Loading...

Emergency Management Decision Support System Based on Bayesian Network

Khani Dehaj, Mohammad | 2022

72 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55716 (09)
  4. University: Sharif University of Technology
  5. Department: Civil Engineering
  6. Advisor(s): Mahsuli, Mojtaba
  7. Abstract:
  8. This research proposes a probabilistic framework for decision support in emergency response. Currently, decision-making is traditionally based on data from reconnaissance teams, while there are other information sources that assist decision-making. These sources of information include social sensors, physical sensors, aerial imaging, and crowdsourcing. The information obtained from these sources is heterogeneous and uncertain, requires a probabilistic data fusion framework to be used in decision making. This research employs Bayesian Networks for this purpose. The outstanding feature of the Bayesian Network is its real-time nature, which set apart it from other methods. This feature makes the Bayesian Network a suitable tool for the development of an emergency management decision support system. The aforementioned sources of information provide evidence on the state of the community and its infrastructure. Using the evidence, the Bayesian Network transforms prior probabilities learned from simulation-based predictions into posterior probabilities through Bayesian updating based on Bayes's theorem. The proposed framework includes three modules: the hazard module, the infrastructure module, and the decision-making module. In the hazard module, the magnitude, hypocenter, and intensity of the earthquake at the location of each infrastructure component are modeled. Considering the interdependency of infrastructure, the infrastructure module models the damage, performance, and serviceability of infrastructure systems based on intensities at their location. As a result of repeated updating, uncertainties is gradually reduced, which leads to situational awareness of the post-disaster state of the community. Subsequently, information obtained from situational awareness is used for decision-making. This information includes the travel time in the transportation network for transferring of the injured and the damage state of infrastructure components for prioritizing the inspection and repair operations. The proposed framework is showcased in a comprehensive application to a virtual city with a population of over 125,000, 17,000 buildings, and power, water, and transportation, and healthcare systems.
  9. Keywords:
  10. Bayesian Network ; Emergency Management ; Probabilistic Modeling ; Infrastructure ; Resilience ; Interdependency ; Infrastructure Resilience ; Decision Making Support System

 Digital Object List

 Bookmark

No TOC