Predicting sewer structural condition using hybrid machine learning algorithms

IF 1.6 3区环境科学与生态学 Q3 WATER RESOURCES

Urban Water Journal Pub Date : 2023-08-09 DOI:10.1080/1573062X.2023.2217430

L. V. Nguyen, S. Razak

引用次数: 1

Abstract

ABSTRACT Predicting the structural condition of sewer pipes plays a vital role in the predictive maintenance of sewer pipes and renewal plans of many water utilities. This study explores the simultaneous utilization of physical and environmental features of sewer pipes in sewer structural condition prediction. Three (3) hybrid machine learning models which are the combination of Bagging (BG), Dagging (DG), and Rotation Forest (RotF) ensembles with a J48 Decision Tree (J48DT) based classifier were used to predict sewer pipe conditions in Ålesund city, Norway. The classification performance of the machine learning models was evaluated using the area under the receiver operating characteristic (AUC-ROC) and the area under the precision-recall (AUC-PRC) curves. The RotF-J48DT model had the highest (AUC-ROC = 0.857, AUC-PRC = 0.918) values, followed by the BG-J48DT, and the base classifier J48DT. The RotF-J48DT hybrid model should be considered when predicting the condition of sewer pipes in the study area.

查看原文本刊更多论文

利用混合机器学习算法预测下水道结构状况

摘要预测污水管道的结构状况在污水管道的预测性维护和许多供水设施的更新计划中起着至关重要的作用。本研究探讨了在下水道结构条件预测中同时利用下水道管道的物理和环境特征。将Bagging（BG）、Dagging（DG）和Rotation Forest（RotF）集成与基于J48决策树（J48DT）的分类器相结合的三（3）个混合机器学习模型用于预测挪威奥兰松德市的下水道状况。使用受试者操作特征下面积（AUC-ROC）和精确召回下面积（AUC-PRC）曲线评估机器学习模型的分类性能。RotF-J48DT模型的AUC-ROC = 0.857，AUC-PRC = 0.918）值，然后是BG-J48DT和基本分类器J48DT。在预测研究区域污水管道的状况时，应考虑RotF-J48DT混合模型。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Urban Water Journal WATER RESOURCES-

CiteScore

4.40

自引率

11.10%

发文量

101

审稿时长

3 months

期刊介绍： Urban Water Journal provides a forum for the research and professional communities dealing with water systems in the urban environment, directly contributing to the furtherance of sustainable development. Particular emphasis is placed on the analysis of interrelationships and interactions between the individual water systems, urban water bodies and the wider environment. The Journal encourages the adoption of an integrated approach, and system''s thinking to solve the numerous problems associated with sustainable urban water management. Urban Water Journal focuses on the water-related infrastructure in the city: namely potable water supply, treatment and distribution; wastewater collection, treatment and management, and environmental return; storm drainage and urban flood management. Specific topics of interest include: network design, optimisation, management, operation and rehabilitation; novel treatment processes for water and wastewater, resource recovery, treatment plant design and optimisation as well as treatment plants as part of the integrated urban water system; demand management and water efficiency, water recycling and source control; stormwater management, urban flood risk quantification and management; monitoring, utilisation and management of urban water bodies including groundwater; water-sensitive planning and design (including analysis of interactions of the urban water cycle with city planning and green infrastructure); resilience of the urban water system, long term scenarios to manage uncertainty, system stress testing; data needs, smart metering and sensors, advanced data analytics for knowledge discovery, quantification and management of uncertainty, smart technologies for urban water systems; decision-support and informatic tools;...