Linear techniques to correct for temperature-induced spectral variation in multivariate calibration

Wülfert, Florian; Kok, Wim Th.; Noord, Onno E. de; Smilde, Age K.

doi:10.1016/s0169-7439(00)00069-1

Cited by 80 publications

(77 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several strategies have been proposed to deal with the non-linearity, such as pre-processing [12] (standard normal variate (SNV) [13], extended multiplicative signal correction (EMSC) [14], etc. ), non-linear calibration techniques (artificial neural network (ANN) [15][16][17], Gaussian processes regression (GPR) [18][19]), and variable selection [20][21]. However, these models may be non-robust in the sense that small change in the calibration data and/or model parameters can result in significant change in model predictions.…”

Section: Introductionmentioning

confidence: 99%

Bagging for robust non-linear multivariate calibration of spectroscopy

Wang

Chen

Lau

2011

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Bagging for robust non-linear multivariate calibration of spectroscopy

Wang

Chen

Lau

2011

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

“…One challenge faced in industrial on-line and in-line applications of spectroscopy is that the samples are not analyzed under well-controlled laboratory conditions, materializing in fluctuations in some of the external factors, such as temperature and pressure. This behaviour will result in significant spectral variations occurring for the same sample under different conditions [8][9][10][11][12][13], causing the resultant calibration model to perform poorly, if these variations are not taken into account.…”

Section: Introductionmentioning

confidence: 99%

“…With a view to eliminating the impact of temperature on the spectra, variable selection techniques can be applied to select those variables (wavelengths) that are less affected by the temperature variations [11][12] [14]. However the variable selection strategies typically involve complex selection algorithms and additional computational costs.…”

Section: Introductionmentioning

confidence: 99%

“…However the variable selection strategies typically involve complex selection algorithms and additional computational costs. It was also demonstrated [11] [14] that it can be difficult to identify and remove completely those wavelengths affected by temperature, and thus the application of variable selection techniques is potentially limited in terms of applicability.…”

Section: Introductionmentioning

confidence: 99%

“…Alternatively the temperature can be explicitly included into the PLS model as an additional variable; however such methods were found to provide inferior prediction results compared with the implicit method, the rationale being the nonlinear effect of temperature on the spectra [11]. To account for the non-linear effect of temperature, Hageman et al [8] reviewed several non-linear regression methods, including locally weighted regression [15], neural networks [15], penalized signal regression [16] [17] and support vector machine [18] [19], where support vector machine achieved the most promising prediction performance.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Chen

Martin

2007

Journal of Chemometrics

View full text Add to dashboard Cite

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.

show abstract

Evaluation of temperature compensation methods for a near‐infrared calibration to predict the viscosity of micellar liquids

Haroon

Arafeh

Rodgers

et al. 2020

Journal of Chemometrics

View full text Add to dashboard Cite

Near‐infrared (NIR) spectroscopy is a popular technique for the measurement of chemical and physical properties in‐line using predictive models. The success of these models in industrial settings, in terms of accuracy and precision, often relies on the removal or avoidance of non‐linear spectral changes associated with fluctuating process parameters like temperature. In this work, a NIR calibration model developed to predict the viscosity of micellar liquids in‐line is used to evaluate various methods designed to account for temperature fluctuations. The viscosity of these liquids can vary on average by ±0.5 Pa s with a 1° change in temperature. The methods trialled include global linear techniques, a multivariate filter (generalised least squares weighting [GLSW]) and direct standardisation. The performances of these techniques were compared against one another based on root mean square error of prediction (RMSEP), prediction bias and rank. The best method was found to be GLSW, which was the least complex (five latent variables) and showed the lowest RMSEP (0.429 Pa s). This study provides insight into the use of recognised methods to remove temperature‐induced spectral variation in a PLS model developed to predict viscosity, where both NIR spectra and the property of viscosity itself are sensitive to temperature.

show abstract

Linear techniques to correct for temperature-induced spectral variation in multivariate calibration

Cited by 80 publications

References 30 publications

Bagging for robust non-linear multivariate calibration of spectroscopy

Bagging for robust non-linear multivariate calibration of spectroscopy

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

Evaluation of temperature compensation methods for a near‐infrared calibration to predict the viscosity of micellar liquids

Contact Info

Product

Resources

About