We describe the detection methods and the results of anomalous conditions in dikes (earthen dams/levees) based on a simultaneous processing of several data streams originating from sensors installed in these dikes. Applied methods are especially valuable in cases where lack of information or computational resources prohibit computing the state of the dike with finite element and other mathematical models. The data-driven methods are part of the artificial intelligence (AI) component of the ‘Urbanflood’ early warning system. This AI component includes pre-processing (e.g., gap filling and measurements synchronization procedures) of data streams, feature extraction and anomaly detection by one-side (also known as one-class) classification methods. Our approach has been successfully validated during a non-destructive piping experiment at the Zeeland dike (The Netherlands).
Article navigation
Research Article|
March 21 2014
Signal analysis and anomaly detection for flood early warning systems
A. L. Pyayt
;
1
Siemens, Corporate Technology, Volynskiy lane 3A, St Petersburg, 191186, Russia2
University of Amsterdam, Computational Science, Science Park 904, 1098 XH, Amsterdam, The Netherlands
E-mail: alexander.pyayt@gmail.com
Search for other works by this author on:
A. P. Kozionov
;
A. P. Kozionov
1
Siemens, Corporate Technology, Volynskiy lane 3A, St Petersburg, 191186, Russia3
St Petersburg State University of Aerospace Instrumentation, Bolshaya Morskaia 67, St Petersburg 190000, Russia
Search for other works by this author on:
V. T. Kusherbaeva
;
V. T. Kusherbaeva
1
Siemens, Corporate Technology, Volynskiy lane 3A, St Petersburg, 191186, Russia
Search for other works by this author on:
I. I. Mokhov
;
I. I. Mokhov
1
Siemens, Corporate Technology, Volynskiy lane 3A, St Petersburg, 191186, Russia
Search for other works by this author on:
V. V. Krzhizhanovskaya
;
V. V. Krzhizhanovskaya
2
University of Amsterdam, Computational Science, Science Park 904, 1098 XH, Amsterdam, The Netherlands5
National Research University ITMO, St Petersburg 197101, Russia7
St Petersburg State Polytechnic University, St Petersburg 195251, Russia
Search for other works by this author on:
B. J. Broekhuijsen
;
B. J. Broekhuijsen
4
Nederlandse Organisatie voor Toegepast Natuurwetenschappelijk Onderzoek (TNO), Eemsgolaan 3 NL-9727 DW, Groningen, The Netherlands
Search for other works by this author on:
R. J. Meijer
;
R. J. Meijer
2
University of Amsterdam, Computational Science, Science Park 904, 1098 XH, Amsterdam, The Netherlands4
Nederlandse Organisatie voor Toegepast Natuurwetenschappelijk Onderzoek (TNO), Eemsgolaan 3 NL-9727 DW, Groningen, The Netherlands
Search for other works by this author on:
P. M. A. Sloot
P. M. A. Sloot
2
University of Amsterdam, Computational Science, Science Park 904, 1098 XH, Amsterdam, The Netherlands5
National Research University ITMO, St Petersburg 197101, Russia6
Nanyang Technological University, Singapore 639798
Search for other works by this author on:
Journal of Hydroinformatics (2014) 16 (5): 1025-1043.
Article history
Received:
May 26 2013
Accepted:
December 29 2013
Citation
A. L. Pyayt, A. P. Kozionov, V. T. Kusherbaeva, I. I. Mokhov, V. V. Krzhizhanovskaya, B. J. Broekhuijsen, R. J. Meijer, P. M. A. Sloot; Signal analysis and anomaly detection for flood early warning systems. Journal of Hydroinformatics 1 September 2014; 16 (5): 1025–1043. doi: https://doi.org/10.2166/hydro.2014.067
Download citation file:
Close
Citation
A. L. Pyayt, A. P. Kozionov, V. T. Kusherbaeva, I. I. Mokhov, V. V. Krzhizhanovskaya, B. J. Broekhuijsen, R. J. Meijer, P. M. A. Sloot; Signal analysis and anomaly detection for flood early warning systems. Journal of Hydroinformatics 1 September 2014; 16 (5): 1025–1043. doi: https://doi.org/10.2166/hydro.2014.067
Download citation file:
Close