBiological Systems Engineeringen
dc.date.accessioned2021-03-18T19:17:45Zen
dc.date.available2021-03-18T19:17:45Zen
dc.date.issued2020-04en
dc.description.abstractStreamflow forecasts are essential for water resources management. Although there are many methods for forecasting streamflow, real-time forecasts remain challenging. This study evaluates streamflow forecasts using a process-based model (Soil and Water Assessment Tool-Variable Source Area model-SWAT-VSA), a stochastic model (Artificial Neural Network -ANN), an Auto-Regressive Moving-Average (ARMA) model, and a Bayesian ensemble model that utilizes the SWAT-VSA, ANN, and ARMA results. Streamflow is forecast from 1 to 8 d, forced with Quantitative Precipitation Forecasts from the US National Weather Service. Of the individual models, SWAT-VSA and the ANN provide better predictions of total streamflow (NSE 0.60-0.70) and peak flow, but underpredicted low flows. During the forecast period the ANN had the highest predictive power (NSE 0.44-0.64), however all three models underpredicted peak flow. The Bayesian ensemble forecast streamflow with the most skill for all forecast lead times (NSE 0.49-0.67) and provided a quantification of prediction uncertainty.en
dc.description.adminPublic domain – authored by a U.S. government employeeen
dc.description.notesWe would like to acknowledge high-performance computing support from Yellowstone (http://n2t.net/ark:/85065/d7wd3xhc) provided by NCAR's Computational and Information Systems Laboratory, support from the National Science Foundation under award numbers 1360415 and 1343802, and funding support from the USDA under project number 2012-67019-19434. All data and methods used in this manuscript are available upon request.en
dc.description.sponsorshipNational Science FoundationNational Science Foundation (NSF) [1360415, 1343802]; USDAUnited States Department of Agriculture (USDA) [2012-67019-19434]en
dc.format.mimetypeapplication/pdfen
dc.identifier.doihttps://doi.org/10.1016/j.envsoft.2020.104669en
dc.identifier.eissn1873-6726en
dc.identifier.issn1364-8152en
dc.identifier.other104669en
dc.identifier.urihttp://hdl.handle.net/10919/102743en
dc.identifier.volume126en
dc.language.isoenen
dc.rightsPublic Domainen
dc.rights.urihttp://creativecommons.org/publicdomain/mark/1.0/en
dc.subjectSWAT-VSAen
dc.subjectANNsen
dc.subjectARMAen
dc.subjectForecastingen
dc.subjectStochastic modelen
dc.subjectProcess-based modelen
dc.subjectBayesian modelen
dc.titleComparison of short-term streamflow forecasting using stochastic time series, neural networks, process-based, and Bayesian modelsen
dc.title.serialEnvironmental Modelling & Softwareen
dc.typeArticle - Refereeden
dc.type.dcmitypeTexten
dc.type.dcmitypeStillImageen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1-s2.0-S1364815219308047-main.pdf
Size:
3.84 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

Scholarly Works, Biological Systems Engineering
Destination Area: Global Systems Science (GSS)