That's Smart: Using Low-Cost Internet-of-Things Sensors to Characterize Water Quality in a City of Atlanta Combined Sewer

That's Smart: Using Low-Cost Internet-of-Things Sensors to Characterize Water Quality in a City of Atlanta Combined SewerAbstractAgencies often look for efficient and inexpensive ways to lower the risk of unauthorized discharges into their combined sewer system, specifically pertaining to water quality monitoring, and finding point sources of pollution. The City of Atlanta is addressing issues with identifying sources of specific pollutants (heavy metals and Total Dissolved Solids) in the stormwater runoff entering the City's combined sewer system. The traditional approach would be to deploy manual samplers at multiple sites, based on potential pollutant sources, such as proximity to an Interstate Highway or to an industrial site, to try to capture samples right after a rain event. Though automation exists allowing for collection of grab samples, often they may not be collected at the correct time and require significant logistics around frequent sample collection. This could lead to an unknown probability of success in understanding if and where there is truly a problem. The City of Atlanta is taking an innovative approach to identifying point sources of specific pollutants in stormwater runoff entering the City's sewers. The City and Stantec worked on a solution to preliminarily characterize the sites prior to a more expensive, and expansive deployment of samplers. This low-cost solution involved the utilization of Internet-of-Things sensors to capture Electrical Conductivity and Total Dissolved Solids water quality readings. These inexpensive sensors continuously capture water quality every 15 minutes. Their findings will help to deploy samplers only in areas that truly warrant further investigation. Sensor data was further analyzed by Stantec's Altitude Operational Services Platform to provide additional insights, including correlating the data with rain events. This presentation will share our multi-pronged approach to early identification, sensor logistics, system calibration, and how the technology behind the platform is helping to improve the combined sewer system 1.2 million people depend on daily. We will also share what's next in our machine learning journey — how predicting pollutant concentrations for future rain events will help us confirm point sources of pollution and learn how the system reacts during first flush rain events. Understanding this will ultimately help to better understand impacts to City systems. This is an excellent example of how our joint teams are using machine learning to find the right balance of smart sensors to build on the City's solution to stormwater, and effectively, wet weather water quality fluctuations.This paper was presented at the WEF Collection Systems and Stormwater Conference, April 9-12, 2024.SpeakerAbrera, JohnPresentation time09:30:0010:00:00Session time08:30:0010:00:00SessionInnovations in Stormwater Data Collection and ManagementSession number26Session locationConnecticut Convention Center, Hartford, ConnecticutTopicClimate Change Adaptation, Combined Sewer Overflow, Flooding, IDDE, Information Technology, Innovative Technology, Long Term Control Planning, Machine Learning, Sensors, Stormwater Management Design And Analysis, Water Quality, Wet WeatherTopicClimate Change Adaptation, Combined Sewer Overflow, Flooding, IDDE, Information Technology, Innovative Technology, Long Term Control Planning, Machine Learning, Sensors, Stormwater Management Design And Analysis, Water Quality, Wet WeatherAuthor(s)Askew, CorneliusAuthor(s)C. Askew1, J. Abrera2, C. GunnAuthor affiliation(s)City of Atlanta Department of Watershed Management 1, Stantec 2SourceProceedings of the Water Environment FederationDocument typeConference PaperPublisherWater Environment FederationPrint publication date Apr 2024DOI10.2175/193864718825159413Volume / Issue Content sourceCollection Systems and Stormwater ConferenceCopyright2024Word count18