EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Real-time quantification of activated sludge concentration and viscosity through deep learning of microscopic images

Hewen Li, Yu Tao, Tiefu Xu, Hongcheng Wang, Min Yang, Ying Chen, Aijie Wang

Environmental Science and Ecotechnology · 2025-03 · 24 · 100527

DOI: 10.1016/j.ese.2025.100527 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Science and Ecotechnology, 2025-03. Verfasst von Hewen Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Eco-Environment, Harbin Institute of Technology, Shenzhen, 518055, China. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Shenzhen Science and Technology Innovation Program, Science, Technology and Innovation Commission of Shenzhen Municipality, Shenzhen Key Laboratory Formation Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The parameters of activatedg sludge are crucial for the daily operation of wastewater treatment plants (WWTPs). In particular, mixed liquor suspended solids (MLSS) and apparent viscosity provide metrics for the biomass and rheological properties of activated sludge. Traditional methods for determining these parameters are time-consuming, require separate measurements for each index, and fail to provide real-time data for future 'smart' WWTPs. Here we show a real-time online microscopic image data analysis system that quantitatively identifies MLSS and apparent viscosity. Microscopic videos of activated sludge are captured in lab-scale sequencing batch reactors under chemical oxygen demand shock, yielding 41482 high-quality images. The Xception convolutional neural network architecture is used to establish both qualitative and quantitative correlations between these microscopic images and MLSS/apparent viscosity. The accuracies of qualitative identification for MLSS and apparent viscosity are both higher than 97%, and the quantitative correlation coefficients are 0.95 and 0.96, respectively. This quantitative correlation between microscopic images of activated sludge and its physical parameters, specifically MLSS and apparent viscosity, provides a basis for real-time online measurements of activated sludge parameters in WWTPs.

Schlagwörter

Stichwörter der Autor:innen

Activated sludgeDeep learningImageMLSSViscosity

Autor:innen und Institutionen

  • School of Eco-Environment, Harbin Institute of Technology, Shenzhen, 518055, China.
  • School of Civil Engineering, Heilongjiang University, Harbin, 150080, China.

Förderung

  • Shenzhen Science and Technology Innovation Program
  • Science, Technology and Innovation Commission of Shenzhen Municipality
  • Shenzhen Key Laboratory Formation Project
  • National Natural Science Foundation of China

Zitieren

APA

Li, H., Tao, Y., Xu, T., Wang, H., Yang, M., Chen, Y., & Wang, A. (2025). Real-time quantification of activated sludge concentration and viscosity through deep learning of microscopic images. Environmental Science and Ecotechnology, 24, 100527. https://doi.org/10.1016/j.ese.2025.100527

Vancouver

Li H, Tao Y, Xu T, Wang H, Yang M, Chen Y, et al. Real-time quantification of activated sludge concentration and viscosity through deep learning of microscopic images. Environmental Science and Ecotechnology. 2025;24:100527. doi:10.1016/j.ese.2025.100527

BibTeX
@article{Li2025,
  author = {Li, Hewen and Tao, Yu and Xu, Tiefu and Wang, Hongcheng and Yang, Min and Chen, Ying and Wang, Aijie},
  title = {Real-time quantification of activated sludge concentration and viscosity through deep learning of microscopic images},
  journal = {Environmental Science and Ecotechnology},
  year = {2025},
  volume = {24},
  pages = {100527},
  doi = {10.1016/j.ese.2025.100527}
}
Kostenlos starten →