The next generation of infrared spectroscopic solutions collect massive amounts of data that is realistically much too dense to be understood by a human. Thus, as a practical necessity, the user is generally interested in a smaller number of “critical” variables that aren’t directly observed. However, considering a more manageable subset of the raw data throws away a great deal of collected information. The problem of distilling the critical variables and related uncertainties from the raw data is one of statistical inference. We adopt a Bayesian approach to better quantify the uncertainties in the critical variables. This approach, when paired with an appropriate model of the hardware and the system being observed, can greatly improve the effective signal to noise and/or reduce the required measurement time.
|