go to SAMSI home page EMPTY SPACE
19 T.W. Alexander Drive
P.O.Box 14006
Research Triangle Park, NC 27709-4006
Tel: 919.685.9350
Fax: 919.685.9360
info@samsi.info

Engineering Methodology
A Working Group in Development, Assessment and Utilization of Complex Computer Models

 

Group Leaders: Tom Santner (Ohio State)

LOCKED Password Protected Site (future)

 

 

Announcements

Meeting Time: Tuesday 12:30 - 2:00
Location: NISS building, Room 203

Remote access for the meeting is available:  Via teleconference at 919-685-9338

For futher assistance in connecting to the meeting via teleconference and WebEX use this link

Note: Until we can get the needed bandwidth, equipment, etc. for broadcasting meetings via a webcam, SAMSI will be employing the following process for remote participation in working groups. A webcam picture will be available for viewing during the meetings. However, for audio, participants will have to call into the conference line.

Meeting Activities

Date Topics & Readings Notes & Downloads
 9/26/06  Introduction of Working Group Members Introduction

 10/3/06 Ian Dinwoodie - NS2 Emmulator
Laura Swiller - Transient, 1-D heat conduction through a slab.
Fei Liu - Discussion of the Thermal Model
Material from Ian's Talk
Thermal Model (L. Swiler)
Results of Thermal Model Challenge
Slides for Fei's Talk
 10/10/06 Abani Patra - Crash Simulator Model and Data for Uncertainty Analysis and Applications to Child Restraint Systems CRS_simulation.pdf
Crash_Simulation_2.pdf 
 10/17/06 Group Discussion of Calibration Models
This will be a group discussion of various calibration models.  We will be discussing a variety of sources including papers by Kennedy and O'Hagan, Higdon as well as Fei Lui's approach for the the thermal model previously discussed.
Calibration Papers:
Kennedy and O'Hagan (2001)
Discussion here and here
Higdon 2005
Slides for Fei's Talk

Here is the material Herbie Lee mentioned during the discussion today:

To follow-up on today's meeting, here are links to two of our tech reports.  

The main reference for treed Gaussian Processes is:
http://www.ams.ucsc.edu/reports/trview.php?content=view&name=ams2006-08

The main reference for adaptive sampling (using the results of a treed
GP emulator to help choose new run locations):
http://www.ams.ucsc.edu/reports/trview.php?content=view&name=ams2006-13

Treed GPs and some of the adaptive design computations are in the R
package tgp, which can be accessed from within R using
install.packages("tgp")
or from the CRAN website:
http://www.cran.r-project.org/src/contrib/Descriptions/tgp.html

Here is a copy of Tom Santner's slides used in today's discussion:

TJS-overview.pdf

 10/24/06 We will be discussing two specific models: 
Geothermal Reservoir Engineering (Tiangang Cui)
A Ground Water Simulation Model (Max Morris)
Here are Max's Slides slide1 slide 2
One option is to have a discussion of predictions when data are non-stationary, but our first topics may be dictated by earlier model discussions. 
10/26/06-
10/27/06 
 Joint Engineering and Methodology Workshop
See http://www.samsi.info/workshops/2006compmod-eng-meth200610.shtml  for details


 10/31/06 NO MEETING    
 11/7/06 We will probably discuss issues about the relations between simulators and reality. For that discussion, the paper in the suggested readings list
Reified Bayesian Modelling and Inference for Physical Systems <http://www.stat.duke.edu/%7Efei/samsi/Readings/Reify.pdf>  (Goldstein
and Rougier, 2006) will be very relevant.

We will also discuss Validation. You might like to get familiar with the papers suggested in Tony~Rs basic reading list
<http://www.stat.duke.edu/%7Efei/samsi/Readings/readinglist_ohagan>.  and with the issues mentioned in the Gaussian Process Methodology
Topics  <http://www.stat.duke.edu/%7Efei/samsi/Sep_25/GaussianProcessMethTopics.pdf> handout that Tony prepared during the Kickoff
workshop.
Here are also a set of slides for the talk:
Tony0-11-07.ppt

There will also be ample time for general discussion and other questions.

The Department of Energy document mentioned by Tom Loredo is available here
 
 11/14/06  Remote (WebEx, Teleconfererencing and Videoconferencing) presentation of Climate models by Climate Modelers groups in NCAR. Room will be 203, and the hours (Mountain Time) of remote connection appear in read in the definite program (remember to add 2 hours to the times displayed in the program). Margaret will send precise instructions.

There will be a total of 4 presentations of Climate models, in the areas of  Anthropogenic Land Cover, Turbulent Flows, Upper Atmosphere, Planetary Boundary Layer; please plan to attend at least one of them (or more if you are interested) as they might suggest interesting methodological issues to consider in the future by our group.
 
11/21/06 No Meeting Thanksgiving Week
11/28/06 This session with be a specific working session devoted to developing a mathematical approach for the vibration model that Tony O'Hagan outlined on Novmeber 7, 2006 Tony0-11-07.ppt.  We will have a knowlegdable model builder available who can we can use to test ideas. Our intent is get specific.  Here is a copy of the presentation made by Hilmi from Roll Royce
12/5/06 This will be a meeting to discuss developing a simpler dynamical model in order to generate some sample data to use in investigating different possible approachs to the turbine blade vibration model/data.  This should be a relatively informal meeting with a good deal of discussion on some basic approaches and ideas.

Here are a selection of papers that are relevant to our discussion of modeling the turbine blade problem:
paper1
paper2
paper3
paper4
paper5
paper6
12/12/06 Guennadi Andrianov will discuss computer codes that are used to help  determine reactor safety.  The uncertainty analysis of such codes is a critical issue in assessing safety.  The discussion of how code  uncertainty is determined will be of primary concern in this session.   His talk is titled

Uncertainty treatment at EDF: A study case  - computer model calibration

Here are a set of slides for his talk:  SAMSI121206.ppt

PLEASE NOTE THAT THIS MEETING WILL START AT 12:15 PM NOT 12:30 PM

1/9/07 This will be a working group discussion devoted to the simplified Rotor Blade model.  There will be a short discussion of implementing state-space models in MATLAB and a demonstration of a simpe model for the turbine blade dynamics.  (Grant,  Gentry)
1/16/07 Today will continue our discussion of the turbine blade modeling problem and present a possible approach to the problem.    011607slides.pdf
blades5.m
1/23/07 We continue our discussion with presentations by Tom Santner and Gentry White 012307slides.pdf
EngMeth23Jan07.pdf
1/30/07 Sandeep K. Shukla will speak on  "Verification of Computer Codes'' his presentation is included here
2/8/07
NOTE: THE DATE IS CHANGED
We are meeting on Thursday instead of Tuesday, the meeting time will still be 12:00-1:30 PM Eastern Time which is earlier than usual.  Additionally the room will be 104 in the NISS Building.  The phone number will be 919-685-9333.  

We will continue the discussion and development of the turbine blade emulator.
Here is the lexicon of explaining the model and the meaning the variables mentioned in today's discussion.
020807.pdf
2/13/07 We will continue discussion of the Forward Filtering Backwards Sampling algorithm from Carter and Kohn 1994 and discuss other sampling issues.  Here are notes for the day, in the near future there will be an updated reading list posted. Here is an updated reading list for some of the papers we have discussed.

See also the reading list for the Methodology Working Group for further resources.
2/22/07 Note that this weeks meeting is moved to Thursday February 22, the same time and contact information apply as before.

The discussion will concern a linearized version of a hydrology model using a state-space formulation, the latter being our continuing theme.   Notes and resources will be posted here prior to the meeting.
Here is a copy of Peter's latest presentation concerning the hydrological model.
2/27/07 Fei Liu will be presenting her work on Dynamic Linear Models (DLMs).  Here is a copy of her presentation.  We will also be discussing the future of the working group meetings.
3/6/07 No Meeting
3/13/07 No Meeting
3/20/07 Brief and informal meeting discussing general topics and progress Gentry will have a few simple examples of state-space model results and Peter will speak on possibilities for dealing with non-linearity.  gaw.pdf
3/27/07 No Topic
4/3/07 Joint Workshop with MUCM no meeting
4/10/07 Follow up discussion from the Joint workshop with MUCM
4/17/07 John McFarland will give a talk on his experience with QASPR data.  Slides of his talk are available here and here.
5/8/08 Preliminary Discussion of talk for Transition Meeting.  Here are the slides.
5/29/07 Follow up meeting from the Transitional Workshop.  We will discuss two papers concerning computational improvements to the MCMC for the State-Space Model.
The papers are here paper1 paper2


Group Members

Name Affiliation Email Address
Don Bartel Cornell dlb13 (at) cornell.edu
Dianne Bautista Ohio State bautista (at) stat.ohio-state.edu
Susie Bayarri University of Valencia/SAMSI susie.bayarri (at) uv.es
Thomas Bengtsson Bells Labs tocke (at) research.bell-labs.com
Tiangang Cui University of Auckland tcui001 (at) math.auckland.ac.nz
Ian Dinwoodie Duke ihd (at) stat.duke.edu
Chris Gotwalt SAS chris.gotwalt (at) sas.com
Genetha Gray SANDI gagray (at) sandi.gov
Eitan Greenshtein N.C. State/SAMSI eitan.greenshtein (at) gmail.com
Gang Han Ohio State han.191 (at) osu.edu
Dave Higdon LANL dhigdon (at) lanl.gov
Ying Hung Georgia Tech yhung (at) isye.gatech.edu
Herbie Lee UC-Santa Cruz herbie (at) ams.ucsc.edu
Simon Lunagomez Duke/SAMSI simon.lgz (at) duke.edu
Abhyuday Mandal University of Georgia amandal (at) stat.uga.edu
Scott Mitchell Sandia samitch (at) sandia.gov
Max Morris Iowa State mmorris (at) iastate.edu
Nancy Nichols Reading University n.k.nichols (at) rdg.ac.uk
Abani Patra University of Buffalo abani (at) eng.buffalo.edu
Angie Patterson GE patterso (at) research.ge.com
Mark Perry LSE m.perry (at) lse.ac.uk
Bruce Pitman University of Buffalo pitman (at) buffalo.edu
Grant Reinman  Pratt and Whitney  grant.reinman (at) pw.utc.com
Jerry Sacks NISS sacks (at) niss.org
Tom Santner Ohio State santner.1 (at) osu.edu
Randy Sitter Simon Fraser University sitter (at) stat.sfu.ca
Curtis Storlie N.C. State storlie (at) stat.ncsu.edu
Laura Swiler Sandia lpswile (at) sandia.gov
Matt Taddy UC-Santa Cruz taddy (at) ams.ucsc.edu
Shih-Chung Tsai GM shih-chung.tsai (at) gm.com
Gentry White N.C. State white (at) stat.ncsu.edu
Henry Wynn LSE h.wynn (at) lse.ac.uk
Thanasis Kottas
UCSC
thanos (at) ams.ucsc.edu
Bruno Sanso UCSC  bruno (at)  ams.ucsc.edu
Dorin Drignei Oakland University drignei (at) oakland.edu
Blaza Toman NIST toman (at) nist.gov
Zhiguang Qian Univ. Wisconsin zhiguang (at) stat.wisc.edu
Shane Reese Brigham Young University reese (at) hannibal.byu.edu
Jason Kao University of Georgia jasonkao (at) uga.edu
Peter Reichert EAWAG (Swiss Federal Institute of Aquatic Science and Technology) reichert (at) eawag.ch
Angela Dean Ohio State University amd (at) stat.ohio-state.edu
Lisa Moore Los Alamos National Labs lmoore (at) lanl.gov
David Steinberg Tel Aviv University dms (at) post.tau.ac.il

 

 

Send your comments about this site to: Tom Santner