Interpretation of dam deformation and leakage with boosted regression trees

Predictive models are essential in dam safety assessment. They have been traditionally based on simple statistical tools such as the hydrostatic-season-time (HST) model. These tools are well known to have limitations in terms of accuracy and reliability. In the recent years, the examples of applicat...

Descripción completa

Detalles Bibliográficos
Autores: Salazar González, Fernando, Toledo Municio, Miguel Ángel, Oñate Ibáñez de Navarra, Eugenio|||0000-0002-0804-7095, Suárez Arroyo, Benjamín
Tipo de recurso: artículo
Fecha de publicación:2016
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/87614
Acceso en línea:https://hdl.handle.net/2117/87614
https://dx.doi.org/10.1016/j.engstruct.2016.04.012
Access Level:acceso abierto
Palabra clave:Dam safety
Machine learning
Dam monitoring
Boosted regression trees
Preses (Enginyeria) -- Mesures de seguretat
Àrees temàtiques de la UPC::Enginyeria civil::Enginyeria hidràulica, marítima i sanitària::Embassaments i preses
id ES_ce1def28fad9f03142bcd8aabce5d28d
oai_identifier_str oai:upcommons.upc.edu:2117/87614
network_acronym_str ES
network_name_str España
repository_id_str
spelling Interpretation of dam deformation and leakage with boosted regression treesSalazar González, FernandoToledo Municio, Miguel ÁngelOñate Ibáñez de Navarra, Eugenio|||0000-0002-0804-7095Suárez Arroyo, BenjamínDam safetyMachine learningDam safetyDam monitoringBoosted regression treesPreses (Enginyeria) -- Mesures de seguretatÀrees temàtiques de la UPC::Enginyeria civil::Enginyeria hidràulica, marítima i sanitària::Embassaments i presesPredictive models are essential in dam safety assessment. They have been traditionally based on simple statistical tools such as the hydrostatic-season-time (HST) model. These tools are well known to have limitations in terms of accuracy and reliability. In the recent years, the examples of application of machine learning and related techniques are becoming more frequent as an alternative to HST. While they proved to feature higher flexibility and prediction accuracy, they are also more difficult to interpret. As a consequence, the vast majority of the research is limited to prediction accuracy estimation. In this work, one of the most popular machine learning techniques (boosted regression trees), was applied to model 8 radial displacements and 4 leakage flows at La Baells Dam. The possibilities of model interpretation were explored: the relative influence of each predictor was computed, and the partial dependence plots were obtained. Both results were analysed to draw conclusions on dam response to environmental variables, and its evolution over time. The results show that this technique can efficiently identify dam performance changes with higher flexibility and reliability than simple regression models.Peer Reviewed20162016-07-0120162016-06-01journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/87614https://dx.doi.org/10.1016/j.engstruct.2016.04.012reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2http://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/876142026-05-27T15:37:01Z
dc.title.none.fl_str_mv Interpretation of dam deformation and leakage with boosted regression trees
title Interpretation of dam deformation and leakage with boosted regression trees
spellingShingle Interpretation of dam deformation and leakage with boosted regression trees
Salazar González, Fernando
Dam safety
Machine learning
Dam safety
Dam monitoring
Boosted regression trees
Preses (Enginyeria) -- Mesures de seguretat
Àrees temàtiques de la UPC::Enginyeria civil::Enginyeria hidràulica, marítima i sanitària::Embassaments i preses
title_short Interpretation of dam deformation and leakage with boosted regression trees
title_full Interpretation of dam deformation and leakage with boosted regression trees
title_fullStr Interpretation of dam deformation and leakage with boosted regression trees
title_full_unstemmed Interpretation of dam deformation and leakage with boosted regression trees
title_sort Interpretation of dam deformation and leakage with boosted regression trees
dc.creator.none.fl_str_mv Salazar González, Fernando
Toledo Municio, Miguel Ángel
Oñate Ibáñez de Navarra, Eugenio|||0000-0002-0804-7095
Suárez Arroyo, Benjamín
author Salazar González, Fernando
author_facet Salazar González, Fernando
Toledo Municio, Miguel Ángel
Oñate Ibáñez de Navarra, Eugenio|||0000-0002-0804-7095
Suárez Arroyo, Benjamín
author_role author
author2 Toledo Municio, Miguel Ángel
Oñate Ibáñez de Navarra, Eugenio|||0000-0002-0804-7095
Suárez Arroyo, Benjamín
author2_role author
author
author
dc.subject.none.fl_str_mv Dam safety
Machine learning
Dam safety
Dam monitoring
Boosted regression trees
Preses (Enginyeria) -- Mesures de seguretat
Àrees temàtiques de la UPC::Enginyeria civil::Enginyeria hidràulica, marítima i sanitària::Embassaments i preses
topic Dam safety
Machine learning
Dam safety
Dam monitoring
Boosted regression trees
Preses (Enginyeria) -- Mesures de seguretat
Àrees temàtiques de la UPC::Enginyeria civil::Enginyeria hidràulica, marítima i sanitària::Embassaments i preses
description Predictive models are essential in dam safety assessment. They have been traditionally based on simple statistical tools such as the hydrostatic-season-time (HST) model. These tools are well known to have limitations in terms of accuracy and reliability. In the recent years, the examples of application of machine learning and related techniques are becoming more frequent as an alternative to HST. While they proved to feature higher flexibility and prediction accuracy, they are also more difficult to interpret. As a consequence, the vast majority of the research is limited to prediction accuracy estimation. In this work, one of the most popular machine learning techniques (boosted regression trees), was applied to model 8 radial displacements and 4 leakage flows at La Baells Dam. The possibilities of model interpretation were explored: the relative influence of each predictor was computed, and the partial dependence plots were obtained. Both results were analysed to draw conclusions on dam response to environmental variables, and its evolution over time. The results show that this technique can efficiently identify dam performance changes with higher flexibility and reliability than simple regression models.
publishDate 2016
dc.date.none.fl_str_mv 2016
2016-07-01
2016
2016-06-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/87614
https://dx.doi.org/10.1016/j.engstruct.2016.04.012
url https://hdl.handle.net/2117/87614
https://dx.doi.org/10.1016/j.engstruct.2016.04.012
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2

http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419939460284416
score 15,300724

Similares en LA Referencia