In this paper we introduce data characterizations for fitting chaotic
data to linear combinations of one-dimensional maps (say, of the unit
interval) for use in subgrid-scale turbulence models. We test the effi
cacy of these characterizations on data generated by a chaotically-for
ced Burgers' equation and demonstrate very satisfactory results in ter
ms of modeled time series, power spectra and delay maps. (C) 1998 Else
vier Science Inc. All rights reserved.