Application of ResNet and Autoencoder models for anomaly detection in wastewater networks data: A Comparative study of supervised and unsupervised approaches
I. Zidaoui , C. Wemmert , C. Joannis , S. Isel , J. Wertel , J. Vazquez
{"title":"Application of ResNet and Autoencoder models for anomaly detection in wastewater networks data: A Comparative study of supervised and unsupervised approaches","authors":"I. Zidaoui , C. Wemmert , C. Joannis , S. Isel , J. Wertel , J. Vazquez","doi":"10.1016/j.flowmeasinst.2025.102946","DOIUrl":null,"url":null,"abstract":"<div><div>Artificial intelligence (AI) enhances data validation for urban wastewater networks by addressing inaccuracies in sensor-generated data from harsh environments. Traditional manual validation methods are labor-intensive and prone to human error, necessitating automated solutions. The performance of two AI-driven models— a supervised ResNet model and an unsupervised Autoencoder—was compared on turbidity data issued from an urban wastewater network. The ResNet model showed improved accuracy when the classification threshold was optimized using the Precison-Recall curve but required rigorous data validation to manage learning bias and class imbalance. The Autoencoder achieved an F1 score of 0.96, demonstrating its efficacy in detecting anomalies when trained on valid data sequences. Hence, AI models significantly reduce the workload of manual data validation, enhance the reliability of water management systems, and allow stakeholders to focus on more critical tasks.</div></div>","PeriodicalId":50440,"journal":{"name":"Flow Measurement and Instrumentation","volume":"105 ","pages":"Article 102946"},"PeriodicalIF":2.3000,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Flow Measurement and Instrumentation","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0955598625001384","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, MECHANICAL","Score":null,"Total":0}
引用次数: 0
Abstract
Artificial intelligence (AI) enhances data validation for urban wastewater networks by addressing inaccuracies in sensor-generated data from harsh environments. Traditional manual validation methods are labor-intensive and prone to human error, necessitating automated solutions. The performance of two AI-driven models— a supervised ResNet model and an unsupervised Autoencoder—was compared on turbidity data issued from an urban wastewater network. The ResNet model showed improved accuracy when the classification threshold was optimized using the Precison-Recall curve but required rigorous data validation to manage learning bias and class imbalance. The Autoencoder achieved an F1 score of 0.96, demonstrating its efficacy in detecting anomalies when trained on valid data sequences. Hence, AI models significantly reduce the workload of manual data validation, enhance the reliability of water management systems, and allow stakeholders to focus on more critical tasks.
期刊介绍:
Flow Measurement and Instrumentation is dedicated to disseminating the latest research results on all aspects of flow measurement, in both closed conduits and open channels. The design of flow measurement systems involves a wide variety of multidisciplinary activities including modelling the flow sensor, the fluid flow and the sensor/fluid interactions through the use of computation techniques; the development of advanced transducer systems and their associated signal processing and the laboratory and field assessment of the overall system under ideal and disturbed conditions.
FMI is the essential forum for critical information exchange, and contributions are particularly encouraged in the following areas of interest:
Modelling: the application of mathematical and computational modelling to the interaction of fluid dynamics with flowmeters, including flowmeter behaviour, improved flowmeter design and installation problems. Application of CAD/CAE techniques to flowmeter modelling are eligible.
Design and development: the detailed design of the flowmeter head and/or signal processing aspects of novel flowmeters. Emphasis is given to papers identifying new sensor configurations, multisensor flow measurement systems, non-intrusive flow metering techniques and the application of microelectronic techniques in smart or intelligent systems.
Calibration techniques: including descriptions of new or existing calibration facilities and techniques, calibration data from different flowmeter types, and calibration intercomparison data from different laboratories.
Installation effect data: dealing with the effects of non-ideal flow conditions on flowmeters. Papers combining a theoretical understanding of flowmeter behaviour with experimental work are particularly welcome.