Spectroscopy and Chemometrics News Weekly #3, 2020

Near Infrared (NIR) Spectroscopy

“Fourier-transform near infrared spectroscopy (FT-NIRS) rapidly and non-destructively predicts daily age and growth in otoliths of juvenile red snapper Lutjanus …” LINK

“Desarrollo de Modelos NIRS de Predicción para el Análisis de la Finura de Fibras Textiles de Vicuña y Llama” LINK

“fNIRS-GANs: Data augmentation using generative adversarial networks for classifying motor tasks from functional near-infrared spectroscopy.” LINK

” Simulated NIR spectra as sensitive markers of the structure and interactions in nucleobases” LINK

“Penentuan Parameter Mutu Buah Jeruk Siam Garut Secara Nondestruktif Menggunakan Spektroskopi NIR” LINK

“Rapid non-destructive moisture content monitoring using a handheld portable Vis–NIR spectrophotometer during solar drying of mangoes (Mangifera indica L.)” LINK

“VIS-NIR wave spectrometric features of acorns (Quercus robur L.) for machine grading” LINK

“Portable NIR Spectroscopy: Affordable Technology for Developing Countries” LINK

“NIR spectroscopy used for non-destructive evaluation of the chemical composition of the investigated papers in addition to typically used standard methods.” LINK

“Feasibility study on prediction of gasoline octane number using NIR spectroscopy combined with manifold learning and neural network” LINK

“Authentication of Tokaj Wine (Hungaricum) with the Electronic Tongue and Near Infrared Spectroscopy” LINK

“Environmental advantages of visible and near infrared spectroscopy for the prediction of intact olive ripeness” LINK

“Rapid screening and quantitative analysis of adulterant Lonicerae Flos in Lonicerae Japonicae Flos by Fourier-transform near infrared spectroscopy” LINK

“Rapid analysis of soluble solid content in navel orange based on visible-near infrared spectroscopy combined with a swarm intelligence optimization method” LINK

“Establishment and relevant analysis of plant’s spectral reflectivity database in visible and near-infrared bands” LINK

Hyperspectral Imaging

“Mineral Mapping of Drill Core Hyperspectral Data with Extreme Learning Machines” LINK

“Deep learning classifiers for hyperspectral imaging: A review” LINK

“Texture and Shape Features for Grass Weed Classification Using Hyperspectral Remote Sensing Images” LINK

“Avoiding Overfitting When Applying Spectral-Spatial Deep Learning Methods on Hyperspectral Images with Limited Labels” LINK

“Estimation Model of Winter Wheat Yield Based on Uav Hyperspectral Data” LINK

Chemometrics and Machine Learning

“Validation of near infrared spectroscopy as an age-prediction method for plastics” LINK

Whoever leads in ArtificialIntelligence in 2030 will rule the world until 2100 | fintech AI MachineLearning DeepLearning robotics LINK

“Chemical Composition of Hexene-Based Linear Low-Density Polyethylene by Infrared Spectroscopy and Chemometrics” LINK

“Establishment of Plot-Yield Prediction Models in Soybean Breeding Programs Using UAV-Based Hyperspectral Remote Sensing” LINK


“NIR reflectance spectroscopy and SIMCA for classification of crops flour” LINK

NIR Equipment

“Prediction of meat quality traits in the abattoir using portable and hand-held near-infrared spectrometers” LINK

“A Plug-and-play Hyperspectral Imaging Sensor Using Low-cost Equipment” LINK

NIR in Environment

“The use of hyperspectral remote sensing to detect PCB contaminated soils in the 0.35 to 12 micron spectral range” LINK

NIR in Agriculture

“Fast measurement of phosphates and ammonium in fermentation-like media: a feasibility study” LINK

“Detection of early decay on citrus using hyperspectral transmittance imaging technology coupled with principal component analysis and improved watershed …” LINK

“Determination of Nutritive Value of Some Feedstuffs Used in Poultry Nutrition by Near Infrared Reflectance Spectroscopy (NIRS) and Chemical Methods” LINK

“근적외선분광법을 이용한 사료용 벼의 사료가치 평가” “Evaluation of Feed Values for Whole Crop Rice Using Near Infrared Reflectance Spectroscopy” LINK

“Classification of crop flours based on protein contents using near infra-red spectroscopy and principle component analysis” LINK

“In-field detection of Alternaria solani in potato crops using hyperspectral imaging” LINK

NIR in Laboratory

“Use of Remote sensing technology to assess grapevine quality” LINK


Spectroscopy and Chemometrics News Weekly 2, 2020 | NIRS NIR Spectroscopy MachineLearning Spectrometer Spectrometric Analytical AI Application Chemical Analysis Lab Labs Laboratories Laboratory Software Sensors QA QC Testing Quality LINK

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich 2, 2020 | NIRS NIR Spektroskopie MachineLearning Spektrometer IoT Sensor Nahinfrarot Chemie Analytik Analysengeräte Analysentechnik Analysemethode Nahinfrarotspektroskopie Laboranalyse LINK

Spettroscopia e Chemiometria Weekly News 2, 2020 | NIRS NIR Spettroscopia MachineLearning analisi chimica Spettrale Spettrometro Chem Sensore Attrezzatura analitica Laboratorio analisi prova qualità Analysesystem predictionmodel LINK

Start Calibrate

This week’s NIR news Weekly is sponsored by Your-Company-Name-Here – NIR-spectrometers. Check out their product page … link

Get the Chemometrics and Spectroscopy News in real time on Twitter @ CalibModel and follow us.

Cost comparision / Price comparison of Chemometrics / Machine Learning / Data Science for NIR-Spectroscopy

CalibrationModel.com (CM) versus Others

Costs are not everything, there are other important factors listed in the table.

CM fix € pricing Others € Price Range (approx.)
Chemometric Package not‑needed
€3500 – €6500 per user
Chemometric Predictor
€1500 – €2500 per NIR device
Chemometric Training not‑needed
€1500 – €2500 per user
Chemometrician* Salary not‑needed
1 years Salary / year
(+ risk of Employee Turnover)
Powerful Computer (many Processors, lot of RAM for big data) not‑needed
€1500 – €4500 per computer
Development and Usage
Development of a Calibration
€80 – €150 / hour
of Chemometrician* using a Chemometric Software (click and wait) and applying it’s knowledge
Usage of a Calibration
€60 / year
Total €178 in first year
€60 in second year
initial (min €8000 , max €15500)
+ 2 * (2 – 4)(hour to cost same! as CM service) * (€80 – €150) Chemometrician* work
no initial cost
very high initial costs
no personnel cost
high personnel* costs
constant CM services
risk of Employee Turnover
global knowledge
risk of only use personal knowledge
easy to calculate fix cost on demand
difficult to calculate variable cost on demand plus Chemometrician* Recruitment needed
Results :
calibration prediction performance
always reproducible highly optimized
only as good as your Chemometrician* daily condition
better prediction performance, due to best-of 10’000x calibrations
small size of experiments, non-optimal calibrations

See also: pricing

Start Calibrate

*) Personnel / Chemometrician / Data Scientist / Data Analyst / Machine Learning Engineer : We are not against it, we are one of them a long time ago, but the way the work is done is changing (see below).

2019 Digitalization and the Future of Work: Macroeconomic Consequences
2019 The Digitalization of the American Workforce
2017 Digitalization and the American workforce , full-report


New: NIR-Predictor V2.4 with new features

The new Version of the free NIR-Predictor
supports multiple native file formats
of miniature, mobile and desktop spectrometers
get your spectra analyced as easy as Drag’n’Drop.

  • NIR-Predictor is an easy to use NIR software for all NIR devices
    to produce quantitative results out of NIR data.

  • CalibrationModel Service provides development of
    customized calibrations out of NIR and Lab data.

  • It allows to use NIR with your own customized
    models without the need of Chemometric Software!

  • We do the Machine Leraning for your NIR-Spectrometer
    and with the free NIR-Predictor you are
    able to analyze new measured samples.

  • For NIR-Vendors we also offer the
    Software Development Kit (SDK) for OEM Predictor use
    via the Application Programming Interface (API).
    Think of a sencod predictor engine,
    as a second heart in your system.


Key Features of NIR-Predictor

  • Super flexible prediction with automatic file format detection
  • Support for many mobile and desktop NIR Spectrometers file format
  • Application concept allows to group multiple Calibrations together for an Application
  • Prediction Report shows Histogram Charts of the tabulated prediction results
  • Sample based Properties File Creator for combining NIR and Lab reference data
  • Checked creation of a single file Calibration Request

Super flexible prediction

Loads multiple files at once in

  • different file-formats and …
  • different wave-ranges and wave-resolutions and …
  • predicts each spectrum with all compatible calibrations and …
  • merges the results in a report and …
  • saves the report as HTML.

It allows you to

  • comparing measurements
  • compare different calibrations
  • compare different spectrometers,
    carry out your own round-robin amongst the vendors’ instruments.
  • compare different spectra file formats

With no configuration and no special menu command,
just drag & drop your data files.


Properties File Creator

A tool for the NIR-User to create the property file easily. It helps to create a CSV file from the measured spectra files with sample names and properties to edit in Spreadsheet/EXCEL software. Lets you enter Lab-Reference-Values in a sample-based manner, corresponding to your sample spectra for calibration. It contains clever automatic analysis mechanisms of inconsistencies in your raw-data to increase the data quality for calibration. Provides detailed analyzer information for manual data cleanup when needed.

It’s time saving and less error prone because you DON’T need to open each spectrum file separately in an editor and copy the spectral values into a table grid beside the Lab-values.

Properties File Creator saves you from:

  • manually error prone and boring tasks
  • importing multiple data files and combining it’s content manually into a single data file to append the lab reference values (aka properties)
  • programming and writing scripts to transform the data into the shape needed
  • no trouble with data handling of
    • Wavelength / Wavenumber information (x-axis)
    • Absorbance / Reflectance labeling (y-axis)
    • checking compatibility of the raw data before merging
    • Averaging Spectral Intensities of a Sample
    • coping, flipping and transposing rows and colums to get the X-Block and Y-Block data sets ready for calibration modeling
    • limited and error prone table grid functionality

Because it’s all automatic and you can check the results and get the analysis information!

Properties File Creator provides you – a individual template based on your raw-data for combining NIR and Lab-values – analysis and checks for better data quality for calibration

Top 8 Reasons why you should use
Automated NIR Calibration Service

  • No subjective model selection
  • No variation in results and interpretation
  • No overfitting model
  • Better accuracy
  • Better precision
  • Time saving!
  • No software cost (no need for Chemometric software and training)
  • One free prediction software for all your NIR systems

Reduce Total Cost of Ownership (TCO) of your NIR

To be ahead of competitors
  • by not owning a chemometric software
  • by not struggling days with these complicated software
  • by not deep dive into chemometrics theory
It takes significant know-how and continous investment to develop calibrations
  • You need to have the relevant skill sets in your organization.
  • That means salaries (the biggest expense in most organizations)
To get most out of it, start now!
  • use the free NIR-Predictor together with your NIR-Instrument software
  • as an NIR-Vendor, integrate the free NIR-Predictor OEM into your NIR-Instrument software
  • don’t delay time-to-market
Read more about NIR Total cost of ownership (TCO)


About the included Demo-Spectra and Demo-Calibrations

The demo calibrations for the spectrometers from

  • Si-Ware Systems
  • Spectral Engines
  • Texas Instruments

are built with the raw data, thankfully provided from Prof. Heinz W Siesler, from this publication

“Hand-held near-infrared spectrometers:
State-of-the-art instrumentation and practical applications”
Hui Yan, Heinz W Siesler
First Published August 20, 2018 Research Article

The demo calibrations for the FOSS are built with the

ANSIG Kaji Competition 2014 shootout data


Quickstart: NIR-Predictor – Manual

Features and Version History: NIR-Predictor – Release Notes History

Supported NIR Spectra Formats: NIR-Predictor supported Spectral Data File Formats

Frequently Asked Questions: NIR-Predictor – FAQ

WebShop : CalibrationModel WebShop