Bayesian Kernel Methods for Critical Infrastructure Resilience Modeling

Integrating Bayesian methods with kernel methods has recently garnered attention, as Bayesian methods make use of previous data in order to estimate posterior probability distributions of the parameter of interest given that it follows a specific prior distribution. As the quantification of resilience has become a vital component of infrastructure risk analysis, the authors use the Beta Bayesian kernel model to estimate resilience metrics used to analyze the recovery process of disrupted critical infrastructure systems. More specifically, stochastic resilience-based component importance measures are assessed using the component's characteristics and disruption data. Such estimates would help risk managers determine the overall best recovery strategy of an infrastructure system in case of a disruption impacting multiple components. The model is deployed in an application to an inland waterway transportation network, the Mississippi River Navigation system, for which the recovery of disrupted locks and dams on sections of the river is analyzed by estimating the resilience using the Bayesian kernel model.

Language

  • English

Media Info

  • Media Type: Web
  • Pagination: pp 687-694
  • Monograph Title: Vulnerability, Uncertainty, and Risk: Quantification, Mitigation, and Management

Subject/Index Terms

Filing Info

  • Accession Number: 01532725
  • Record Type: Publication
  • ISBN: 9780784413609
  • Files: TRIS, ASCE
  • Created Date: Jul 7 2014 3:01PM