Machine Learning Models for Reinforced Concrete Pipes Condition Prediction: The State-of-the-Art Using Artificial Neural Networks and Multiple Linear Regression in a Wisconsin Case Study

TL;DR

This study compares artificial neural networks and multiple linear regression models to predict the condition of sewer pipelines, demonstrating that ANNs provide higher accuracy while MLR offers better interpretability, aiding infrastructure management.

Contribution

It introduces a machine learning approach combining ANNs and MLR for sewer pipe condition prediction, highlighting their respective advantages and suggesting hybrid models for future improvements.

Findings

ANNs achieved an R2 of 0.9066, outperforming MLR's 0.8474.

Key predictors include pipe length, age, and diameter.

MLR identified significant predictors with better interpretability.

Abstract

The aging sewer infrastructure in the U.S., covering 2.1 million kilometers, encounters increasing structural issues, resulting in around 75,000 yearly sanitary sewer overflows that present serious economic, environmental, and public health hazards. Conventional inspection techniques and deterministic models do not account for the unpredictable nature of sewer decline, whereas probabilistic methods depend on extensive historical data, which is frequently lacking or incomplete. This research intends to enhance predictive accuracy for the condition of sewer pipelines through machine learning models artificial neural networks (ANNs) and multiple linear regression (MLR) by integrating factors such as pipe age, material, diameter, environmental influences, and PACP ratings. ANNs utilized ReLU activation functions and Adam optimization, whereas MLR applied regularization to address multicollinearity, with both models assessed through metrics like RMSE, MAE, and R2. The findings indicated that ANNs surpassed MLR, attaining an R2 of 0.9066 compared to MLRs 0.8474, successfully modeling nonlinear relationships while preserving generalization. MLR, on the other hand, offered enhanced interpretability by pinpointing significant predictors such as residual buildup. As a result, pipeline degradation is driven by pipe length, age, and pipe diameter as key predictors, while depth, soil type, and segment show minimal influence in this analysis. Future studies ought to prioritize hybrid models that merge the accuracy of ANNs with the interpretability of MLR, incorporating advanced methods such as SHAP analysis and transfer learning to improve scalability in managing infrastructure and promoting environmental sustainability.