Abstract #301819

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2002 Program page
JSM 2002 Abstract #301819
Activity Number: 146
Type: Contributed
Date/Time: Monday, August 12, 2002 : 2:00 PM to 3:50 PM
Sponsor: Section on Risk Analysis*
Abstract - #301819
Title: Rare Event Models for Importance Sampling in Particle Dispersion
Author(s): Mark Fitzgerald*+ and Richard Picard
Affiliation(s): University of Colorado, Denver and Los Alamos National Laboratory
Address: , , , ,
Keywords: Importance Sampling ; Markov chains ; Adaptive Methods
Abstract:

For emergency response scenarios, such as factory chemical releases or biological weapons attacks, atmospheric scientists need the ability to estimate potential human exposure or release location within a few minutes of the event. Currently, particle dispersion codes simulate particle paths (Markov chains) and perform estimation with sample means. For rare event phenomena, millions (or billions) of sample paths must be simulated, to have a reasonable chance of seeing even one particle path of interest. Biasing particle paths via importance sampling is crucial to producing reliable estimates of rare events in a reasonable amount of computing time. Adaptive methods are needed to find appropriate importance distributions, and a good class of models in which to adapt is needed.

  • The address information is for the authors that have a + after their name.
  • Authors who are presenting talks have a * after their name.

Back to the full JSM 2002 program

JSM 2002

For information, contact meetings@amstat.org or phone (703) 684-1221.

If you have questions about the Continuing Education program, please contact the Education Department.

Revised March 2002