Events
- SAMSI Program on Development, Assessment and Utilization of Complex Computer Models (2006-2007): Study of computer models
needs to take place in the context of actual computer models. But because of the inherent complexity of computer models, and the very
different types of such models, SAMSI held a thematic year with sub-programs, focusing on specific computer modeling scenarios.
This approach allowed in-depth exploration of specific types of computer models. Subprograms included environmental/ecological models,
uncertainty in models of granular materials, engineering and biological models, as well as a program geared to methodology.
- NCAR Theme of the Year on Statistics for Numerical Models (2006-2007):
Numerical models are vital to simulate geophysical, chemical and ecological processes and to understand the relationship among components in
the Earth system. As models have become larger and more complex, their construction, validation and analysis are no longer amenable to simple
approaches and statistical summaries. Statistical science in the past 20 years has advanced to handle the interpretation of complicated
multivariate, spatial and temporal data sets and it is well suited to tackle the massive outputs from numerical experiments that are now the
norm in the geosciences. This theme is undertaken with the goal of matching cutting edge statistical methods to the needs of geophysical model
development and to make statisticial scientists aware of the particular scientific issues and research in the geophysical modeling community.
Several workshops were held to bring statisticians and application area scientists together to work on pressing questions. The first workshop was intended as a scoping and brainstorming meeting where four NCAR modeling groups met with a large group of statisticians interested in the design and analysis of computer experiments. The intent was that concrete problems would be identified that helped structure a joint statistical working group activity at SAMSI's thematic year (above). For each modeling group statistical researchers served as a liaison to guide collaboration among the modeling group and the statistical working groups. Subsequent workshops were in a more traditional conference format, but included a blend of tutorial and research talks, as well as presentations on the progress on specific modeling projects initiated in the first workshop. - Summer School on the Design and Analysis of Computer Experiments at SFU (2006):
This endeavor was jointly sponsored by the NICDS Program on Computer Experiments and SAMSI. The Summer School had
several exciting components. Firstly, there was a 1.5-day short course run by leading researchers Will Welch and Jerry Sacks (NISS).
In addition, a mini-symposium with talks from leading academics and
also young researchers (e.g., Fei Liu, Duke University; Matt Taddy, UC Santa Cruz; Bela Nagy, UBC; and Pritam Ranjan,
SFU) was held. Lastly, a 2-day problem solving event took place. For this, physicists from Los Alamos National Lab (Katrin Heitman and Salman Habib)
presented a real computer experiment of current interest for their research program. The goal of the problem solving endeavor was
to help solve the physicists’ problem using the techniques learned in the short course. The participants
were separated into groups, and at the end of the final day presented their solutions.
- Workshop on the Design and Analysis of Computer Experiments (2004):
The workshop format aimed to facilitate interaction among the participants. Like many others such events, the workshop had a combination of talks,
poster sessions and roundtable discussions. However, the presentations aimed to address three theme topics of the workshop
(1. Factor Screening in High Dimensions; 2. Function Fitting in High Dimensions; and 3. Integration of Physical and Computer Experiments).
Furthermore, the topics presented also met a secondary criterion in that they demonstrated new methodology or an application
in one of the theme areas. These unique features were aimed at stimulating research on specific problems.