Next Article in Journal
Aquifer Response to Stream-Stage Fluctuations: Field Tests and Analytical Solution for a Case Study of the Yangtze River in Wuhan, China
Next Article in Special Issue
Validation of Machine Learning Models for Structural Dam Behaviour Interpretation and Prediction
Previous Article in Journal
River Buffer Effectiveness in Controlling Surface Runoff Based on Saturated Soil Hydraulic Conductivity
Previous Article in Special Issue
Deep Neural Network and Polynomial Chaos Expansion-Based Surrogate Models for Sensitivity and Uncertainty Propagation: An Application to a Rockfill Dam
Article

Anomaly Detection in Dam Behaviour with Machine Learning Classification Models

International Centre for Numerical Methods in Engineering (CIMNE), Universitat Politècnica de Catalunya, 08034 Barcelona, Spain
*
Author to whom correspondence should be addressed.
Academic Editor: Anargiros I. Delis
Water 2021, 13(17), 2387; https://doi.org/10.3390/w13172387
Received: 22 June 2021 / Revised: 19 August 2021 / Accepted: 25 August 2021 / Published: 30 August 2021
(This article belongs to the Special Issue Soft Computing and Machine Learning in Dam Engineering)
Dam safety assessment is typically made by comparison between the outcome of some predictive model and measured monitoring data. This is done separately for each response variable, and the results are later interpreted before decision making. In this work, three approaches based on machine learning classifiers are evaluated for the joint analysis of a set of monitoring variables: multi-class, two-class and one-class classification. Support vector machines are applied to all prediction tasks, and random forest is also used for multi-class and two-class. The results show high accuracy for multi-class classification, although the approach has limitations for practical use. The performance in two-class classification is strongly dependent on the features of the anomalies to detect and their similarity to those used for model fitting. The one-class classification model based on support vector machines showed high prediction accuracy, while avoiding the need for correctly selecting and modelling the potential anomalies. A criterion for anomaly detection based on model predictions is defined, which results in a decrease in the misclassification rate. The possibilities and limitations of all three approaches for practical use are discussed. View Full-Text
Keywords: anomaly detection; machine learning; support vector machines; random forest; one-class classification anomaly detection; machine learning; support vector machines; random forest; one-class classification
Show Figures

Figure 1

MDPI and ACS Style

Salazar, F.; Conde, A.; Irazábal, J.; Vicente, D.J. Anomaly Detection in Dam Behaviour with Machine Learning Classification Models. Water 2021, 13, 2387. https://doi.org/10.3390/w13172387

AMA Style

Salazar F, Conde A, Irazábal J, Vicente DJ. Anomaly Detection in Dam Behaviour with Machine Learning Classification Models. Water. 2021; 13(17):2387. https://doi.org/10.3390/w13172387

Chicago/Turabian Style

Salazar, Fernando, André Conde, Joaquín Irazábal, and David J. Vicente 2021. "Anomaly Detection in Dam Behaviour with Machine Learning Classification Models" Water 13, no. 17: 2387. https://doi.org/10.3390/w13172387

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop