Predicting Urban Reservoir Levels Using Statistical Learning Techniques

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.

Analyzing the climate sensitivity of the coupled water-electricity demand nexus in the Midwestern United States

“…The impact of El Niño-a large scale climate predictor-aligns with previous results focusing on the water supply side of urban water systems [35]. In other words, the results from this study indicate that the El Niño plays an important role in both aspects of urban water availability (supply and demand).…”

“…There was a focus on variables that are easily measured by meteorological stations because of the availability of such data, as well as the results of previous studies, which showed the importance of meteorological variables on water and electricity demand [32,33,23,34]. Similarly, it has been shown that the El Niño/Southern Oscillation plays an important role in affecting hydroclimatic processes across the US, and reservoir levels in particular [35], and thus making it an important variable to include in the analysis of residential water use.…”

Evaluation of Random Forest for short-term daily streamflow forecast in rainfall and snowmelt driven watersheds

“…Linear model in the same study, however, considered the coefficient for precipitation to be significant (p << 0.01) while temperature coefficient was not (p = 0.08). In Obringer and Nateghi (2018), authors predicted daily reservoir levels in three reservoirs in Indiana, Texas, and Atlanta using RF and other ML techniques. Precipitation was reported as the least important variable and ranked behind dew point temperature and humidity.…”

Conversations on Rethinking Human Development

“…Rain is the main way water resources are replenished, and the state of our water resources and the climate are well researched. So, from scientific research for drought management (Obringer and Nateghi 2018) to rain collection and water purification technologies, there are numerous and affordable tools for better water management that can easily be deployed at a community level.…”