Collaborative Research Team Project #02

Statistical Modeling of the World: Computer and Physical Models in Earth, Ocean, and Atmospheric Sciences

This project explores new methodology for using complex computer models and field observations, for applications in earth, ocean, and atmospheric sciences.

Research Category: Ecology & Environment
Region: National
Date: 2015-2018

Why Study Models of the World?

Recent gains in computational power have increased our ability to simulate complex physical phenomena. This brings the potential to investigate scientific questions that historically would have been addressed only through expensive physical experimentation, if at all.

The exploration of complex systems via computational models is common in science. Recent applications range from astrophysics and climate change to the study of micro-scale organisms.

For example, the recent Intergovernmental Panel on Climate Change (IPCC) report contains several conclusions that are based on inference about the real world using computational models. These models allow us to better anticipate, prevent and/or mitigate risk.

Areas of Exploration

Methodology Development

Includes developing new methodology for using complex computer models and field observations for important environmental applications.

Predictive Modeling

Includes leveraging the information from computer models and field observations to make predictions of physical systems, with estimates of uncertainty. Additionally, to estimate unknown physical constants (i.e., a type of inverse problem).

Solving Global Challenges

Research Team’s Goals

To develop new methodology for using complex computer models and field observations for environmental applications.

This project aims to:

promote collaboration among scientists;
make important contributions to statistical and earth, ocean, and atmospheric sciences;
enhance graduate student training.

People Behind the Project

Project Team

Derek Bingham, Team Leader | Simon Fraser University

Collaborators

Hugh Chipman | Acadia University

Richard Karsten | Acadia University

Pritam Ranjan | Acadia University

Gwenn Flowers | Simon Fraser University

Douw G. Steyn | University of British Columbia

William Welch | University of British Columbia

As well as researchers at Brigham Young University, Los Alamos National Laboratory and the National Center for Atmospheric Research.

Relevant Publications

An Introduction Computer Model Calibration with an Application to Radiative Shock Hydrodynamics. Bingham, D.
Design of Experiments in the CANSSI CRT ”Statistical Modeling of the World: Computer and Physical Models in Earth, Ocean, and Atmospheric Sciences”. Bingham, D., Flowers, G., Harari, O. and Pratola, M.
“An introduction to Bayesian statistics and model calibration”, Bingham, D., Grosskopf, M. and Higdon, D.
Inference for Multi-Model Ensembles: An Application in Glaciology. Bingham, D., Flowers, G. and Harari, O.
Harari, O. and Bingham, D. (2016), “Discussion on the Paper Bayesian Design of Experiments for Generalised Linear Models and Dimensional Analysis with Industrial and Scientific Application” by David C. Woods, Antony M. Overstall, Maria Adamou and Timothy W. Waite”, Quality Engineering, 29, p. 104-106.
Harari,O., Bingham, D., Dean, A.M. and Higdon, D.M. (2016) “Computer Experiments: Prediction Accuracy, Sample Size and Model Complexity Revisited”, Statistica Sinica, in press.
Mak, S., Bingham, D., and Lu, Y. (2016) “A Regional Compound Poisson Process for Hurricane and Tropical Storm Damage”, JRSS ‘C, 65, p. 677-703.
Pratola, M., Harari, O., Bingham, D. and Flowers, G. (2016) “Design and Analysis of Experiments on Non-Convex Regions”. Technometrics, in press.
van Bommel, M., Ranjan, P. and Chipman, H. (2017), “A stage-wise surrogate modelling algorithm for tidal power simulations”, to be submitted to CANSSI’s special issue in CJS.
Harari, O., Bingham, D. and Flowers, G. (2017), “Calibration for multi-model ensembles – Glaciology calibration”, to be submitted to Annals of Applied Statistics.
Surjanovic, Bingham, D. and Flowers, G. (2017), “Using computer model uncertainty to inform the design of physical experiments: An application in glaciology”, to be submitted to Journal of Glaciology.
Altman, R. M., Harari, O., Moisseeva, N., Steyn, D. and Welch, W. J. (2017), “Statistical Modelling of Annual Rainfall Pattern in Guanacaste, Costa Rica”, in preparation.
Shi, T., Steyn, D. G. and Welch, D. G. (2017), “Extraction of spatial-temporal ozone features to characterize (and compare) ozone episodes.

Contact

Statistical Modeling of the World: Computer and Physical Models in Earth, Ocean, and Atmospheric Sciences is a Collaborative Research Team project. This program tackles complex problems through a three-year research and training agenda.

CANSSI offers approximately $200,000 for this type of project, which requires a team of faculty, postdocs, and students.

Learn more