This paper proposes to learn an approximate Bayesian Network (BN) model from Monte-Carlo simulations of an infrastructure system exposed to seismic hazard. Exploiting preliminary physical simulations has the twofold benefit of building a drastically simplified BN and of predicting complex system performance metrics. While the approximate BN cannot yield exact probabilities for predictive analyses, its use in backward analyses based on evidenced variables yields promising results as a decision support tool for post-earthquake rapid response. Only a reduced set of infrastructure components, whose importance is ranked through a random forest algorithm, is selected to predict the performance of the system. Further, owing to the higher importance of evidenced nodes, the ranking method is enhanced with a recursive evidence-driven BN-building algorithm, which iteratively inserts evidenced components into the subset identified by the random forest algorithm. This approach is applied to a French road network, where only 5 to 10 components out of 58 are kept to estimate the distribution of system performance metrics that are based on traffic flow. Sensitivity studies on the number of selected components, the number of off-line simulation runs and the discretization of variables reveal that the reduced BN applied to this specific example generates trustworthy estimates.

Approximate Bayesian Network Formulation for the Rapid Loss Assessment of Real-World Infrastructure Systems / Gehl, Pierre; Cavalieri, Francesco; Franchin, Paolo. - In: RELIABILITY ENGINEERING & SYSTEM SAFETY. - ISSN 0951-8320. - STAMPA. - 177:(2018), pp. 80-93. [10.1016/j.ress.2018.04.022]

Approximate Bayesian Network Formulation for the Rapid Loss Assessment of Real-World Infrastructure Systems

Cavalieri, Francesco;Franchin, Paolo
2018

Abstract

This paper proposes to learn an approximate Bayesian Network (BN) model from Monte-Carlo simulations of an infrastructure system exposed to seismic hazard. Exploiting preliminary physical simulations has the twofold benefit of building a drastically simplified BN and of predicting complex system performance metrics. While the approximate BN cannot yield exact probabilities for predictive analyses, its use in backward analyses based on evidenced variables yields promising results as a decision support tool for post-earthquake rapid response. Only a reduced set of infrastructure components, whose importance is ranked through a random forest algorithm, is selected to predict the performance of the system. Further, owing to the higher importance of evidenced nodes, the ranking method is enhanced with a recursive evidence-driven BN-building algorithm, which iteratively inserts evidenced components into the subset identified by the random forest algorithm. This approach is applied to a French road network, where only 5 to 10 components out of 58 are kept to estimate the distribution of system performance metrics that are based on traffic flow. Sensitivity studies on the number of selected components, the number of off-line simulation runs and the discretization of variables reveal that the reduced BN applied to this specific example generates trustworthy estimates.
Bayesian networks, Seismic risk, Decision support, Road network, Bayesian learning, System performance
01 Pubblicazione su rivista::01a Articolo in rivista
Approximate Bayesian Network Formulation for the Rapid Loss Assessment of Real-World Infrastructure Systems / Gehl, Pierre; Cavalieri, Francesco; Franchin, Paolo. - In: RELIABILITY ENGINEERING & SYSTEM SAFETY. - ISSN 0951-8320. - STAMPA. - 177:(2018), pp. 80-93. [10.1016/j.ress.2018.04.022]
File allegati a questo prodotto
File Dimensione Formato  
Cavalieri_ApproximateBayesian_2018.pdf

accesso aperto

Tipologia: Documento in Post-print (versione successiva alla peer review e accettata per la pubblicazione)
Licenza: Creative commons
Dimensione 1.99 MB
Formato Adobe PDF
1.99 MB Adobe PDF Visualizza/Apri PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1130414
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 21
  • ???jsp.display-item.citation.isi??? 20
social impact