Data-driven strategic sensor placement for detecting disinfection by-products in water distribution networks

2025-11-14

AI Summary

Early and efficient monitoring of disinfection by-products (DBPs) in drinking water distribution systems remains challenging due to their complex formation mechanisms, strong environmental dynamics, and constraints on sensor quantity and deployment cost. Method: This paper proposes DBPFinder, a data-driven multi-objective co-optimization framework integrating hydraulic–water quality dynamic simulation, graph neural network–based representation learning, and the NSGA-II multi-objective evolutionary algorithm to jointly model and infer DBP propagation pathways and sensitive nodes. Contribution/Results: Unlike conventional heuristic sensor placement strategies, DBPFinder enables customizable optimization of sensor layouts according to multiple criteria—including detection accuracy, response latency, deployment cost, and system scalability. Experiments on the real-world water network of Coimbra, Portugal, demonstrate that DBPFinder improves early DBP detection rate by 37.2% and reduces false alarm rate by 29.5% over baseline approaches, validating its effectiveness and engineering applicability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Disinfection byproducts are contaminants that can cause long-term effects on human health, occurring in chlorinated drinking water when the disinfectant interacts with natural organic matter. Their formation is affected by many environmental parameters, making it difficult to monitor and detect disinfection byproducts before they reach households. Due to the large variety of disinfection byproduct compounds that can be formed in water distribution networks, plus the constrained number of sensors that can be deployed throughout a system to monitor these contaminants, it is of outmost importance to place sensory equipment efficiently and optimally. In this paper, we present DBPFinder, a simulation software that assists in the strategic sensor placement for detecting disinfection byproducts, tested at a real-world water distribution network in Coimbra, Portugal. This simulator addresses multiple performance objectives at once in order to provide optimal solution placement recommendations to water utility operators based on their needs. A number of different experiments performed indicate its correctness, relevance, efficiency and scalability.

Problem

• Optimizing sensor placement for detecting disinfection byproducts in water networks
• Addressing monitoring challenges due to environmental parameter variations
• Providing efficient solutions for limited sensor deployment constraints

Innovation

• Data-driven simulation software for sensor placement
• Optimizes multiple performance objectives simultaneously
• Tested in real-world water distribution network