Machine Learning for Detecting Virus Infection Hotspots Via Wastewater-Based Epidemiology - The Case of SARS-CoV-2 RNA

Aug 4, 2026

Wastewater-based epidemiology (WBE) supports public health monitoring by detecting pathogens in wastewater, enabling low-cost tracking of infections that may be missed by conventional surveillance. This work addresses gaps at the intersection of hydraulic modeling and WBE, and the integration of machine learning with WBE for viral outbreak detection. A physically based hydraulic model is loosely coupled with machine learning to trace pathogen sources in sewer networks under varying conditions. Applied to a hypothetical SARS-CoV-2 case, hotspot recognition is promising but depends on high time-resolution sampling and sewer-specific properties such as flow velocity, sampling protocol, and boundary conditions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Key Points

Abstract

Plain Language Summary

1. Introduction

RESEARCH ARTICLE 10.1029/2023GH000866 Key Points: • Using a numerical model of wastewater network and machine learning has the potential for the early detection of viral outbreaks • The ability to recognize disease hotspots depends on sampling frequency and method • The use of sewer models can improve the usefulness of wastewater-based epidemiology data Supporting Information: Supporting Information may be found in the online version of this article. Correspondence to: Y. A. Abebe, [y.abebe@un-ihe.org](y.abebe@un-ihe.org) Citation: Zehnder, C., Béen, F., Vojinovic, Z., Savic, D., Torres, A. S., Mark, O., et al. (2023). Machine learning for detecting virus infection hotspots via wastewater-based epidemiology: The case of SARS-CoV-2 RNA. GeoHealth, 7, e2023GH000866. [https://doi](https://doi). org/10.1029/2023GH000866 Received 4 JUL 2023 Accepted 10 SEP 2023 Author Contributions: Conceptualization: Calvin Zehnder, Frederic Béen, Zoran Vojinovic, Dragan Savic, Arlex Sanchez Torres, Ole Mark Data curation: Calvin Zehnder, Frederic Béen Formal analysis: Calvin Zehnder Investigation: Calvin Zehnder Methodology: Calvin Zehnder, Frederic Béen, Zoran Vojinovic, Dragan Savic, Arlex Sanchez Torres, Ole Mark, Ljiljana Zlatanovic Software: Calvin Zehnder, Zoran Vojinovic, Ljiljana Zlatanovic © 2023 The Authors. GeoHealth published by Wiley Periodicals LLC on behalf of American Geophysical Union. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes. Machine Learning for Detecting Virus Infection Hotspots Via Wastewater-Based Epidemiology: The Case of SARS-CoV-2 RNA Calvin Zehnder1 , Frederic Béen2, Zoran Vojinovic1,3,4,5, Dragan Savic2,3,4 , Arlex Sanchez Torres1, Ole Mark6 , Ljiljana Zlatanovic7,8, and Yared Abayneh Abebe1,9 1Water Supply, Sanitation and Environmental Engineering Department, IHE Delft Institute for Water Education, Delft, The Netherlands, 2KWR Water Research Institute, Nieuwegein, The Netherlands, 3Centre for Water Systems, College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, UK, 4Faculty of Civil Engineering, University of Belgrade, Belgrade, Serbia, 5National Cheng Kung University, Tainan, Taiwan, 6Krüger Veolia, Søborg, Denmark, 7Sanitary Engineering, Delft University of Technology, Delft, The Netherlands, 8PWN, Velserbroek, The Netherlands, 9Department of Hydraulic Engineering, Faculty of Civil Engineering and Geosciences, Delft University of Technology, Delft, The Netherlands Abstract Wastewater-based epidemiology (WBE) has been proven to be a useful tool in monitoring public health-related issues such as drug use, and disease. By sampling wastewater and applying WBE methods, wastewater-detectable pathogens such as viruses can be cheaply and effectively monitored, tracking people who might be missed or under-represented in traditional disease surveillance. There is a gap in current knowledge in combining hydraulic modeling with WBE. Recent literature has also identified a gap in combining machine learning with WBE for the detection of viral outbreaks. In this study, we loosely coupled a physically-based hydraulic model of pathogen introduction and transport with a machine learning model to track and trace the source of a pathogen within a sewer network and to evaluate its usefulness under various conditions. The methodology developed was applied to a hypothetical sewer network for the rapid detection of disease hotspots of the disease caused by the SARS-CoV-2 virus. Results showed that the machine learning model's ability to recognize hotspots is promising, but requires a high time-resolution of monitoring data and is highly sensitive to the sewer system's physical layout and properties such as flow velocity, the pathogen sampling pro

FAQs

How does the study detect viral infection hotspots using wastewater-based epidemiology?

It couples a physically based hydraulic model of pathogen introduction and transport with a machine learning model that tracks and evaluates hotspot areas within a sewer network, using monitored wastewater signals.

What factors most affect the machine learning model’s hotspot recognition performance?

Hotspot identification is sensitive to monitoring time resolution and to sewer system physical layout and properties, including flow velocity, the pathogen sampling procedure, and model boundary conditions.

What does the proposed methodology enable beyond outbreak detection?

It suggests rapid back-tracing of human-excreted biomarkers using sampling at outlets or other key points, though it would require high-frequency, contaminant-specific sensor systems not currently available.

Aug 4, 2026

Upload by Genevieve