Decision Making Model for Municipal Wastewater Conventional Secondary Treatment with Bayesian Networks

Journal article (2022)

Authors

Edgardo Medina Autonomous University of Mexico State, Toluca
Carlos Roberto Fonseca Autonomous University of Mexico State, Toluca
Iván Gallego-Alarcón Autonomous University of Mexico State, Toluca
O. Morales Napoles Hydraulic Structures and Flood Risk - CEG
Miguel A. Gómez-Albores Autonomous University of Mexico State, Toluca
Mario Esparza-Soto Autonomous University of Mexico State, Toluca
Carlos Alberto Mastachi-Loza Autonomous University of Mexico State, Toluca
Daury García-Pulido Autonomous University of Mexico State, Toluca
Research Group
Hydraulic Structures and Flood Risk (CEG) (TU Delft)
Copyright: © 2022 Edgardo Medina, Carlos Roberto Fonseca, Iván Gallego-Alarcón, O. Morales Napoles, Miguel Angel Gómez-Albores, Mario Esparza-Soto, Carlos Alberto Mastachi-Loza, Daury García-Pulido
DOI
help_outline
https://doi.org/10.3390/w14081231
Bayesian networks Structured expert judgment Decision making model Wastewater secondary treatment
More Info
expand_more

Published Date

2022

Language

English

Faculty

Civil Engineering & Geosciences

Department

Hydraulic Engineering

Research Group

Hydraulic Structures and Flood Risk

Abstract

Technical, economic, regulatory, environmental, and social and political interests make the process of selecting an appropriate wastewater treatment technology complex. Although this problem has already been addressed from the dimensioning approach, our proposal in this research, a model of decision making for conventional secondary treatment of municipal wastewater through continuous-discrete, non-parametric Bayesian networks was developed. The most suitable network was structured in unit processes, independent of each other. Validation, with data in a mostly Mexican context, provided a positive predictive power of 83.5%, an excellent kappa (0.77 > 0.75), and the criterion line was surpassed with the location of the model in a receiver operating characteristic (ROC) graph, so the model can be implemented in this region. The final configuration of the Bayesian network allows the methodology to be easily extended to other types of treatments, wastewater, and to other regions.