EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A novel approach for multivariate time series interval prediction of water quality at wastewater treatment plants

Siyu Liu, Zhaocai Wang iD, Yanyu Li

Water Science & Technology · 2024

DOI: 10.2166/wst.2024.371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Water Science & Technology, 2024. Verfasst von Siyu Liu und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Information, Shanghai Ocean University, Shanghai 201306, China. Hauptthemen laut MEDLINE: Water Quality, Wastewater, Waste Disposal, Fluid. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Humanities and Social Sciences Research Planning Fund Program, Ministry of Education, China, State Key Laboratory of Water Resources and Hydropower Engineering Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study proposes a novel approach for predicting variations in water quality at wastewater treatment plants (WWTPs), which is crucial for optimizing process management and pollution control. The model combines convolutional bi-directional gated recursive units (CBGRUs) with adaptive bandwidth kernel function density estimation (ABKDE) to address the challenge of multivariate time series interval prediction of WWTP water quality. Initially, wavelet transform (WT) was employed to smooth the water quality data, reducing noise and fluctuations. Linear correlation coefficient (CC) and non-linear mutual information (MI) techniques were then utilized to select input variables. The CBGRU model was applied to capture temporal correlations in the time series, integrating the Multiple Heads of Attention (MHA) mechanism to enhance the model's ability to comprehend complex relationships within the data. ABKDE was employed, supplemented by bootstrap to establish upper and lower bounds of the prediction intervals. Ablation experiments and comparative analyses with benchmark models confirmed the superior performance of the model in point prediction, interval prediction, the analysis of forecast period, and fluctuation detection for water quality data. Also, this study verifies the model's broad applicability and robustness to anomalous data. This study contributes significantly to improved effluent treatment efficiency and water quality control in WWTPs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Water QualityWastewaterWaste Disposal, FluidModels, TheoreticalMultivariate AnalysisTime FactorsWater Purification

Stichwörter der Autor:innen

adaptive bandwidth kernel function density estimationconvolutional bi-directional gated recurrent unitinterval predictionmulti-head attention mechanismwastewater treatment plant model

Substanzen

Wastewater

Autor:innen und Institutionen

  • College of Information, Shanghai Ocean University, Shanghai 201306, China.
  • College of Economics and Management, Shanghai Ocean University, Shanghai 201306, China E-mail: zcwang@shou.edu.cn.
  • College of Economics and Management, Shanghai Ocean University, Shanghai 201306, China.

ORCID-Profile: Zhaocai Wang

Förderung

  • Humanities and Social Sciences Research Planning Fund Program, Ministry of Education, China
  • State Key Laboratory of Water Resources and Hydropower Engineering Science

Zitieren

APA

Liu, S., Wang, Z., & Li, Y. (2024). A novel approach for multivariate time series interval prediction of water quality at wastewater treatment plants. Water Science & Technology. https://doi.org/10.2166/wst.2024.371

Vancouver

Liu S, Wang Z, Li Y. A novel approach for multivariate time series interval prediction of water quality at wastewater treatment plants. Water Science & Technology. 2024. doi:10.2166/wst.2024.371

BibTeX
@article{Liu2024,
  author = {Liu, Siyu and Wang, Zhaocai and Li, Yanyu},
  title = {A novel approach for multivariate time series interval prediction of water quality at wastewater treatment plants},
  journal = {Water Science & Technology},
  year = {2024},
  doi = {10.2166/wst.2024.371}
}
Kostenlos starten →