Geophysical Statistics Project

The figure displays profiles for a wavelet-based, nonstationary covariance function estimated for surface ozone in the eastern U.S. with each panel showing a covariance surface between the grid point indicated by the red dot and the rest of the grid points. Such covariance functions are at the heart of statistical procedures that estimate the spatial distribution of ozone from data collected by a network of monitoring stations. This spatial distribution is critical in producing the necessary regional inferences that would be required for monitoring air quality and to quantify the exposure of a population to high ozone levels.

For the past decade, the Geophysical Statistics Project (GSP) has been a leader in training and research emphasizing the synergy between the geosciences and the statistical sciences. Aside from basic methodological and theoretical statistical research, GSP has had a strong training component supporting from four to six postdoctoral visiting scientists (see GSP proposal). The post-docs are immersed in research activities that not only focus their skills as applied statisticians but also expose them to important applications in the geosciences.

In addition to these core activities, GSP also has an active visitor program providing research opportunities for visiting graduate students and junior and senior faculty members from across the nation and abroad. As with the post-doctoral training program, the goal of these programs is to foster collaboration between graduate students, post-docs, the permanent and visiting statistical staff, and the NCAR scientists. These programs, as well as the research and training aspects of GSP emphasizing the interaction between statistics and the geosciences, embody the tenets of integration, innovation, and community building within the NCAR strategic plan. Specifically, this program supports the NCAR strategic priorities of "Conducting research in computer science, applied mathematics, statistics, and numerical methods," "Enhancing science education," and "Engaging a broader and more diverse community."

During FY 2006, GSP researchers have been involved in a number of important projects, including analyzing climate model experiments, developing methodology for analyzing extremes of weather and climate, and carbon transport (see GSP plans in CISL Annual Report 2005). GSP continues to develop methodology for analyzing spatial data, including nonstationary covariance models, models for spatial lattice data, multivariate spatial observations, spatial-temporal models, as well as general methodology for computational statistics and Bayesian hierarchical models.

In FY 2007, the scientific focus on analyzing climate model experiments will continue, in particular with GSP scientists being involved in such NCAR programs as the North American Regional Climate Model Assessment Program (NARCCAP). Beyond climate models, there are a number of statistical and data analysis issues within the many different computer modeling groups at NCAR. To help focus our efforts in these areas, GSP will be active within the 2007 IMAGe Theme-of-the-Year, Statistics and Computer Models, that will also engage statisticians and mathematicians at the Statistical and Applied Mathematical Sciences Institute (SAMSI), an NSF mathematics center in Research Triangle Park, North Carolina.

This project is made possible through NSF Core funding.