Graph-based calibration transfer

TL;DR

This paper introduces a novel graph-based calibration transfer method that uses manifold regularization of PLS to align calibration standards across instruments without requiring similar spectral features, improving calibration transfer accuracy.

Contribution

The proposed method uniquely employs manifold regularization of PLS to enable calibration transfer with arbitrary standards, bypassing the need for similar spectral features or explicit pre-processing.

Findings

Outperforms current state-of-the-art methods on the corn benchmark dataset.

Effectively removes inter-device variation without explicit data pre-processing.

Demonstrates robustness with different calibration standards.

Abstract

The problem of transferring calibrations from a primary to a secondary instrument, i.e. calibration transfer (CT), has been a matter of considerable research in chemometrics over the past decades. Current state-of-the-art (SoA) methods like (piecewise) direct standardization perform well when suitable transfer standards are available. However, stable calibration standards that share similar (spectral) features with the calibration samples are not always available. Towards enabling CT with arbitrary calibration standards, we propose a novel CT technique that employs manifold regularization of the partial least squares (PLS) objective. In particular, our method enforces that calibration standards, measured on primary and secondary instruments, have (nearly) invariant projections in the latent variable space of the primary calibration model. Thereby, our approach implicitly removes inter-device variation in the predictive directions of X which is in contrast to most state-of-the-art techniques that employ explicit pre-processing of the input data. We test our approach on the well-known corn benchmark data set employing the NBS glass standard spectra for instrument standardization and compare the results with current SoA methods.