A new approach for multivariate instrument standardization is presente
d. This approach is based on the use of neural networks (NNs) for mode
ling spectral differences between two instruments. In contrast to the
piecewise direct standardization (PDS) method to which it is compared,
the proposed method builds a single transfer model for all spectral w
indows. The apparently incompatible requirements for a high number of
training objects and a low number of standardization samples are addre
ssed by truncating spectra in finite-size windows and assessing a posi
tion index to each window, Each spectral window with the corresponding
position index constitutes a training object. No prior background cor
rection is required with this method. Both the proposed method and PDS
were applied to some real and simulated data sets, and results were e
valuated for reconstruction and subsequent calibration. On the studied
data sets, the neural network approach was found to perform at least
as well as PDS for both reconstruction and calibration.