This paper concerns with the development of a direct parameter identification procedure for a class of nonlinear reaction–diffusion equations. We assume to know the model equations with the exception of a set of constant parameters, such as diffusivity and reaction term parameters. Using the finite element method the original partial differential equation is transformed into a set of ordinary differential equations. A linear least squares method is then applied to estimate the unknown parameters by using normal equations. The measurements errors obtained following this approach are significantly lower than the error obtained by a nonlinear least squares identification procedure. In order to better understand the differences between the two approaches, a sensitivity analysis with respect to initial conditions and mesh dimension is performed. The robustness of the method is tested on noise corrupted data, showing that the linear least square method may be sensitive to perturbations in the data. The procedure is applied to two ecological models describing the dynamics of population growth.

Mocenni, C., Madeo, D., & Sparacino, E. (2011). Linear least squares parameter estimation of nonlinear reaction diffusion equations. MATHEMATICS AND COMPUTERS IN SIMULATION, 81, 2244-2257 [10.1016/j.matcom.2011.05.006].

Linear least squares parameter estimation of nonlinear reaction diffusion equations

MOCENNI, CHIARA;MADEO, DARIO;SPARACINO, EMILIANO
2011

Abstract

This paper concerns with the development of a direct parameter identification procedure for a class of nonlinear reaction–diffusion equations. We assume to know the model equations with the exception of a set of constant parameters, such as diffusivity and reaction term parameters. Using the finite element method the original partial differential equation is transformed into a set of ordinary differential equations. A linear least squares method is then applied to estimate the unknown parameters by using normal equations. The measurements errors obtained following this approach are significantly lower than the error obtained by a nonlinear least squares identification procedure. In order to better understand the differences between the two approaches, a sensitivity analysis with respect to initial conditions and mesh dimension is performed. The robustness of the method is tested on noise corrupted data, showing that the linear least square method may be sensitive to perturbations in the data. The procedure is applied to two ecological models describing the dynamics of population growth.
Mocenni, C., Madeo, D., & Sparacino, E. (2011). Linear least squares parameter estimation of nonlinear reaction diffusion equations. MATHEMATICS AND COMPUTERS IN SIMULATION, 81, 2244-2257 [10.1016/j.matcom.2011.05.006].
File in questo prodotto:
File Dimensione Formato  
MCS_2011.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 290.19 kB
Formato Adobe PDF
290.19 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11365/42691
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo