Spectroscopy and Chemometrics/Machine-Learning News Weekly #49, 2021

NIR Calibration-Model Services

Effective development of new quantitative prediction equations for multivariate data like NIR spectra | spectrum LINK

How to improve calibration models for NIR Instrument Devices? Wheat Food Security LINK

Spectroscopy and Chemometrics News Weekly 48, 2021 | NIRS NIR Spectroscopy MachineLearning Spectrometer Spectrometric Analytical Chemistry Chemical Analysis Lab Labs Laboratories Laboratory Software IoT Sensors QA QC Testing Quality LINK

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich 48, 2021 | NIRS NIR Spektroskopie MachineLearning Spektrometer IoT Sensor Nahinfrarot Chemie Analytik Analysengeräte Analysentechnik Analysemethode Nahinfrarotspektroskopie Laboranalyse LINK

Spettroscopia e Chemiometria Weekly News 48, 2021 | NIRS NIR Spettroscopia MachineLearning analisi chimica Spettrale Spettrometro Chem IoT Sensore Attrezzatura analitica Laboratorio analisi prova qualità Analysesystem QualityControl LINK

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

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

Near-Infrared Spectroscopy (NIRS)

“Insight into the stability of protein in confined environment through analyzing the structure of water by temperature-dependent near-infrared spectroscopy” LINK

“Determination of starch and amylose contents in various cereals using common model of near-infrared reflectance spectroscopy.” LINK

“RESEARCH ARTICLE Near-infrared spectroscopy for the distinction of wood and charcoal from Fabaceae species: comparison of ANN, KNN AND SVM …” LINK

“Device-Independent Discrimination of Falsified Amoxicillin Capsules Using Heterogeneous Near-Infrared Spectroscopic Devices for Training and Testing of a Support Vector Machine” LINK

“High quality VO(2) thin films synthesized from V(2)O(5) powder for sensitive near-infrared detection” | LINK

“Detection of toxic chemicals in hand sanitizers using near-infrared spectroscopy” LINK

“Identification of Baha’sib mung beans based on Fourier transform near infrared spectroscopy and partial least squares” LINK

“Remote Sensing : Identification of Amaranthus Species Using Visible-Near-Infrared (Vis-NIR) Spectroscopy and Machine Learning Methods” LINK

“Nondestructive Detection of Internal Flavor in ‘Shatian’Pomelo Fruit Based on Visible/Near Infrared Spectroscopy” | LINK

“Determination of sex-enhancing drugs illegally added in health care products by TLC-NIRS combined technology” LINK

“Rapid detection of exogenous sucrose in black tea samples based on near-infrared spectroscopy” LINK

“Rapid determination of diesel fuel properties by near-infrared spectroscopy” LINK

“Biosensors : Room-Temperature Synthesis of Air-Stable Near-Infrared Emission in FAPbI3 Nanoparticles Embedded in Silica” LINK

“Potential of visible-near infrared spectroscopy for the determination of three soil aggregate stability indices” LINK

” A dataset of the chemical composition and near-infrared spectroscopy measurements of raw cattle, poultry and pig manure” LINK

“Forests : Identifying Wood Based on Near-Infrared Spectra and Four Gray-Level Co-Occurrence Matrix Texture Features” LINK

“… Selection for Referenceless Multivariate Calibration: A Case Study on Nicotine Determination in Flue-Cured Tobacco Powder by Near-Infrared (NIR) Spectroscopy” LINK

“Prediction and Utilization of Malondialdehyde in Exotic Pine Under Drought Stress Using Near-Infrared Spectroscopy” | LINK

“Quantification of irrigated lesion morphology using near-infrared spectroscopy” | LINK

“A Comparison between the Post-and Pre-dispersive Near Infrared Spectroscopy in Non-Destructive Brix Prediction Using Artificial Neural Network” LINK

Infrared Spectroscopy (IR) and Near-Infrared Spectroscopy (NIR)

“Efficient Broadband Near‐Infrared Emission in the GaTaO4:Cr3+ Phosphor” | LINK

“Aflatoxin contaminated cocoa beans classification using near-infrared spectroscopy” LINK

“The Effect Of Hemodynamic Parameters On Peripheral Near Infrared Spectroscopy In An Animal Model” LINK

“Iridium(III) Complexes with [2, 1, 0] Charged Ligands Realized DeepRed/NearInfrared Phosphorescent Emission” LINK

Raman Spectroscopy

“Multivariate Analysis Aided Surface-Enhanced Raman Spectroscopy (MVA-SERS) Multiplex Quantitative Detection of Trace Fentanyl in Illicit Drug Mixtures Using a Handheld Raman Spectrometer” LINK

Hyperspectral Imaging (HSI)

“BRCN-ERN: A Bidirectional Reconstruction Coding Network and Enhanced Residual Network for Hyperspectral Change Detection” LINK

“Rapid identification of adulterated safflower seed oil by use of hyperspectral spectroscopy” LINK

“Remote Sensing : Monitoring the Severity of Pantana phyllostachysae Chao on Bamboo Using Leaf Hyperspectral Data” LINK

“Rapid identification of the green tea geographical origin and processing month based on near-infrared hyperspectral imaging combined with chemometrics” LINK

“Chemometric strategies for near infrared hyperspectral imaging analysis: classification of cotton seed genotypes” LINK

“Applied Sciences : Determination of Sugar, pH, and Anthocyanin Contents in Port Wine Grape Berries through Hyperspectral Imaging: An Extensive Comparison of Linear and Non-Linear Predictive Methods” LINK

“… Area Index, Chlorophyll Content and Fraction of Vegetation Cover Using an Empirical-Statistical Approach from Chris-Proba Satellite Hyperspectral Images over the …” LINK

“Design and verification of a large-field hyperspectral imaging system” LINK

“Visualization of heavy metal cadmium in lettuce leaves based on wavelet support vector machine regression model and visible‐near infrared hyperspectral imaging” LINK

“Band Selection for HSI Classification using Binary Constrained Optimization” LINK

“New Approach to the Old Challenge of Free Flap Monitoring—Hyperspectral Imaging Outperforms Clinical Assessment by Earlier Detection of Perfusion Failure” LINK

Spectral Imaging

“Machine learning and hyper spectral imaging: multi spectral endoscopy in the gastro intestinal tract towards hyper spectral endoscopy” LINK

Chemometrics and Machine Learning

“… residual extreme learning machine (PLSRR-ELM) calibration algorithm applied in fast determination of gasoline octane number with near-infrared spectroscopy” LINK

“Recognition of authentic or false blood based on NIR spectroscopy and PCA-WNN-PSO algorithm” LINK


“Comparison of PLS and SVM models for soil organic matter and particle size using vis-NIR spectral libraries” LINK

“Multivariate Calibration of Concentrations of C, Mn, Si, Cr, Ni, and Cu in Low-Alloy Steels from Raw Low-Resolution Spectra Obtained By Laser-Induced Breakdown Spectroscopy” LINK

Optics for Spectroscopy

“Foam Flows in Turbulent Liquid Exfoliation of Layered Materials and Implications for Graphene Production and Inline Characterisation” LINK

“Chemical Engineering of Cu-Sn Disordered Network Metamaterials” LINK

“High-Performance Waveguide-Integrated Bi<sub>2</sub>O<sub>2</sub>Se Photodetector for Si Photonic Integrated Circuits” LINK

Equipment for Spectroscopy

“Electrical and Mechanical Properties of Intrinsically Flexible and Stretchable PEDOT Polymers for Thermotherapy” LINK

“Application of hand-held near-infrared and Raman spectrometers in surface treatment authentication of cork stoppers” LINK

Process Control and NIR Sensors

“Dry Powder Mixing Is Feasible in Continuous Twin Screw Extruder: Towards Lean Extrusion Process for Oral Solid Dosage Manufacturing” | LINK

“Manipulating electroluminochromism behavior of viologen substituted iridium(III) complexes through ligand engineering for information display and encryption” LINK

Environment NIR-Spectroscopy Application

“Remote Sensing : Estimating Vertical Distribution of Leaf Water Content within Wheat Canopies after Head Emergence” LINK

Agriculture NIR-Spectroscopy Usage

“Towards ecological intensification of agriculture: from management to soil bacterial and nitrogen-cycling communities” LINK

“Er: YAG Laser Cleaning of Painted Surfaces: Functional Considerations to Improve Efficacy and Reduce Side Effects” LINK

“Agronomy : Evaluation of Metabolomic Profile and Growth of Moringa oleifera L. Cultivated with Vermicompost under Different Soil Types” LINK

“High-throughput phenotyping of cool-season crops using non-invasive sensing techniques” LINK

Forestry and Wood Industry NIR Usage

“Polymers : Passive Fire Protection of Taeda pine Wood by Using Starch-Based Surface Coatings” LINK

Food & Feed Industry NIR Usage

“Foods : Microbiological Quality Assessment of Chicken Thigh Fillets Using Spectroscopic Sensors and Multivariate Data Analysis” LINK

“The potential to increase beef production in tropical Nth Australia by including Desmanthus cv JCU 2 in a Buffel grass (Cenchrus ciliaris) dominant pasture” LINK

Pharma Industry NIR Usage

“Spectroscopic characteristics of Xeloda chemodrug” | LINK

Laboratory and NIR-Spectroscopy

“Potential of laboratory hyperspectral data for in-field detection of Phytophthora infestans on potato” LINK


“Beam test of carbon ion production for development of new compact ECR ion source for multi ion therapy” LINK

“Silver Peroxide Nanoparticles for Combined Antibacterial Sonodynamic and Photothermal Therapy” | LINK

“Splanchnic oxygen saturation during reoxygenation with 21% or 100% O2 in newborn piglets” | LINK

NIR-Predictor Release Notes

Legend: [+] added, [*] improved, [/] bugfix, [-] removed

NIR-Predictor Download Page

V2.6.0.2 Public Release – 18.08.2021


  • [/] “Create Properties File …” could lead in seldom cases to an IndexOutOfRangeException in SampleReplicates.analyze3ToString. The bug has not affected created data.

V2.6 Public Release – 1. June 2020

New Key Features

  • Reads and predicts .SPC spectra file format (Thermo-Scientific Galactic GRAMS)

    Support for multi spectra and single spectra .SPC files.
    Multiple multi-spectra files can be predicted in one step.

  • Spectra Plots on the prediction reports

    Visualizes the min,median,max spectrum of the spectra dropped as files on the NIR-Predictor.
    This gives a minimal and good spectral overview of the predicted property results.


  • [+] Thermo-Scientific Galactic GRAMS SPC spectra file format support for multi spectra and single spectra files. Multiple multi-spectra files can be imported in one step.

  • [+] Spectra Plot Thumbnail on the Prediction Report

    • Spectra Plot color legend: min,median,max spectrum by predicted property or if no calibration is available by spectral intensity.
  • [+] Prediction Report Header information extended

    • because of introduced spectra plot, with
      • “Spectral Range” (x-axis) of the spectra e.g. “1000 to 2400 Nanometers [500 datapoints]”
      • “Spectral YUnit” e.g. “ABSORBANCE”
    • and fully documentation of the used system (for system validation purpose)
      • “Operating System” detailed version information about the Operating System.
  • [+] User Interface

    • A shortcut for the function “Update Applications (F4)” is also possible with a click on the “Application” text label.
    • A shortcut for the function “Update Calibrations (F5)” is also possible with a click on the “Calibrations” text label.

V2.5 Public Release – 5. May 2020

New Key Features


  • [+] More Vendor Spectra File Supported: ams, Avantes, PIXELTEQ, Senorics.
  • [+] Simple Custom CSV Data Spectra File Supported.
  • [+] Properties File Creator supports now both Sample-based and Spectra-based propertyFiles templates.
  • [*] Improved parsing of JCAMP and Vendor file formats.
  • [*] Improved parsing of propertyFiles and CalibrationRequest.
  • [*] About dialog shows detailed software version.

V2.4 Public Release – September 2019

New Key Features

  • Multi spectral-formats, multi spectra-files with with multi calibrations predictions

    Automatic file format detection.

    see NIR-Predictor supported Spectral Data File Formats

  • Properties File Creator

    A tool for the NIR-User to create the propertyFile easily. It helps to create a CSV file from the measured spectraFiles with sampleNames and Properties to edit in Spreadsheet/EXCEL software.

    Sample based with automatic sample/spectra replicate/repeats detection and analysis for data cleanup for better data quality.

    Lets you enter Lab-Reference-Values in a sample-based manner, corresponding to your sample spectra for calibration. 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. (Data Cleaning, Data Cleansing, Data Quality)

    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.

  • Create Calibration Request

    Packs created Properties files and spectra files in a compressed ZIP file for sending to the CalibrationModel.com Service. Helps with additional information about the property type you entered and if the Lab-values are enough to get calibrated.

  • Histogram Charts

    Showing the distribution of the predicted results per calibration. Color shows the out-of-calibration range results.


  • [+] Menu function (F7) to “Create Calibration Request…”
  • [+] Histograms of Prediction Values per Property in the Prediction Report. Shows the distribution of the predicted results per calibration.
  • [*] Prediction Report reduced file size, ca. 25% less.
  • [*] Prediction Report – Missing ‘Date Time’ are shown as empty.
  • [*] Prediction report list the Spectra files in a compact way, same path information is shown once.
  • [+] Prediction Report supports the order/sorting of the prediction results of the spectra, which can be defined as: GivenOrder | Date_Name | Name_Date | Date_NamesWithNumbers | NamesWithNumbers or Reverse sorted.
  • [+] The last used Application is loaded on next start. Because often you need to continue on the same, if not you need to change it anyway.
  • [*] Prediction Report lists “Result Ordering” and “Outlier Symbols” settings above the table, to quick know how the table is ordered and the symbols are defined.
  • [+] Prediction Report contains an overall Outlier Statistics for multiple spectra below the header of “Prediction Value List”.
  • [+] Menu “Show latest Updates” opens the https://calibrationmodel.com/NIR-Predictor-Release-Notes/ in the browser.

V2.3 Public Release – June 2019

New Key Features

  • Native spectra file formats

    Support for many mobile NIR Spectrometers.

    See NIR-Predictor supported Spectral Data File Formats

  • Application concept

    Allows to group multiple Calibrations together for an Application.

  • Properties File Creator

    Menu “Create Properties File…” to enter Lab-Reference-Values for calibration. The file is created from a folder of spectra files, so it contains their names, dates and hashes.


  • [+] Support for native file formats of many mobile and hand-held NIR Spectrometers.
  • [+] Automatic file format detection.
  • [+] Select Applications for predictions.
  • [+] Application allows to group multiple Calibrations together for a Application.
  • [+] Calibration Property Legend shows the “Folder” name of the Calibration file. That allows the user to distinguish duplicates of calibration property names. If the Calibration File is flat in the default Calibrations folder then under “Folder” stands “”.
  • [*] Calibrations are sorted in the prediction report by 1. Folder (you can structure the Calibs in subfolders as you like), 2. Property name, 3. Property Range Max.
  • [+] Menu function (F4) to “Search and load Applications” from the calibration folder, where you can arrange the calibration files in folder structure.
  • [+] Menu function (F5) to “Search and load Calibrations” from the calibration folder, where you can arrange the calibration files in folder structure and move deactivated calibs outside.
  • [+] Menu function (F6) to “Create Properties File…” to enter Lab-Reference-Values for calibration. The file is created from a folder of spectra files, so it contains their names, dates and hash.
  • [*] Ctrl+O to select spectra files to predict (same as dialog button or drag & drop files)
  • [*] File Select Dialog is only opened once to multi-select spectra files.
  • [+] Predicts multiple spectra files at once in different file-formats and different wave-ranges and wave-resolutions with all compatible calibrations.
  • [*] Prediction Report with sorted Calibration/Properties by subfolder and Property name. Allows grouping of calibrations in sub folders.
  • [*] Prediction Report results table can be copied to spreadsheet programs like Excel containing the structure.
  • [*] Instead of warning information “CalibrationIncompatibleForSpectrum” there is no predicted value, to have a compact nice readable report. And a “-” mark is set in Outlier column Out. In the legend it’s listed as “- : spectrum is incompatible to calibration”
  • [*] The property unit is not shown as [] if it is not known.
  • [*] Functions keys for menu functions, for fast access.

V2.2 Public Release – August 2018

Key Features

  • Drag & drop spectra files to be loaded, pre-processed, predicted and reported.

  • Automatic pre-processing of spectra

  • Multi spectra files with with multi calibrations prediction


  • Installation: There are no administrator rights required, unpack the zip file to a folder “NIR-Predictor” in your documents or on your desktop. Read the ReadMe.txt and run the application (.exe) file.
  • Uninstall: Make sure to backup your reports and calibrations inside your “NIR-Predictor” folder. Delete the “NIR-Predictor” folder.
  • [+] Report is stored automatically.
  • [+] Outlier statistics.
  • [+] Total predictions statistics.
  • [+] All the steps are automatic. And can be done individually to act on input changes.
  • [+] comes with demo data, so you can predict sample spectra with demo calibrations.
  • [+] has no functional limitations, no nagging, no ads and needs no license-key.
  • [+] runs on Microsoft Windows 7/8/8.1/10 (Starter, Basic, Professional) (32 bit / 64 bit).
  • [+] Minimal System Requirements: Windows 7 Starter 32Bit, 1.6 GHz, 2 GB RAM, non-Administrator account

V1.0 – V2.1 Internal Releases – 2018