Application of Machine Learning Models for Water Pipeline Leakage Detection

Abstract

The applicability of machine learning models for detecting water pipeline leakage was evaluated in this study. The machine learning models, extreme gradient boosting (XGBoost), gradient boosting machine (GBM), LightGBM, categorical boosting (CatBoost), adaptive boosting (AdaBoost), and random forest (RF) models, which were developed using the open dataset of water pipeline leakage detection, were evaluated and compared based on classification performance using confusion matrix and performance indices. The results show that the latest boosting models, XGBoost, GBM, LightGBM, and CatBoost, yield superior classification performance compared to RF and AdaBoost models. Although the performance of the latest boosting models is similar, the LightGBM model (accuracy = 0.960, precision = 0.941, recall = 0.955, F1-score = 0.948, and specificity = 0.970) shows the best performance. Therefore, the latest boosting machine learning models can be used as effective predicting tools to develop big data-based water pipeline leakage detection systems and manage water pipeline leak risks.