Estimation of the ARNO model baseflow parameters using daily streamflow data

An approach is described for estimation of baseflow parameters of the ARNO model, using historical baseflow recession sequences extracted from daily s treamflow records. This approach allows four of the model parameters to be estimated without rainfall data, and effectively facilitates partitioning o f the parameter estimation procedure so that parsimonious search procedures can be used to estimate the remaining storm response parameters separately . Three methods of optimization are evaluated for estimation of four basefl ow parameters. These methods are the downhill Simplex (S), Simulated Anneal ing combined with the Simplex method (SA) and Shuffled Complex Evolution (S CE). These estimation procedures are explored in conjunction with four obje ctive functions: (1) ordinary least squares; (2) ordinary least squares wit h Box-Cox transformation; (3) ordinary least squares on prewhitened residua ls; (4) ordinary least squares applied to prewhitened with Box-Cox transfor mation of residuals. The effects of changing the seed random generator for both SA and SCE methods are also explored, as are the effects of the bounds of the parameters. Although all schemes converge to the same values of the objective function, SCE method was found to be less sensitive to these iss ues than both the SA and the Simplex schemes. Parameter uncertainty and int eractions are investigated through estimation of the variance-covariance ma trix and confidence intervals. As expected the parameters were found to be correlated and the covariance matrix was found to be not diagonal. Furtherm ore, the linearized confidence interval theory failed for about one-fourth of the catchments while the maximum likelihood theory did not fail for any of the catchments. (C) 1999 Elsevier Science B.V. All rights reserved.