Sewer Condition Prediction and Analysis of Explanatory Factors

A machine learning approach for predicting and localizing the failure and damage point in sewer networks due to pipe properties

As a basic infrastructure, sewers play an important role in the innards of every city and town to remove unsanitary water from all kinds of livable and functional spaces. Sewer pipe failures (SPFs) are unwanted and unsafe in many ways, as the disturbance that they cause is undeniable. Sewer pipes meet manholes frequently, unlike water distribution systems, as in sewers, water movement is due to gravity and manholes are needed in every intersection as well as through pipe length. Many studies have been focused on sewer pipe failures and so on, but few investigations have been done to show the effect of manhole proximity on pipe failure. Predicting and localizing the sewer pipe failures is affected by different parameters of sewer pipe properties, such as material, age, slope, and depth of the sewer pipes. This study investigates the applicability of a support vector machine (SVM), a supervised machine learning (ML) algorithm, for the development of a prediction model to predict sewer pipe failures and the effects of manhole proximity. The results show that SVM with an accuracy of 84% can properly approximate the manhole effects on sewer pipe failures.

Machine Learning Models for Slope Stability Classification of Circular Mode Failure: An Updated Database and Automated Machine Learning (AutoML) Approach

Slope failures lead to large casualties and catastrophic societal and economic consequences, thus potentially threatening access to sustainable development. Slope stability assessment, offering potential long-term benefits for sustainable development, remains a challenge for the practitioner and researcher. In this study, for the first time, an automated machine learning (AutoML) approach was proposed for model development and slope stability assessments of circular mode failure. An updated database with 627 cases consisting of the unit weight, cohesion, and friction angle of the slope materials; slope angle and height; pore pressure ratio; and corresponding stability status has been established. The stacked ensemble of the best 1000 models was automatically selected as the top model from 8208 trained models using the H2O-AutoML platform, which requires little expert knowledge or manual tuning. The top-performing model outperformed the traditional manually tuned and metaheuristic-optimized models, with an area under the receiver operating characteristic curve (AUC) of 0.970 and accuracy (ACC) of 0.904 based on the testing dataset and achieving a maximum lift of 2.1. The results clearly indicate that AutoML can provide an effective automated solution for machine learning (ML) model development and slope stability classification of circular mode failure based on extensive combinations of algorithm selection and hyperparameter tuning (CASHs), thereby reducing human efforts in model development. The proposed AutoML approach has the potential for short-term severity mitigation of geohazard and achieving long-term sustainable development goals.

Development and Comparison of Prediction Models for Sanitary Sewer Pipes Condition Assessment Using Multinomial Logistic Regression and Artificial Neural Network

Sanitary sewer pipes infrastructure system being in good condition is essential for providing safe conveyance of the wastewater from homes, businesses, and industries to the wastewater treatment plants. For sanitary sewer pipes to deliver the wastewater to the treatment plants, they must be in good condition. Most of the water utilities have aged sanitary sewer pipes. Water utilities inspect sewer pipes to decide which segments of the sanitary sewer pipes need rehabilitation or replacement. The process of inspecting the sewer pipes is described as condition assessment. This condition assessment process is costly and necessitates developing a model that predicts the condition rating of sanitary sewer pipes. The objective of this study is to develop Multinomial Logistic Regression (MLR) and Artificial Neural Network (ANN) models to predict sanitary sewer pipes condition rating using inspection and condition assessment data. MLR and ANN models are developed from the City of Dallas’s data. The MLR model is built using 80% of randomly selected data and validated using the remaining 20% of data. The ANN model is trained, validated, and tested. The significant physical factors influencing sanitary pipes condition rating include diameter, age, pipe material, and length. Soil type is the environmental factor that influences sanitary sewer pipes condition rating. The accuracy of the performance of the MLR and ANN is found to be 75% and 85%, respectively. This study contributes to the body of knowledge by developing models to predict sanitary sewer pipes condition rating that enables policymakers and sanitary sewer utilities managers to prioritize the sanitary sewer pipes to be rehabilitated and/or replaced.

A Two-Stage Data-Driven Spatiotemporal Analysis to Predict Failure Risk of Urban Sewer Systems Leveraging Machine Learning Algorithms

Risk-informed asset management is key to maintaining optimal performance and efficiency of urban sewer systems. Although sewer system failures are spatiotemporal in nature, previous studies analyzed failure risk from a unidimensional aspect (either spatial or temporal), not accounting for bidimensional spatiotemporal complexities. This is owing to the insufficiency of good-quality data, which ultimately leads to under-/overestimation of failure risk. Here, we propose a generalized methodology/framework to facilitate a robust spatiotemporal analysis of urban sewer system failure risk, overcoming the intrinsic challenges of data imperfections-e.g., missing data, outliers, and imbalanced information. The framework includes a two-stage data-driven modeling technique that efficiently models the highly right-skewed sewer system failure data to predict the failure risk, leveraging a bidimensional space-time approach. We implemented our analysis for Bogotá, the capital city of Colombia. We train, test, and validate a battery of machine learning algorithms-logistic regression, decision trees, random forests, and XGBoost-and select the best model in terms of goodness-of-fit and predictive accuracy. Finally, we illustrate the applicability of the framework in planning/scheduling sewer system maintenance operations using state-of-the-art optimization techniques. Our proposed framework can help stakeholders to analyze the failure-risk models' performance under different discrimination thresholds, and provide managerial insights on the model's adequate spatial resolution and appropriateness of decentralized management for sewer system maintenance.

Wastewater collection system failures in a capital city: analysis and sustainable prevention

An analysis of failures in a capital city's wastewater collection system was carried out and recommendations were made for sustainable preventive measures based on a risk of failure assessment. Most failures in sewer lines were associated with blockage caused by sediment accumulation and clogging from fats, oils and/or grease dumped by restaurants along several streets, combined with poor or nonexistent maintenance of the lines. Sewer lines in streets with higher risk levels due to multiple food establishments along those streets experienced most of the failures. Sustainability of the proposed maintenance was evidenced since it reduces costs and exposure to harmful substances and hazardous conditions as well as minimizing environmental impacts.

Comparison of Statistical and Machine Learning Models for Pipe Failure Modeling in Water Distribution Networks

The application of statistical and Machine Learning models plays a critical role in planning and decision support processes for efficient and reliable Water Distribution Network (WDN) management. Failure models can provide valuable information for prioritizing system rehabilitation even in data scarcity scenarios, such as developing countries. Few studies have analyzed the performance of more than two models, and examples of case studies in developing countries are insufficient. This study compares various statistical and Machine Learning models to provide useful information to practitioners for the selection of a suitable pipe failure model according to information availability and network characteristics. Three statistical models (i.e., Linear, Poisson, and Evolutionary Polynomial Regressions) were used for failure prediction in groups of pipes. Machine Learning approaches, particularly Gradient-Boosted Tree (GBT), Bayes, Support Vector Machines and Artificial Neuronal Networks (ANNs), were compared in predicting individual pipe failure rates. The proposed approach was applied to a WDN in Bogotá (Colombia). The statistical models showed an acceptable performance (R2 between 0.695 and 0.927), but the Poisson Regression was the most suitable for predicting failures in pipes with lower failure rates. Regarding Machine Learning models, Bayes and ANNs exhibited low performance in the prediction of pipe failure condition. The GBT approach had the best performing classifier.

Sewer Life Span Prediction: Comparison of Methods and Assessment of the Sample Impact on the Results

Survival models can support the estimation of the resources needed for future renovations of sewer systems. They are particularly useful, when a large share of network will need renovation. This paper studies modelling sewer deterioration in a context, where data are available for pipes selected for inspections due to suspected or experienced poor condition. We compare the random survival forest and the Weibull regression for modelling survival and find that both methods yield similar results, but the random survival forest performs slightly better. We propose a method for estimating the range in which the actual network survival curve lies. We conclude that in order to reach reliable results, a life span model needs to be constructed based on a random sample of pipes, which are then consecutively inspected and in addition, censoring and left truncation need to be accounted for. The inspection data applied in this paper had been collected with the aim of finding pipes in poor condition in the network. As a result, the data were biased towards poor condition and unrepresentative in terms of pipe ages.

A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources

Random forests (RF) is a supervised machine learning algorithm, which has recently started to gain prominence in water resources applications. However, existing applications are generally restricted to the implementation of Breiman’s original algorithm for regression and classification problems, while numerous developments could be also useful in solving diverse practical problems in the water sector. Here we popularize RF and their variants for the practicing water scientist, and discuss related concepts and techniques, which have received less attention from the water science and hydrologic communities. In doing so, we review RF applications in water resources, highlight the potential of the original algorithm and its variants, and assess the degree of RF exploitation in a diverse range of applications. Relevant implementations of random forests, as well as related concepts and techniques in the R programming language, are also covered.