D. Koutsoyiannis, Optimal decomposition of covariance matrices for multivariate stochastic models in hydrology, WATER RES R, 35(4), 1999, pp. 1219-1229
A new method is proposed for decomposing covariance matrices that appear in
the parameter estimation phase of all multivariate stochastic models in hy
drology. This method applies not only to positive definite covariance matri
ces (as do the typical methods of the literature) but to indefinite matrice
s, too, that often appear in stochastic hydrology. It is also appropriate f
or preserving the skewness coefficients of the model variables as it accoun
ts for the resulting coefficients of skewness of the auxiliary (noise) vari
ables used by the stochastic model, given that the latter coefficients are
controlled by the decomposed matrix. The method is formulated in an optimiz
ation framework with the objective function being composed of three compone
nts aiming at (1) complete preservation of the variances of variables, (2)
optimal approximation of the covariances of variables, in the case that com
plete preservation is not feasible due to inconsistent (i.e., not positive
definite) structure of the covariance matrix, and (3) preservation of the s
kewness coefficients of the model variables by keeping the skewness of the
auxiliary variables as low as possible. Analytical expressions of the deriv
atives of this objective function are derived, which allow the development
of an effective nonlinear optimization algorithm using the steepest descent
or the conjugate gradient methods. The method is illustrated and explored
through a real world application, which indicates a very satisfactory perfo
rmance of the method.