The impact of temperature variations on spectroscopic calibration modelling: a comparative study

Abstract

Abstract:Temperature fluctuations can have a significant impact on the repeatability of spectral measurements and as a consequence can adversely affect the resulting calibration model. More specifically, when test samples measured at temperatures unseen in the training data set are presented to the model, degraded predictive performance can materialize. Current methods for addressing the temperature variations in a calibration model can be categorized into two classescalibration model based approaches, and spectra standardization methodologies. This paper presents a comparative study on a number of strategies reported in the literature including partial least squares (PLS), continuous piecewise direct standardization (CPDS) and loading space standardization (LSS), in terms of the practical applicability of the algorithms, their implementation complexity, and their predictive performance. It was observed from the study that the global modelling approach, where latent variables are initially extracted from the spectra using PLS, and then augmented with temperature as the independent variable, achieved the best predictive performance. In addition, the two spectra standardization methods, CPDS and LSS, did not provide consistently enhanced performance over the conventional global modelling approach, despite the additional effort in terms of standardizing the spectra across different temperatures. Considering the algorithmic complexity and resulting calibration accuracy, it is concluded that the global modelling (with temperature) approach should be first considered for the development of a calibration model where temperature variations are known to affect the fundamental data, prior to investigating the more powerful spectra standardization approaches.

On-line and non-destructive measurement of core temperature in heat treated fish cakes by NIR hyperspectral imaging

“…The water has absorption peaks at 840 nm, 970 nm, 1190 nm, 1450 nm, and 1940 nm due to a combination of different overtones of OH stretching and bending bands. This temperature shift complicates calibration models based on NIR for samples with varying temperature, since this effect has to be accounted for (Chen & Martin, 2007). On the other hand, the phenomenon can also be used to monitor the temperature in materials.…”

Influence and correction of temperature on optical measurement for fat and protein contents in a complex food model system

“…Similar results were obtained by Peirs et al [11] who concluded that representative calibration sets to cover the temperature range expected in the future seemed to be the best option for measurement of the soluble solids contents of apples under unstable temperature conditions. Also Chen and Martin [17] undertook a comparison of the predictive performance of a number of temperature correction techniques and concluded that the global modeling approach achieved the best predictive performance.…”

A Local Model and Calibration Set Ensemble Strategy for Open-Path FTIR Gas Measurement with Varying Temperature

“…Difficulty with temperature variations in the open path occur in both industrial and atmospheric measurements. Degraded predictive performance of calibration models in which the temperatures of calibration and prediction differ is a known problem [39,40]. Quantitative interpretation of spectra at varying temperatures is difficult [41].…”