Abstract
Urban water supplies are critical to the growth of the city and the wellbeing of its citizens. However, these supplies can be vulnerable to hydrological extremes, such as droughts and floods, especially if they are the main source of water for the city. Maintaining these supplies and preparing for future conditions is a crucial task for water managers, but predicting hydrological extremes is a challenge. This study tested the abilities of eight statistical learning techniques to predict reservoir levels, given the current hydroclimatic conditions, and provide inferences on the key predictors of reservoir levels. The results showed that random forest, an ensemble, tree-based method, was the best algorithm for predicting reservoir levels. We initially developed the models using Lake Sidney Lanier (Atlanta, Georgia) as the test site; however, further analysis demonstrated that the model based on the random forest algorithm was transferable to other reservoirs, specifically Eagle Creek (Indianapolis, Indiana) and Lake Travis (Austin, Texas). Additionally, we found that although each reservoir was impacted differently, streamflow, city population, and El Niño/Southern Oscillation (ENSO) index were repeatedly among the most important predictors. These are critical variables which can be used by water managers to recognize the potential for reservoir level changes.
Highlights
To minimize these vulnerabilities, water managers must be aware of the likelihood of any major changes in reservoir level that may affect water availability, so that they can begin to prepare and, hopefully, minimize any negative effects
This study focused on determining the most accurate statistical learning technique for predicting reservoir levels based on the current hydroclimatic conditions
We hypothesized that random forest would perform well, as tree-based methods have been successful in predicting reservoir conditions[5,6]
Summary
Water managers must be aware of the likelihood of any major changes in reservoir level that may affect water availability, so that they can begin to prepare and, hopefully, minimize any negative effects. The authors leveraged a tree-based model that used weather data from the European Centre for Medium-Range Weather Forecasts (ECMWF) as the input to predict water levels They found that the model could adequately predict high-flow conditions within the 9 days, which would allow water managers to implement the regulating features and reduce the risk of flooding downstream. When they repeated their analysis for low-flow scenarios, the authors found that they could not accurately predict droughts, likely because droughts require longer forecasts, which cannot always be made with the meteorological data used in this study. We hypothesized that the random forest model would perform the best, as both Ficchi et al and Yang et al demonstrated the ability of tree-based models to predict reservoir levels[5,6]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
