Predictive models are essential in dam safety assessment. Both deterministic and statistical models applied in the day-to-day practice have demonstrated to be useful, although they show relevant limitations at the same time. On another note, powerful learning algorithms have been developed in the field of machine learning (ML), which have been applied to solve practical problems. The work aims at testing the prediction capability of some state-of-the-art algorithms to model dam behaviour, in terms of displacements and leakage. Models based on random forests (RF), boosted regression trees (BRT), neural networks (NN), support vector machines (SVM) and multivariate adaptive regression splines (MARS) are fitted to predict 14 target variables. Prediction accuracy is compared with the conventional statistical model, which shows poorer performance on average. BRT models stand out as the most accurate overall, followed by NN and RF. It was also verified that the model fit can be improved by removing the records of the first years of dam functioning from the training set.Peer ReviewedPostprint (author’s final draft

This paper aims to present and validate a numerical technique for the simulation of the overtopping and onset of failure in rockfill dams caused by mass sliding. This goal is achieved by coupling a fluid dynamic model for the simulation of the free surface and through-flow problems together with a numerical technique for the calculation of the rockfill response and deformation. Both the flow within the dam body and in its surroundings are taken into account. An extensive validation of the resulting computational method is performed by solving several failure problems on physical models of rockfill dams for which experimental results have been obtained by the authors.

The paper focuses on the analysis of radial-gated spillways, which is carried out by the solution of a numerical model based on the finite element method (FEM). The Oliana Dam is considered as a case study and the discharge capacity is predicted both by the application of a level-set-based free-surface solver and by the use of traditional empirical formulations. The results of the analysis are then used for training an artificial neural network to allow real-time predictions of the discharge in any situation of energy head and gate opening within the operation range of the reservoir. The comparison of the results obtained with the different methods shows that numerical models such as the FEM can be useful as a predictive tool for the analysis of the hydraulic performance of radial-gated spillways.

Se presentan resultados obtenidos mediante la aplicación del MétododePartículasyElementosFinitos (PFEM) en la simulación dedeslizamientosdeladeraenembalses. Es un fenómeno complejo, por la interacción entre el material deslizado, la masa de agua del embalse, yel conjunto formado por el vaso y la presa. PFEM es un esquema numérico original con el que se ha afrontado con éxito la resolución de problemas de interacción fluido-estructura. Combina un enfoque Lagrangiano con la resolución de las ecuaciones deelementosfinitosmediante la generación de una malla, que se actualiza en cada paso de tiempo. Se presentan resultados de casos de validación en los que se han reproducido ensayos en laboratorio existentes en la bibliografía técnica. Se muestran también otros cálculos más complejos, sobre la cartografía a escala real de un embalse, donde se aprecia el fenómeno de generación de la ola, su propagación por el embalse y la afección a la presa. Por último, se ha modelado el deslizamiento ocurrido en 1958 en la bahía de Lituya (Alaska), enel que la caída de 90 millones de toneladas de roca produjo una ola que alcanzó una sobreelevación máxima de 524 m en la ladera opuesta. Los resultados permiten afirmar que PFEM puede ser una herramienta útil enel análisis de riesgos frente a este tipo de fenómenos, ofreciendo una buena aproximación de las afecciones potenciale

This paper presents the results of an extensive laboratory set of tests aimed to study the failure of the downstream shoulder of highly permeable rockfill subjected to overflow. The experimental research comprised testing 114 physical models by varying the following elements: (i) the median size of the uniform gravels (7 to 45 mm); (ii) the configuration of the dam, i.e., upstream and downstream shoulders and crest or just the downstream shoulder; (iii) the dam height (from 0.2 to 1 m), (iv) the crest length (from 0.4 to 2.5 m), (v) the downstream slope (from 1 to 3.5 H:V), (vi) the type of impervious element (i.e., central core, upstream face, and no impervious element). The tests allowed us to identify two failure mechanisms, slumping and particle dragging. In addition, the downstream slope was observed to be one of the most important variables in this parametric study, as it influenced the pore water pressures inside the dam, the failure discharge, and the occurrence of one or the other mechanism of failure.