D. Koutsoyiannis, A generalized mathematical framework for stochastic simulation and forecast of hydrologic time series, WATER RES R, 36(6), 2000, pp. 1519-1533
A generalized framework for single-variate and multivariate simulation and
forecasting problems in stochastic hydrology is proposed. It is appropriate
for short-term or long-term memory processes and preserves the Hurst coeff
icient even in multivariate processes with a different Hurst coefficient in
each location. Simultaneously, it explicitly preserves the coefficients of
skewness of the processes. The proposed framework incorporates short-memor
y (autoregressive moving average) and long-memory (fractional Gaussian nois
e) models, considering them as special instances of a parametrically define
d generalized autocovariance function, more comprehensive than those used i
n these classes of models. The generalized autocovariance function is then
implemented in a generalized moving average generating scheme that yields a
new time-symmetric (backward-forward) representation, whose advantages are
studied. Fast algorithms for computation of internal parameters of the gen
erating scheme are developed, appropriate for problems including even thous
ands of such parameters. The proposed generating scheme is also adapted thr
ough a generalized methodology to perform in forecast mode, in addition to
simulation mode. Finally, a specific form of the model fur problems where t
he autocorrelation function can be defined only for a certain finite number
of lags is also studied. Several illustrations are included to clarify the
features and the performance of the components of the proposed framework.