EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A cooperative agent-based approach for influent–effluent nitrogen assessment in WWTPs

Míriam Timiraos, Antonio Díaz-Longueira, Manuel Rubiños, José-Luis Casteleiro-Roca, Elena Arce, José Luis Calvo-Rolle

Journal of Logic and Computation · 02.11.2026 · 36 (8)

DOI: 10.1093/logcom/exag058 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Logic and Computation, online erschienen am 13.11.2026. Verfasst von Míriam Timiraos und 5 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This work presents an enhanced cooperative intelligent agent for operational assessment in wastewater treatment plants (WWTPs). The proposed framework extends previous approaches through the incorporation of a new influent virtual sensor capable of estimating total nitrogen concentrations at the WWTP inlet using operational variables obtained from the treatment process. In addition, the architecture integrates the existing effluent virtual sensor and combines both predictions through a cooperative evaluation strategy. To improve operational interpretability, the system incorporates the operational nitrogen indicator together with the well-established nitrogen removal efficiency indicator, which is used as an additional operational metric to evaluate nitrogen removal performance between the influent and effluent stages. The integration of these indicators allows the intelligent agent to identify operational stress conditions, evaluate treatment efficiency and support adaptive decision-making processes. The proposed architecture combines data preprocessing, virtual sensing, operational evaluation and intelligent reasoning within a unified framework designed to improve WWTP monitoring and operational supervision. The experimental results demonstrate the effectiveness of the proposed cooperative approach. Among the evaluated machine learning techniques, the support vector machine achieved the best predictive performance, reaching an $R^{2}$ of 0.99987, an root mean square error of 0.20163 mg/L, an mean absolute error of 0.15331 mg/L and a symmetric mean absolute percentage error of 0.07426% during the validation stage. These results confirm the feasibility of the proposed framework for improving process assessment and supporting intelligent wastewater treatment management.

Zitieren

APA

Timiraos, M., Díaz-Longueira, A., Rubiños, M., Casteleiro-Roca, J., Arce, E., & Calvo-Rolle, J. L. (2026). A cooperative agent-based approach for influent–effluent nitrogen assessment in WWTPs. Journal of Logic and Computation, 36(8). https://doi.org/10.1093/logcom/exag058

Vancouver

Timiraos M, Díaz-Longueira A, Rubiños M, Casteleiro-Roca J, Arce E, Calvo-Rolle JL. A cooperative agent-based approach for influent–effluent nitrogen assessment in WWTPs. Journal of Logic and Computation. 2026;36(8). doi:10.1093/logcom/exag058

BibTeX
@article{Timiraos2026,
  author = {Timiraos, Míriam and Díaz-Longueira, Antonio and Rubiños, Manuel and Casteleiro-Roca, José-Luis and Arce, Elena and Calvo-Rolle, José Luis},
  title = {A cooperative agent-based approach for influent–effluent nitrogen assessment in WWTPs},
  journal = {Journal of Logic and Computation},
  year = {2026},
  volume = {36},
  number = {8},
  doi = {10.1093/logcom/exag058}
}
Kostenlos starten →