a b s t r a c tStudy region: The Upper Colorado River Basin (UCRB), comprised of the Colorado and Gunnison River basins, is the prime water source for much of the western United States. Study focus: Future climate change models were used to drive a hydrologic model of the UCRB to evaluate future water resources and hydropower potential of the basin, using three different climate projections. The Intergovernmental Panel on Climate Change (IPCC) emission scenarios, the A2-business as usual, and the B1-reduced emissions scenarios were evaluated. More than 4500 water diversions and 17 reservoirs were incorporated into the hydrologic model. New hydrological insights for the region: Precipitation projections from climate models vary up to 16%; flow projections revealed greater differences, up to 50%. The climate models projected increase in temperature at low elevations with extreme seasonality at high elevations, although summer temperatures increased at all elevations. The models projected a 60% decline in precipitation at lower elevations and a 74% increase at high elevations, although precipitation declined during the summer months at all elevations. Using the A2 scenario an overall decrease in annual flow was predicted, attributed to a reduction in precipitation and increasing temperature trends; however, this was not consistent during the winter months, BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). 474 M. Kopytkovskiy et al. / Journal of Hydrology: Regional Studies 3 (2015) 473-493which showed an increase in precipitation at high elevations and a modest temperature increase during the winter and resulted in an increase in stream flow. The responses to climate change on reservoir levels varied basin-wide due to variability in precipitation, evapotranspiration, and stream flow. Simulations indicated that water levels in Blue Mesa Reservoir (the largest reservoir in the UCRB) would decline by more than 70% with increasing annual temperatures. Reservoirs with smaller surface areas to the volume ratio were not significantly impacted by evapotranspiration. Our results indicate that hydropower management strategies in the UCRB must adapt to potential climate change, but the required adaptations are dependent on several factors including reservoir size and location.
Machine Learning (ML) algorithms provide an alternative for the prediction of pollutant concentration. We compared eight ML algorithms (Linear Regression (LR), uniform weighting k-Nearest Neighbor (UW-kNN), variable weighting k-Nearest Neighbor (VW-kNN), Support Vector Regression (SVR), Artificial Neural Network (ANN), Regression Tree (RT), Random Forest (RF), and Adaptive Boosting (AdB)) to evaluate the feasibility of ML approaches for estimation of Total Suspended Solids (TSS) using the national stormwater quality database. Six factors were used as features to train the algorithms with TSS concentration as the target parameter: Drainage area, land use, percent of imperviousness, rainfall depth, runoff volume, and antecedent dry days. Comparisons among the ML methods demonstrated a higher degree of variability in model performance, with the coefficient of determination (R2) and Nash–Sutcliffe (NSE) values ranging from 0.15 to 0.77. The Root Mean Square (RMSE) values ranged from 110 mg/L to 220 mg/L. The best fit was obtained using the AdB and RF models, with R2 values of 0.77 and 0.74 in the training step and 0.67 and 0.64 in the prediction step. The NSE values were 0.76 and 0.72 in the training step and 0.67 and 0.62 in the prediction step. The predictions from AdB were sensitive to all six factors. However, the sensitivity level was variable.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.