Applying Machine Learning and Earth Observations to Model Urban Water System Reliability, Resilience, and Vulnerability

Reliability, Resilience, and vulnerability (RRV) inform urban water system (UWS) operational and management decisions. Systems dynamics modeling can replicate the physical UWS processes, but high parameterization, immense development period, and software licensing present significant barriers to their widespread practice. To address these challenges, this study utilizes the Xtreme Gradient Boost (XGBoost) algorithm, automated feature selection, automated hyper-parameter optimization, and NASA earth observations as a novel machine learning framework to predict daily reservoir levels, groundwater extraction rates, and out-of-district water requests for determining UWS performance. We examine the XGBoost water systems model (XGB-WSM) forecasting accuracy during dry, average, and wet climate scenarios compared with a water systems model developed to assess Salt Lake City's UWS. The XGB-WSM accurately models seasonal reservoir level dynamics, groundwater extraction rates, and out-of-district requests during the dry and average climate scenarios with a low RMSE and high R2 (>0.91). Wet climate conditions challenged the model; however, the seasonal trends and relationships to water system component thresholds mirrored the observed. We find that the combination of NASA earth observations and machine learning demonstrate high potential for further development and integration in water resources planning and management, such as identifying and optimizing system operations, increasing community engagement, and strengthening the understanding of the water system for utilities without an existing systems model.