Detection of Increases of De Facto Reuse Using Machine Learning

Machine learning was used to determine the percentages of de facto water reuse in Lake Mead, a drinking water source for millions of people. Wastewater effluent was mixed with lake water and a variety of water quality parameters were measured with online sensors to train and test the models.

Learning Objectives

Increases in stormwater runoff or wastewater effluent in drinking water intakes can introduce hazards to consumers if not properly treated. It can be useful to monitor the amount of de facto water reuse occurring at the intake of the drinking water treatment plant, in case corrective action is required. Therefore, this study demonstrates how online sensors could be paired with machine learning algorithms to determine the percentages of de facto water reuse from wastewater effluent and stormwater runoff, focusing on Lake Mead as an example.

Presenter(s)

Emily Clements
Southern Nevada Water Authority