Quantification of Model Uncertainty: Calibration, Model Discrepancy, and Identifiability

@inproceedings{Arendt2012QuantificationOM,
  title={Quantification of Model Uncertainty: Calibration, Model Discrepancy, and Identifiability},
  author={Paul Daniel Arendt and Daniel W. Apley and Wei Chen},
  year={2012}
}
To use predictive models in engineering design of p hysical systems, one should first quantify the model uncertainty via model updating techniques emp loying both simulation and experimental data. While calibration is often used to tune unkno w calibration parameters of the computer model, the addition of a discrepancy function has b een used to capture model discrepancy due to underlying missing physics, numerical approximation s, and other inaccuracies of the computer model that would exist… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 43 CITATIONS

Improving identifiability in model calibration using multiple responses

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Bayesia n c libration of computer models

M. C. Kennedy, A. O'Hagan, 2001
  • Journal of the Royal Statistical Society: Series B, 63(3), p. 425-464.
VIEW 9 EXCERPTS
HIGHLY INFLUENTIAL

A Framework for Validation of Computer Models

  • Technometrics
  • 2007
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Similar Papers

Loading similar papers…