Spectroscopic (NIR) Calibration

Spectroscopic (NIR) Calibration

Number of days:3
Fee: € 1500
Find scheduled events

Over the last 2 decades more and more companies opt for (on-line) NIR calibration models as an alternative to time-consuming and expensive lab analyses. This is often the case throughout the whole production process: to check the quality of the feedstock at delivery, to obtain timely information on different process streams, and to quantify the quality of the end product. 
Also in food companies the use of NIR calibration models for e.g. the monitoring and automation of processing of biological products has become common practice.
Due to continuous chemometrical developments, the number of applications of spectroscopic calibration - especially NIR - continues to increase, despite the strong overlap of spectral bands and peaks in the NIR region.

In this course we will go through the different steps required for a successful Spectroscopic Calibration: from sample selection over validation and interpretation of the models, up to guidelines and recommendations for the maintenance and update of calibration models in the future. Since emphasis will be put on practice, theoretical aspects will be alternated with practical exercises.

Each participant is offered free individual follow-up coaching. Follow-up coaching means that each participant can appeal to the trainer’s expertise, after having applied the methods treated in the course to his / her own cases. This coaching comprises an individual follow-up session of two hours with the trainer, as well as follow-up support by phone.  Read more.

In this course, the participants will develop a feel for the multivariate approach to spectroscopic calibration, gain insight into the underlying methods, learn to perform a multivariate calibration in "normal" situations and recognise problem situations.

If your aim is to perform multivariate calibrations and/or to properly interpret the results, this course will satisfy your needs.
No prior knowledge is required.


Day 1: 

  • NIR introduction
  • Exploratory Multivariate Analysis
    • Visualisation of information in big data sets
    • Principal Component Analysis (PCA)
    • Cluster analysis: searching for groups of similar samples

Day 2: 

  • Basic principles of calibration techniques
    • Multiple Linear Regression (MLR)
    • Principal Component Regression (PCR) 
    • Partial Least Squares (PLS) 
  • Interpretation of calibration models
  • Model validation
  • Preprocessing and scaling of spectra

Day 3: 

  • Detection of outliers and non-linearities
  • Prediction with calibration models
  • Selection of calibration samples
  • Standardisation of calibration models
  • Monitoring the performance of (on-line) calibration models

Each course day will be held from 9 am to about 4.30 pm. The course fee includes handouts, lunches and the individual follow-up coaching.