IMI Interdisciplinary Mathematics InstituteCollege of Arts and Sciences

How can we ever trust extrapolative predictions?

  • March 21, 2016
  • 1:15 p.m.
  • LeConte 312


The ultimate purpose of most computational models is to make predictions, commonly in support of some decision-making process (e.g., for design or operation of some system). The quantities that need to be predicted (the quantities of interest or QoIs) are generally not experimentally observable before the prediction, since otherwise no prediction would be needed. Assessing the validity of such extrapolative predictions, which is critical to informed decision-making, is challenging. In classical approaches to validation, model outputs for observed quantities are compared to observations to determine if they are consistent. By itself, this consistency only ensures that the model can predict the observed quantities under the conditions of the observations. This limitation dramatically reduces the utility of the validation effort for decision making because it implies nothing about predictions of unobserved QoIs or for scenarios outside of the range of observations. This talk presents a validation and predictive assessment process that supports extrapolative predictions for models with known sources of error. The process includes stochastic modeling, calibration, validation, and predictive assessment phases where representations of known sources of uncertainty and error are built, informed, and tested. The proposed methodology is applied to an illustrative extrapolation problem involving a misspecified nonlinear oscillator.

Short Bio: Gabriel Terejanu has been an Assistant Professor in the Department of Computer Science and Engineering at University of South Carolina since 2012. Previously he was a Postdoctoral Fellow at the Institute for Computational Engineering and Sciences at University of Texas at Austin. He holds Ph.D. in Computer Science and Engineering from University at Buffalo. He is currently working on the development of a comprehensive uncertainty quantification framework to accelerate the scientific discovering process and decision-making under uncertainty. Some projects currently supported by NSF and VP for Research include discovery of novel catalytic materials for biorefinery industry, modeling and prediction of naturally occurring carcinogenic toxins, and development of statistical models for tracking individual student knowledge.

© Interdisciplinary Mathematics Institute | The University of South Carolina Board of Trustees | Webmaster