Ensemble-Based Machine Learning Approach For Improved Leak Detection in Water Mains

This paper presents an acoustic leak detection system for distribution water mains using machine learning methods. The problem is formulated as a binary classifier to identify leak and no-leak cases using acoustic signals.

The proposed solution includes a multi-strategy ensemble learning (MEL) using a gradient boosting tree (GBT) classification model, which has performed better in maximizing detection rate and minimizing false positives as compared with other classification models such as KNN, ANN, and rule-based techniques.


Complete the form below to download the whitepaper

By providing my personal information on this form, I consent to receiving updates, information regarding upcoming events and other marketing communications from Mueller Water Products and our related companies. Information regarding the types of personal information we collect, the purposes for which we use such information, how we disclose such information, and relevant retention periods is available in our Website Privacy Statement.