Keywords
causal inference
leakage detection
Abstract
Urban water distribution systems are monitored through multivariate time series from flow meters, pressure sensors, chlorine concentration, turbidity, pump status, valve position, reservoir level, and district metering areas. Abnormal events such as leakage, contamination, pump malfunction, and valve misoperation often produce delayed and spatially propagated effects across connected pipeline zones. This study proposes an intervention-based variable attribution method for leakage and contamination detection in water distribution time series. The method combines hydraulic topology constraints with causal discovery to learn directed dependencies among pressure, flow, quality, and pump-control variables. An intervention-based residual module estimates how the system would behave if a suspected abnormal variable were held at its expected causal value. Fine-grained anomaly attribution is then performed by ranking variables according to their intervention effect on downstream deviations. Experiments are conducted on a municipal water network dataset containing 1,480 pressure sensors, 620 flow meters, 210 water-quality stations, 96 pump units, and 44 monitoring variables collected at 5-minute intervals over 16 months. The dataset contains 184 million timestamped measurements and 1,320 verified abnormal events, including pipe leakage, valve-control failure, chlorine decay anomaly, turbidity spike, pump cycling instability, and reservoir-level deviation. The proposed method reduces median event localization delay from 4.2 hours to 58 minutes compared with a graph autoencoder baseline. The average spatial localization error decreases from 3.8 pipeline zones to 1.4 zones. False alerts are limited to 2.2 cases per district metering area per month. The top-ranked causal zone matches maintenance records in 1,018 events. These findings indicate that causal variable attribution can improve fine-grained detection and localization of abnormal events in water distribution systems.
References
1. Liang, R., Ye, Z., Liang, Y., & Li, S. (2025). Deep Learning-Based Player Behavior Modeling and Game Interaction System Optimization Research.
2. Farah, E., & Shahrour, I. (2024). Water leak detection: a comprehensive review of methods, challenges, and future directions. Water, 16(20), 2975.
3. Wu, C., & Chen, H. (2025). Research on system service convergence architecture for AR/VR system.
4. Palma, L., Hatam, F., Di Nardo, A., & Prévost, M. (2024). Contaminations in water distribution systems: A critical review of detection and response methods. AQUA—Water Infrastructure, Ecosystems and Society, 73(6), 1285-1302.
5. Chen, X., Xiao, H., Zeng, Z., Zhang, S., & Xiao, R. (2025). Fine-Grained Multivariate Time Series Anomaly Detection via Causal Inference. Knowledge-Based Systems, 114765.
6. Jiao, Y., Wang, A., Zhao, B., & Shi, T. (2026). The Impact of Visual Language Strategies in Public Art Creation on Community Spatial Perception and Public Behavior.
7. Joseph, K., Shetty, J., Patnaik, R., Matthew, N. S., Van Staden, R., Liyanage, W. P., ... & Sharma, A. K. (2025). Early leak and burst detection in water pipeline networks using machine learning approaches. Water, 17(14), 2164.
8. Yin, J., Rao, H., & Huang, Y. (2026, March). Dynamic Modeling and Heterogeneity Analysis of Platform User Behavior Time Series. In 2026 International Conference on AI in Education Technology and Applications (AIETA) (pp. 30-33). IEEE.
9. Gui, H., Wang, B., Lu, Y., & Fu, Y. (2025). Computational Modeling-Based Estimation of Residual Stress and Fatigue Life of Medical Welded Structures.
10. Werbinska-Wojciechowska, S., & Rogowski, R. (2025). Proactive Maintenance of Pump Systems Operating in the Mining Industry—A Systematic Review. Sensors, 25(8), 2365.
11. Chen, F., Liang, H., Li, S., Yue, L., & Xu, P. (2025). Design of Domestic Chip Scheduling Architecture for Smart Grid Based on Edge Collaboration.
12. Yang, J. (2026). Stage‐Coupled Computational Framework for Stratified Accessibility and Equity Analysis in Community‐Based Elderly Care Services.
13. Rodríguez, M., Tobón, D. P., & Múnera, D. (2025). A framework for anomaly classification in Industrial Internet of Things systems. Internet of Things, 29, 101446.
14. Zhang, Z. (2026). A Study on Return Optimization in E-commerce for Complex Consumer Goods Driven by Installation Information Quality. Available at SSRN 6734720.
15. Xu, T., Zhang, J., & Zhu, W. (2026). Reproducible Modeling Pipelines and Cross-Window Stability in Subprime Auto Loan Credit Risk Assessment. Available at SSRN 6893861.
16. Rajalakshmi, M., & Velmurugan, T. (2026). Physics-guided contrastive temporal graph learning for anomaly detection and root-cause localization in industrial control systems. Scientific Reports.
17. Shakeri, R., Amini, H., Fakheri, F., Lam, M. Y., & Zahraie, B. (2025). Comparative analysis of correlation and causality inference in water quality problems with emphasis on TDS Karkheh River in Iran. Scientific Reports, 15(1), 2798.
18. Zhou, Y., & Jia, R. (2025). Research on Driving Behavior Risk Identification and Safety Assessment Methods Based on Artificial Intelligence. Artificial Intelligence and Machine Learning Review, 6(2), 1-15.
19. Pei, Z., Huang, Q., & Wang, S. (2026). When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning. arXiv preprint arXiv:2606.29354.
20. Ajenifuja, G. R. (2022). Comparative Study of Non-Destructive Testing Methods for Failure Detection in High-Pressure Industrial Equipment. Journal of Industrial Safety Engineering, 14(3), 112-125.
21. Zhang, Z., Tong, Y., & Gao, Y. (2026). Retrieval-Augmented Generation with Low-Latency Deployment for Vertical Domains Question Answering: A Case Study on Economic Resource Platforms.
22. Qi, C., & Qiao, X. (2026). Using AI to Monitor AI: Automated Operations Through Log-Driven Intelligence. Available at SSRN 6795840.
23. Rajalakshmi, M., & Velmurugan, T. (2026). Physics-guided contrastive temporal graph learning for anomaly detection and root-cause localization in industrial control systems. Scientific Reports.
24. Su, D., & Dong, Y. (2026). Classroom-Based Assessment with Bayesian Learning Analytics for Instructional Decision-Making in ASD Inclusive Education.
25. Santos‐Fernandez, E., Ver Hoef, J. M., Peterson, E. E., McGree, J., Villa, C. A., Leigh, C., ... & Mengersen, K. (2024). Unsupervised anomaly detection in spatio‐temporal stream network sensor data. Water Resources Research, 60(11), e2023WR035707.
26. Ma, Y. (2026). Industrial Financial Risk Prediction Model Based on Graph Neural Network and Knowledge Graph Inference. Journal of Circuits, Systems and Computers, 35(16), 2650103.
27. Namdeo, A. (2024). Causal AI for root cause detection in cloud process pipelines. International Journal of Research and Applied Innovations, 7(3), 10774-10785.
28. Gao, G., Gao, R., Lu, C., Gao, R., & Kuang, Y. (2026, March). Security Governance Methods and Quantitative Evaluation for Enterprise SMS and Verification Code Systems. In 2026 International Conference on Generative Artificial Intelligence and Information Security (GAIIS) (pp. 455-458). IEEE.
29. Razaq, A. (2025). Reducing False and Improving Response Time in High-Occupancy Buildings: A Quantitative Study of NFPA 72-Complaint Cause-and-Effect Testing Outcomes. American Journal of Scholarly Research and Innovation, 4(01), 856-893.
30. Li, Y., & Liu, S. (2026, May). A Study on Dynamic Optimization of Alerting Policies and Multi-Agent Decision-Making Mechanisms in Cloud Environments. In 2026 7th International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) (pp. 703-706). IEEE.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright (c) 2026 Julien Moreau, Claire Dubois (Author)