Combining Data-driven Methods with Finite Element Analysis for Flood Early Warning Systems

We developed a robust approach for real-time levee condition monitoring based on combination of data-driven methods (one-side classification) and finite element analysis. It was implemented within a flood early warning system and validated on a series of full-scale levee failure experiments organised by the IJkdijk consortium in August-September 2012 in the Netherlands. Our approach has detected anomalies and predicted levee failures several days before the actual collapse. This approach was used in the UrbanFlood decision support system for routine levee quality assessment and for critical situations of a potential levee breach and inundation. In case of emergency, the system generates an alarm, warns dike managers and city authorities, and launches advanced urgent simulations of levee stability and flood dynamics, thus helping to make informed decisions on preventive measures, to evaluate the risks and to alleviate adverse effects of a flood.

[1]  Bartosz Balis,et al.  Flood early warning system: design, implementation and computational modules , 2011, ICCS.

[2]  Peter M. A. Sloot,et al.  Time-Frequency Methods for Structural Health Monitoring , 2014, Sensors.

[3]  G.,et al.  Full-scale field validation of innovative dike monitoring systems , 2013 .

[4]  Peter M. A. Sloot,et al.  Modeling earthen dikes using real-time sensor data , 2013 .

[5]  Peter M. A. Sloot,et al.  Distributed Simulation of City Inundation by Coupled Surface and Subsurface Porous Flow for Urban Flood Decision Support System , 2013, ICCS.

[6]  Valeria V. Krzhizhanovskaya,et al.  Numerical prediction of the IJkDijk trial embankment failure , 2015 .

[7]  Gordon Ng,et al.  Levee Monitoring System Better Management through Better Information , 2010 .

[8]  T. Poppe,et al.  Neural clouds for monitoring of complex systems , 2008, Optical Memory and Neural Networks.

[9]  J. D. Simm,et al.  The significance of failure modes in the design and management of levees - a perspective from the International Levee Handbook team , 2012 .

[10]  Valeria V. Krzhizhanovskaya,et al.  Signal analysis and anomaly detection for flood early warning systems , 2014 .

[11]  Adam Bezuijen,et al.  Full-scale testing of piping prevention measures: three tests at the Ijkdijk , 2014 .

[12]  J. Pastor,et al.  Finite element method and limit analysis theory for soil mechanics problems , 1980 .

[13]  Peter M. A. Sloot,et al.  An Approach for Real-Time Levee Health Monitoring Using Signal Processing Methods , 2013, ICCS.

[14]  M. Velasco,et al.  Methodology for risk assessment of flash flood events due to climate and land-use changes: application to the Llobregat basin , 2014 .

[15]  S. Van Baars,et al.  The Causes and Mechanisms of Historical Dike Failures in the Netherlands , 2009 .