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

Wagena, Moges B.Goering, DustinCollick, Amy S.Bock, EmilyFuka, Daniel R.Buda, Anthony R.Easton, Zachary M.2021-03-182021-03-182020-041364-8152104669http://hdl.handle.net/10919/102743Streamflow 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.application/pdfenPublic DomainSWAT-VSAANNsARMAForecastingStochastic modelProcess-based modelBayesian modelComparison of short-term streamflow forecasting using stochastic time series, neural networks, process-based, and Bayesian modelsArticle - RefereedEnvironmental Modelling & Softwarehttps://doi.org/10.1016/j.envsoft.2020.1046691261873-6726