On June 1, 2009, Air France Flight 447 with 228 passengers and crew disappeared over the Atlantic while on a flight from Rio de Janeiro to Paris. About two years after the loss of the aircraft and four intensive searches, a group of statisticians was able to predict almost the exact location of the wreckage. Searchers found it within a week.
On Tuesday, Feb. 2, at NASA’s Langley Research Center in Hampton, Virginia, J. Van Gurley will present “Bayesian Search for Air France 447: The Math that Found a Needle in a Haystack” at 2 p.m. in the Pearl Young Theater. Gurley is with Metron, Incorporated, whose Advanced Mathematics Applications Division is credited with producing the analysis that found the aircraft.
Gurley will be available to answer questions from the media during a news briefing at 1:15 p.m. that day. Media who wish to do so should contact Chris Rink at 757-864-6786, or by e-mail at chris.rink@nasa.gov, by noon on the day of the talk for credentials and entry to the center.
That same evening at 7:30, Gurley will present a similar program for the general public at the Virginia Air & Space Center in downtown Hampton. This Sigma Series event is free and no reservations are required.
Bayesian statistics is a set of mathematical rules for using new data to continuously update an existing knowledge base. A well-developed method for planning searches for missing aircraft, ships lost at sea, or people missing on land, Bayesian search theory combines all the available information about the location of a search object. This is important in one-of-a-kind searches where there is little or no statistical data to rely upon.
The theory has been applied successfully to searches for the missing nuclear submarine USS Scorpion and the 1857 shipwreck of the SS Central America. It is used routinely the by U.S. Coast Guard to find people and ships missing at sea.
Gurley’s talk presents the basic elements of the theory, and how it was used to locate the wreck of Air France flight 447 after two years of unsuccessful search. He will finish with a discussion of the current search for Malaysian Air flight 370 in the Indian Ocean, describing what is known and how the Bayesian approach could be used to guide search efforts.
As a senior manager at Metron in the District of Columbia, Gurley leads a number of research and development efforts in predictive analytics, data fusion, and mission planning for the Defense Advanced Research Projects Agency, Office of Naval Research, and Federal Aviation Administration. Prior to joining Metron, he completed a 26-year career in the United States Navy rising to the rank of captain while serving as a submarine warfare officer, and naval meteorology and oceanography specialist. His education includes a Bachelor of Science in physics from the University of Florida, and a Master of Science and engineering degrees in ocean engineering awarded jointly by the Massachusetts Institute of Technology and Woods Hole Oceanographic Institute.
For more information about NASA Langley’s Colloquium and Sigma Series Lectures, visit:
http://colloqsigma.larc.nasa.gov
