Intelligent multispectral vision system for non-contact water quality monitoring for wastewater

Simple item page
dc.contributor.authorPreitner, Karen
dc.contributor.authorBlanc, Sébastien
dc.contributor.authorHonzatko, David
dc.contributor.authorKündig, Clément
dc.contributor.authorPad, Pedram
dc.contributor.authorSaeedi, Sareh
dc.contributor.authorPeña-Haro, Salvador
dc.contributor.authorLechevallier, Pierre
dc.contributor.authorRieckermann, Jörg
dc.contributor.authorDunbar, L. Andrea
dc.date.accessioned2023-05-11T13:00:36Z
dc.date.available2023-05-11T13:00:36Z
dc.date.issued2023-02-02
dc.description.abstractWater quality monitoring in sewer networks remains a technical challenge even though water pollution and control are high priorities since decades. Current water quality monitoring usually analyzes samples in laboratories, allowing only sporadic measurements, or uses immersed sensors in the wastewater, leading to clogging and sensor fouling resulting in expense due to intensive maintenance. Both techniques thus have serious limitations. Previous research showed that UV-Vis reflectance spectrometry can be used for non-contact monitoring of turbidity (TUR) and Chemical Oxygen Demand (COD), which are two key water quality indicators. Although spectrometer achieve high spectral resolution their limited spatial field of view is roblematic for highly inhomogeneous surfaces as is the case wastewater In this study, we obtain beyond state-of-art measurement accuracies by combining machine learning techniques with increased spatial field-of-view Multi-Spectral Imaging (MSI) whilst substantially reducing the spectral resolution. We designed and built a dedicated setup with a monochromatic camera and an active illumination of thirteen LEDs covering the spectrum range of 200-700 nm. We acquired and calibrated data on 27 samples with different concentrations of TUR and COD. Machine learning regression models were trained and evaluated with the extracted spectra. We tested the Partial Least Square (PLS), Support Vector Machine (SVM) and Random Forest (RF). PLS regression performed best with excellent correlation coefficients (R2) of the 0.99 for TUR and 0.93 for COD. We obtained similar results with the SVM algorithm (R2 = 0.99 and 0.92), whilst RF had lower scores (R2 = 0.96 and 0.71).en_US
dc.identifier.citationProc. SPIE 12438-61, AI and Optical Data Sciences IV (2 February 2023)en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12839/1227
dc.language.isoenen_US
dc.subjectMulti-spectral imagingen_US
dc.subjectWater quality controlen_US
dc.subjectMachine learningen_US
dc.subjectWastewateren_US
dc.titleIntelligent multispectral vision system for non-contact water quality monitoring for wastewateren_US
dc.typeProceedings Articleen_US
dc.type.csemdivisionsBU-Men_US
dc.type.csemresearchareasData & AIen_US
dc.type.csemresearchareasIoT & Visionen_US
dc.type.csemresearchareasPhotonicsen_US
dc.type.csemresearchareasOtheren_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Intelligent multispectral vision system for contactless water quality monitoring for wastewater_finale_rev2.pdf
Size:
1.07 MB
Format:
Adobe Portable Document Format
Description:
Article
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.82 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Publications