Predictive Computational Science: Computer Predictions in the Presence of Uncertainty

Predictive computational science is the scientific discipline concerned with assessing the predictability of mathematical and computational models of physical events in the presence of uncertainties. It embraces the processes of model selection, statistical calibration and validation of models, model verification, and their use in forecasting features of physical events with quantified uncertainty. In this exposition, the conceptual, mathematical, and statistical foundations of predictive computational science are presented together with demonstrative applications to simple problems in structural mechanics.