Data-driven Modeling of Combined Sewer Systems for Urban Sustainability: An Empirical Evaluation

2024-08-21

arXiv.org

AI Summary

This study addresses the challenge of predicting combined sewer overflow (CSO) risk in large urban combined sewer systems (CSS) under climate change, particularly during extreme weather events and communication disruptions. Leveraging three years of high-resolution, real-world time-series monitoring data, we systematically evaluate the capacity of deep learning models—including LSTM, TCN, and Informer—to model dynamic hydraulic loads. A key innovation is the first systematic comparison of globally versus locally sensor-driven models under partial sensor failure scenarios, enabling a robustness evaluation framework. Results demonstrate that the proposed deep learning models achieve high-accuracy load forecasting (MAE < 0.08) under both nominal and communication-interrupted conditions, significantly outperforming conventional physics-based models. This validates their practical feasibility for enabling dynamic load redistribution and resilience-oriented control. The work delivers a deployable, data-driven predictive solution for urban water infrastructure management.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Neuro-Symbolic Learning
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Climate change poses complex challenges, with extreme weather events becoming increasingly frequent and difficult to model. Examples include the dynamics of Combined Sewer Systems (CSS). Overburdened CSS during heavy rainfall will overflow untreated wastewater into surface water bodies. Classical approaches to modeling the impact of extreme rainfall events rely on physical simulations, which are particularly challenging to create for large urban infrastructures. Deep Learning (DL) models offer a cost-effective alternative for modeling the complex dynamics of sewer systems. In this study, we present a comprehensive empirical evaluation of several state-of-the-art DL time series models for predicting sewer system dynamics in a large urban infrastructure, utilizing three years of measurement data. We especially investigate the potential of DL models to maintain predictive precision during network outages by comparing global models, which have access to all variables within the sewer system, and local models, which are limited to data from a restricted set of local sensors. Our findings demonstrate that DL models can accurately predict the dynamics of sewer system load, even under network outage conditions. These results suggest that DL models can effectively aid in balancing the load redistribution in CSS, thereby enhancing the sustainability and resilience of urban infrastructures.

Problem

• Modeling Combined Sewer Systems
• Predicting sewer system dynamics
• Enhancing urban infrastructure sustainability

Innovation

• Deep Learning time series models
• Global and local model comparison
• Sewer system load prediction