Spektroskopie und Chemometrie Neuigkeiten Wöchentlich #25-30, 2017

Leider ist der Eintrag nur auf English verfügbar.

Wir machen NIR Chemometrie einfach

Hi, we’re CalibrationModel. Our aim is to transform your NIR data to superior calibration models. We do this by using knowledge driven software applying good practices and rules from literature, publications, regulatory guidelines and more. Our service is used by NIR specialists to deliver a valuable model for their NIR analysis measurements. With CalibrationModel services, NIR specialists can find out how their NIR Data can be robust and optimally modeled by which data preprocessing and wavelength selection, etc. You can implement CalibrationModel in a matter of minutes using our contact form and send your NIR data to receive optimized model settings as a blueprint.
NIR specialists (Spectroscopist, Chemometricians) love perfect models. They’re curious about how to improve their models even further, because all NIR models need continuous maintenance and updates.
Using CalibrationModel services, NIR Specialists can deliver real value to their measurement results through powerful model optimization capabilities.
CalibrationModel We make NIR Chemometrics easy. Near-Infrared Data Modeling Calibration Service

NIR Spectroscopy Calibration Report for quantitative predictive models

When you send your quantitative NIR spectra data to our NIR Calibration Model Service, you get a detailed calibration report (calibration protocol) of the found optimal calibration settings, so you are able to see all insights and easily re-build the model in your NIR/Chemometric software.

Here is a part of our calibration report, that exactly describes the data used in the calibration set (CSet), the validation set (VSet) and the test set (TSet). The numbers are the number ids of the spectra in your delivered NIR data file.

The calibration method settings and parameters are
Waveselection : the variable selection or wavenumber selection or wavelength selection
Pretreatments : the spectral data pre-processing
PCs : the number of Principal Components (PC) or Latent Variables (LV)
Method : the modeling method algorithm used, e.g. PLS

Then the statistical analysis of the PLS model by the different sets (CSet, VSet, Tset).

Calibration Report

Statistical analysis of calibration, validation and test results : 1 Name, 2 Unit, 3 N : number of spectra, 4 N : number of samples, 5 Average spectra count per sample, 6 Reference values, 7 Min, 8 Mean, 9 Median, 10 Max, 11 Standard deviation, 12 Skewness : left (-) or right (+) lack of symmetry, 13 Kurtosis : flat (-) or peaked (+) shape, 14 Model statistics, 15 RPD, 16 R², 17 RMSEC, RMSEP, RMSET : root mean square of prediction errors, 18 SEC, SEP, SET : standard error (bias corrected), 19 Bias, 20 Skewness of prediction errors, 21 Kurtosis of prediction errors, 22 Intercept, 23 Slope, 24 Intercept (reverse), 25 Slope (reverse), 26 Sample Prediction Repeatability Error, 27 Sample Prediction Repeatability Error (of Missing data MSet)

This shows how we deliver the optimal settings. With the statistical values, the NIR model predicted values of all spectra and additional plots you are able to compare with your re-built model to verify that the models perform nearly equally.

Wie werden Nahinfrarotspektroskopie Kalibrierungen im 21. Jahrhundert entwickelt?

The Problem

Calibration modeling is a complex and very important part of NIR spectroscopy, especially for quantitative analysis. If the model is badly designed the best instrument precision and highest data quality does not help getting good and robust measurement results. And NIR Spectroscopy requires periodically recalibration and validation.

How are NIR models built today?

In a typical usage in industry, a single person is responsible to develop the models (see survey). He or she uses a Chemometric software that has a click-and-wait working process to adjust all the possible settings for the used algorithms in dialogs and wait for calculations and graphics and then to think about the next modeling steps and the time is limited to do so. Do we expect to find the best use-able or optimal model that way? How to develop near-infrared spectroscopy calibrations in the 21st Century?

Our Solution

Why not put all the knowledge a good model builder is using into software and let the machines do the possibilities of calculations and presenting the result? Designing the software that way, that the domain knowledge is built-in, not just only the algorithms for machine learning and make it possible to scale the calculations to multi-core computers and up to cloud servers. Extend the Chemometric Software with the Domain Knowledge and make as much computer power available as needed.

As it was since the beginning

User → Chemometric Software → one Computer → some results to choose from

==> User’s time needed to click-and-wait for creating results

Our Solution

User → (Domain Knowledge → automatized Chemometric Software) → many Computers → the best models

==> User’s time used to study the best models and reasoning about his product / process

Note that the “Domain Knowledge” here does perfectly support the User’s product and process knowledge to get the things done right and efficient.

Scaling at three layers

  • Knowledge : use the domain knowledge to drive the Chemometric Software
  • Chemometric Software : support many machine learning algorithms and data pre-processings and make it automatic
  • Computer : support multi-core calculations and scale it to the cloud

The hard part in doing this, is of course the aggregation of the needed domain knowledge and transform it into software. The Domain Knowledge for building Chemometric NIR Spectroscopic models is well known and it’s huge and spreads multiple disciplines. Knowledge-driven software for computing helps to find the gold needle in the haystacks. It’s all about scaling that makes it possible. See Proof of Concept.

New possibilities

  • NIR users can get help working more efficient and getting better models.
  • New types of applications for NIR can be discovered.
  • Evaluation of NIR Applications to replace conventional analytical methods.
  • Hopeless calibrations development efforts can be re-started.
  • Higher model accuracy and robustness can be delivered.
  • Automate the experimental data part of your application study.
  • Person independent optimization will show new solutions, because it’s not limited by a single mindset => combining all the aggregated knowledge and its combinations.
  • Software independent optimization will show new solutions, because none of vendor specific limitations and missing algorithms are present => combining all open available algorithms and there permutations.
  • Computing service is included.

Contact us for trial

Your NIR data is modeled by thousands of different useful calibration models and you get the best of them! That was not possible before in such a easy and fast way! See How it works

NIR Kalibrationsentwicklung (Teil 2)

( zu Teil 1 )

Alle folgenden Kategorien werden durch die Verwendung mehrerer verschiedener Algorithmen und Formeln umgesetzt, was zu vielen unterschiedlichen Kalibrierungen führt.

Arbeitsschritte bei der Modell Erstellung
  • Daten Bereinigung – (schlechte Daten, fehlende Werte, Duplikateliminierung, spektrale Qualität / Intensität / Rauschen, Eingabewert Tippfehler, …)
  • Initial Kalibrierung einrichten – Auswahl der Kalibrierungs-, Validierungs- und Test-Sets
  • Wellenlängen Auswahl
  • Datenvorverarbeitung, Datenvorbehandlungen
  • Method Berechnung
  • Die Wahl der Anzahl der Hauptkomponenten / Latente Variablen / Faktoren
  • Validierung des Kalibrierungs Modell / Performance Statistiken – (Genauigkeit, Präzision, Linearität, Wiederholbarkeit, Reichweite, Verteilung, Robustheit / Stabilität, Empfindlichkeit, Einfachheit, etc.)
  • Ausreißer Untersuchung und Beseitigung

Das Problem der Wahl der optimalen Anzahl von Faktoren, um das Optimum zwischen Unterfittung und Überfittung zu finden, wird gelöst durch mehrere implementierte Methoden und Protokollen, was zu mehreren Kalibrierungen führt.

Die Auswertung und die Auswahl der besten Kalibrierung basiert auf vielen einzelnen statistischen Werten, einschließlich der beliebtesten RMSEP, SEP, Bias, SEC, R2 und PCs usw.

Ergebnisse und Berichte

Eine detailliertes Kalibrierprotokoll wird bereitgestellt, das die beste verfügbare Kalibrierung detailliert mit allen Kalibrierparameter Einstellungen und Statistiken der Vorhersage Leistung des Kalibrier-Sets, des Validierungs-Sets und des Test-Sets beinhaltet. Eine visuelle Betrachtung der Kalibrierung wird mit den wichtigsten Grafiken zur Verfügung gestellt.

Unser Service funktioniert mit jedem quantitative NIR-Spektren Daten Satz im Standardformat JCAMP-DX-Format und verwendet hauptsächlich PLS und PCR um kompatibel zu sein mit anderen chemometrischen Kalibrierungssoftwaren.

Summary of the NIR Chemometric survey polls

Summary of the NIR Chemometric survey polls (as of end of Sept. 2013)

The interesting finding is that most of the answers fit the following pattern. The most companies that use NIR have one NIR Instrument and only one employee that is able to develop NIR calibrations. For that the most common off-the-shelf chemometrics program is used and spent 2 hours or over a month and therefore gets no calibration training about the complex topics like Chemometrics and NIR Spectroscopy or only once (introduction). The calibration maintenance ranges from never to 3 times a year. Interestingly, there was no one who uses portable NIR instruments. We continue our surveys, for the discovery of new trends. Conclusion Seeing this picture, we think that there is huge potential to improve the calibrations. Advanced knowledge can help individuals to build the calibrations with best practices and improve their models accuracy and reliability. Once the decision and investment in NIR technology is done, you should get the best out of your data, because this extra NIR performance can be given by calibration optimization. We offer this as an easy to use and independent service.

(English) Meet us at the NIR 2013 – 16th International Conference on Near Infrared Spectroscopy (ICNIRS 2013)

Meet us at the NIR 2013 – 16th International Conference on Near Infrared Spectroscopy (ICNIRS 2013) in Montpeiller, France , 2-7 June 2013.

If you are interested in analysis and optimization of your data during the conference, please take a JCAMP export of your data on a USB-memory stick with you.

We will also present a poster P129 :

A novel intelligent knowledge-based Chemometric Software Framework for quantitative NIR Calibration Modeling‘ by Roman Bossart




  • Unter Chemometrik oder auch Chemometrie versteht man die chemische Teildisziplin, die sich mit der Anwendung mathematischer und statistischer Methoden beschäftigt, um zum einen in optimaler Weise chemische Verfahren und Experimente zu planen, zu entwickeln oder auszuwählen. Zum anderen kann mit chemometrischen Methoden ein Maximum an chemischen Informationen aus experimentellen Messdaten extrahiert werden. Beispielsweise sind Spektren der Nahinfrarotspektroskopie nur mittels der Chemometrie auswertbar. – Wikipedia (2012)
  • Chemometrik ist das, was Chemometriker tun. – Anonym
  • Chemometrie ist die Anwendung von mathematischen und statistischen Techniken in der Chemie.


Chemometrie Programme / Software

NIR Chemometrie Software

Wir entwickeln die NIR Kalibrations Modelle mit Hersteller unabhängiger Chemometrie Software, die hauptsächlich mit den weit verbreiteten und bewährten Methoden PLS und PCR arbeitet und alle gängigen Datenvorbehandlungen unterstützt. So kann mit jeder Hersteller spezifischen Chemometrie Software das Modell verwendet werden.

Dies ist eine Auflistung von kompatiblen Chemometrie Software Paketen:

Chemometrie-Software als Support-Service

Chemometrie-Software gebündelt mit NIR-Spektrometer*

Standalone Chemometric software packages *

*) Disclaimer: Wir haben keine Verbindung mit jeder dieser Sites oder deren Gesellschaften.

Chemometric Software
Which Chemometric Software are you using for NIR?