Data-driven modelling for flood defence structure analysis

Abstract

Data-driven modelling for flood defence structure analysisPyayt, A.; Mokhov, I.I.; Kozionov, A.P.; Kusherbaeva, V.T.; Lang, B.; Krzhizhanovskaya, V.; Meijer, R.J. General rightsIt is not permitted to download or to forward/distribute the text or part of it without the consent of the author(s) and/or copyright holder(s), other than for strictly personal, individual use, unless the work is under an open content license (like Creative Commons). Disclaimer/Complaints regulationsIf you believe that digital publication of certain material infringes any of your rights or (privacy) interests, please let the Library know, stating your reasons. In case of a legitimate complaint, the Library will make the material inaccessible and/or remove it from the website. Please Ask the Library: http://uba.uva.nl/en/contact, or a letter to: Library of the University of Amsterdam, Secretariat, Singel 425, 1012 WP Amsterdam, The Netherlands. You will be contacted as soon as possible. Download date: 10 May 2018 301Comprehensive Flood Risk Management -Klijn & Schweckendiek (eds) © 2013 Taylor & Francis Group, London, ISBN 978-0-415-62144-1 Data-driven modelling for flood defence structure analysis ABSTRACT: We present a data-driven modelling approach for detection of anomalies in flood defences (levees, dykes, dams, embankments) equipped with sensors. An auto-regressive linear model and feed-forward neural network were applied for modelling a transfer function between the sensors. This approach has been validated on a dike in Boston, UK-one of the pilot sites of the UrbanFlood projectthat showed both normal and abnormal sensor behaviour. Comparison of the linear and non-linear models is presented. The suggested model-based anomaly detection approach will extend functionality of the developed Artificial Intelligence component of the UrbanFlood Early Warning System.

Time-Frequency Methods for Structural Health Monitoring

“…Process models were used for the Boston levee data analysis [28]: feed-forward neural networks and autoregressive models with exogenous inputs (ARX) were constructed for sensor fault detection. In this work we combine two approaches: feature extraction (wavelet transformation) and process models (analysis of the phase shift based on FFT).…”

Optimal selection of numerical models for flood embankment pore pressure and temperature data

“…A loss of embankment stability is the most-common reason why floods cause damage to areas near rivers (e.g., the Vistula River embankment in Krakow near the heat and power plant, or the Odra River in Winska in Lower Silesia). Many countries (e.g., Denmark and the Netherlands) have developed systems that monitor embankments and predict failure [12,14,16,17]. In Poland, this system is the Computer System for Monitoring River Embankments project (ISMOP), which is financed by the NCBiR [2,9].…”

A Big Data processing strategy for hybrid interpretation of flood embankment multisensor data

“…However, integrated monitoring systems not only allow the measurement, but also the transmission and recording of experimental data in a dedicated database or data-warehouse while some systems also do data processing and interpretation. Such systems have been developed, for example, in Denmark and the Netherlands, and are now being constructed in Poland as part of the Computer System of River Embankment Monitoring (Polish acronym -ISMOP) project, financed by NCBiR (Baliś et al 2011, Krzhizhanovskaya et al 2011, Pyayt et al 2012, Pengel et al 2013, Piórkowski & Leśniak 2014.…”