Automated Detection of Anomalies in High-Frequency Water Quality Sensor Data using Deep Learning

Section 1: Publication

Publication Type

Authorship

Wang, X

Title

Automated Detection of Anomalies in High-Frequency Water Quality Sensor Data using Deep Learning

Year

2019

Publication Outlet

DOI

http://hdl.handle.net/11375/24680

ISBN

ISSN

Citation

Wang, X (2019). Automated Detection of Anomalies in High-Frequency Water Quality Sensor Data using Deep Learning http://hdl.handle.net/11375/24680

Abstract

Wastewater treatment facilities are increasingly installing sensors to monitor water quality. As these datasets have increased in size and complexity, it has become difficult to identify abnormal readings in a timely manner either manually or using simple rules that might have been sufficient previously. Two ammonia sensors were installed at the Dundas Wastewater Treatment Plant in November 2017. The collected ammonia concentration data shows a daily pattern. A learning-based method is implemented in this thesis to identify any readings which violate this daily pattern. The data points which were predicted to be anomalous were qualitatively ranked based on the severity and the likelihood of being faulty. The result of the learning-based method was evaluated and compared to other traditional detection methods.

Plain Language Summary

Section 2: Additional Information

Program Affiliations

GWF: Global Water Futures

Project Affiliations

GWF-SSSWQM: Sensors and Sensing Systems for Water Quality Monitoring

Submitters

Name	Role	Email	Institution

Publication Stage

Theme

Presentation Format

Additional Information

Masters, McMaster University, Sensors