Wastewaterga.png
FA info icon.svg Angle down icon.svg Source data
Type Paper
Year 2024
Location London, ON, Canada
Cite as Citation reference for the source document. Giorgio Antonini, Joshua M. Pearce, Franco Berruti, Domenico Santoro; A novel camera-based sensor for real-time wastewater quality monitoring. Water Practice and Technology 2024; wpt2024211. doi: https://doi.org/10.2166/wpt.2024.211 academia open access

Recent advancements have significantly improved turbidity and absorbance measurement techniques, crucial for municipal and industrial wastewater quality monitoring. This experimental system utilizes image analysis and machine learning on monochrome-camera images of real secondary wastewater effluent samples, irradiated with six LEDs, to classify turbidity and predict absorbance in the visible range. It focuses on low turbidity measurements (0–15 nephelometric turbidity units [NTUs]), the hardest challenge for conventional turbidity sensors. Specifically, this camera-based technique was able to classify within a 2 NTU class, 96 turbidity samples collected from a real wastewater treatment plant with precision and accuracy of over 96%. Additionally, it effectively predicted turbidity and absorbance with a neural network, achieving R-squared coefficients of 0.76 and 0.72, respectively. This innovative monitoring system, deployable in several locations of a wastewater treatment plant, not only addresses the limitations of the existing methods for the low turbidity range but also brings the potential for plant-wide process monitoring. Further testing is in progress to validate the proposed approach in other wastewater applications, such as combined sewer overflow monitoring and waste-activated sludge upset detection where more extreme and rapid changes are expected to occur.

Source code: https://osf.io/x5z2v/


Keywords[edit | edit source]

computer vision, monitoring, absorbance, camera-sensor, LEDs, machine learning, turbidity, wastewater monitoring

Wastewaterga.png

Highlights[edit | edit source]

  • Camera-based sensor to monitor and detect anomalies in wastewater treatment plant.
  • Machine learning methods applied to image analysis of low turbidity range.
  • Turbidity classified from 0 to 15 NTU with an interval size of 2 with accuracy >96%.
  • Absorbance in the visible range is simultaneously predicted.

See also[edit | edit source]

FA info icon.svg Angle down icon.svg Page data
Part of FAST Completed
Keywords computer vision, monitoring, absorbance, camera-sensor, leds, machine learning, turbidity, wastewater monitoring
SDG SDG06 Clean water and sanitation, SDG09 Industry innovation and infrastructure
Authors Giorgio Antonini;Joshua M. Pearce;Franco Berruti;Domenico Santoro
License CC-BY-SA-4.0
Organizations FAST, Western University
Language English (en)
Related 0 subpages, 22 pages link here
Impact 5 page views (more)
Created August 16, 2024 by Joshua M. Pearce
Last modified October 3, 2024 by Joshua M. Pearce
Cookies help us deliver our services. By using our services, you agree to our use of cookies.