A hybrid dynamic graph neural network framework for real-time anomaly detection

• Published in: Journal of hydroinformatics Vol. 26; no. 12; pp. 3172 - 3191
• Main Authors: Moraitis, Georgios, Makropoulos, Christos
• Format: Journal Article
• Language: English
• Published: London IWA Publishing 01.12.2024
• Subjects: Accuracy; Alarm behavior; Anomalies; Behavior; Comparative analysis; Connectivity; Data transmission; Deep learning; False alarms; Fault detection; Fault minimization; Graph neural networks; Graph representations; Graph theory; Multivariate analysis; Neural networks; Real time operation; Rivers; Robustness; Sensors; Spatiotemporal data; Water; Water distribution; Water distribution systems; Water engineering
• ISSN: 1464-7141; 1465-1734
• DOI: 10.2166/hydro.2024.164

The timely and robust detection of anomalies is essential for resilient and secure operations of critical water infrastructures against operational faults or malicious actions. However, real-world systems exhibit diverse and evolving spatiotemporal relationships among their components, posing an int...