Second-Order MaxEnt Predictive Modelling Methodology. II: Probabilistically Incorporated Computational Model (2nd-BERRU-PMP)

This work presents a comprehensive second-order predictive modeling (PM) methodology based on the maximum entropy (MaxEnt) principle for obtaining best-estimate mean values and correlations model responses parameters. is designated by acronym 2nd-BERRU-PMP, where attribute “2nd” indicates that this incorporates second- order uncertainties (means covariances) second (and higher) sensitivities of computed to The BERRU stands “Best-Estimate Results with Reduced Uncertainties” last letter (“P”) in “probabilistic,” referring MaxEnt probabilistic inclusion computational responses. contradistinction 2nd-BERRU-PMD methodology, which deterministically combines experimental information, as presented accompanying (Part I). Although both 2nd-BERRU-PMP methodologies yield expressions include parameters, respective predicted responses, calibrated parameters their (covariances), are not identical each other. Nevertheless, results encompass, particular cases, produced extant data assimilation adjustment procedures, rely minimization, least-square sense, user-defined functional meant represent discrepancies between measured