Spectroscopy and Chemometrics News Weekly #5, 2019


Increase Your Profit with optimized NIRS Accuracy QA QC Food Feed Lab Biotech LINK

Spectroscopy and Chemometrics News Weekly 4, 2019 | NIRS NIR Spectroscopy Chemometrics analysis Spectral Spectrometer Spectrometric Analytical Sensors LINK

Spektroskopie und Chemometrie Neuigkeiten Wöchentlich 4, 2019 | NIRS NIR Spektroskopie Chemometrie Proben Analyse Spektrometer Spektral Sensor Nahinfrarot Analysengeräte Analysentechnik Analysemethode Analyzer Nahinfrarotspektroskopie LINK

Spettroscopia e Chemiometria Weekly News 4, 2019 | NIRS Spettroscopia Chemiometria analisi chimica Spettrale Spettrometro Sensore Attrezzatura analitica LINK


“Information Extraction in Frequency Domain Based on Entropy Theory and Genetic Algorithm in Near-Infrared Spectra” LINK

“Evaluation of Informative Bands Used in Different PLS Regressions for Estimating Leaf Biochemical Contents from Hyperspectral Reflectance” LINK

“Fusing spectral and textural information in near-infrared hyperspectral imaging to improve green tea classification modelling” LINK

“Development of Near Infrared Spectroscopy Models for Quantitative Prediction of the Content of Bioactive Compounds in Olive Leaves” LINK

“Using Consensus Strategy and Interval Partial Least Square Algorithm in Wavelet Domain for Analysis of Near-infrared Spectroscopy” LINK

“Classification of six herbal bioactive compositions employing LAPV and PLSDA” LINK

“Determination of ?-linolenic in Donkey Meat by Near Infrared Spectroscopy and Chemometrics” LINK

Near Infrared

“A Study on Rapid Non-destructive Detection of Eugenol in Caryophylli Flos by NIR Spectroscopy and Partial Least Square” LINK

“A feasibility study on quantitative analysis of low concentration methanol by FT-NIR spectroscopy and aquaphotomics” LINK

“Spectral Engines – NIRONE Sensor X makes material analyzing possible for consumers” NIRS NIR Spectral Sensor spectroscopy LINK

“trinamiX – Hertzstück™ NIR detector array modules for spectroscopy” NIRS NIR Spectral Sensor analyzing LINK

“Calibration of near infrared spectroscopy (NIRS) data of three Eucalyptus species with extractive contents determined by ASE extraction for rapid identification of species and high extractive contents” LINK

“Rapid assessment of monovarietal Portuguese Extra Virgin Olive Oil’s (EVOO’s) fatty acids by Fourier-transform Near-Infrared Spectroscopy (FT-NIRS)” LINK

New JSI Paper: Effect of colony age on near infrared hyperspectral images of foodborne bacteria. | bacteria NIR hyperspectral imaging LINK

“Evaluation of moisture content in processed apple chips using nirs and wavelength selection techniques” LINK

“Nondestructive Near-Infrared Spectroscopic Analysis of Oils on Wood Surfaces” LINK

“Treading on the unknown increases prefrontal activity: A pilot fNIRS study.” LINK


“Near infrared spectroscopic analysis of total alkaloids as nicotine, total nitrogen and total ash in Cuban cigar tobacco” LINK

“Identification of Natural Bamboo Fiber and Regenerated Bamboo Fiber by the Method of Modified near Infrared Spectroscopy” LINK

“On-line Measurement System for Anti icing Agent Content of Jet Fuel Based on Near Infrared Spectroscopy” LINK

“Investigation on Near-Infrared Quantitative Detection based on Heteromorphic Sample Pool” LINK

“Physiological interference reduction for near infrared spectroscopy brain activity measurement based on recursive least squares adaptive filtering and least squares support vector machines.” LINK

“A systemic review of functional near-infrared spectroscopy for stroke: Current application and future directions” LINK

“Biochemical Changes in Irradiated Oral Mucosa: A FTIR Spectroscopic Study” Biosensors LINK


“Raman-on-chip for high-throughput, high-resolution handheld spectroscopy” LINK


“Terahertz Spectroscopy: An investigation of the Structural Dynamics of Freeze-Dried PLGA Microspheres” LINK


“Cost-effective uncooled InGaAs SWIR image sensors and how to use them in Machine Vision” LINK


“Explainer: What is a quantum computer? How it works, why it’s so powerful, and where it’s likely to be most useful first” LINK


“Hyper spectral Analysis of Soil Iron Oxide using Fieldspec4 Spectroradiometer” LINK


“Decoration composition of Iberian Iron Age ivory artifacts identified by no-destructive chemical analyses” LINK

“CRISPR-Cas9 mediated targeted disruption of FAD2-2 microsomal omega-6 desaturase in soybean (Glycine max.L).” LINK

Spectroscopy and Chemometrics News #01-#10 2018


Check out Applied Spectroscopy’s special issue on chemometrics! (2018.03.10) LINK

“Development and Validation of a New Methodology to Assess the Vineyard Water Status by On-the-Go Near Infrared Spe… (2018.02.27) LINK

“Outliers, Part II: Pitfalls in Detecting Outliers” (2018.02.22) LINK

Identification of ground meat species using near-infrared spectroscopy and class modeling techniques – Aspects o… (2018.01.31) LINK

“Combining Broadband Spectra and MachineLearning to Derive Material Properties” – Steve Buckley (2018.01.31) LINK

Near Infrared

“Near-Infrared Spectroscopic Study of Chlorite Minerals” (2018.02.27) LINK

“Comparison of Methods for Estimating Mechanical Properties of Wood by NIR Spectroscopy” | NIRS (2018.02.25) LINK

“Verification of Pharmaceutical Raw Materials Using FT-NIR Spectroscopy” | FTNIR (2018.02.19) LINK

“The scanner claims to help stylists determine natural hair color & health through the use of near-infrared and vi… (2018.02.05) LINK

Near-infrared reflectance spectroscopy (NIRS) calibrations for assessment of oil, phenols, glucosinolates and fat… (2018.02.02) LINK

This is how I choose avocados for dinner – see a video of our new VNIR hyperspectral sensor demo in action! https://t.… (2018.02.02) LINK!

Near infrared chemical analysis technique is a small piece of a big cake a large part of study known as spectroscopy.… (2018.01.09) LINK!

mRMR-based wavelength selection for NIRS quantitative detection of Chinese yellow wine (2018.01.09) LINK

Saturn’s north polar hexagon in near-infrared, February 13 2017. Processed using data – (2018.01.08) LINK!


Research on the Effects of Drying Temperature on Nitrogen Detection of Different Soil Types by Near Infrared… (2018.02.02) LINK

Application of Near Infrared Reflectance Spectroscopy for Rapid and Non-Destructive Discrimination of Hulled Barl… (2018.01.09) LINK


Press Release – Imec demonstrates Shortwave Infrared (SWIR) range hyperspectral imaging camera | http… (2018.02.02) LINK


A micro-spectrometer fit for a smartphone: Could the power to measure things like CO2, food freshness, and blood su… (2018.02.25) LINK

TactiScan – unforeseen safety, efficiency and accuracy for detecting illicit narcotics. Visit TactiScan’s website for… (2018.02.22) LINK!

Ocean Optics () partners with Pyreos () on mid-IR spectroscopy solutions; laserfocusworld; see… (2018.02.08) LINK!

Ibsen ( ) Launches new Compact Spectrometer with Improved Resolution and 4096 Pixels (2018.02.02) LINK

Light Sensors: The Absorption Spectrometer, LIDAR, and Thermal Cameras on Display at CES 2018 (2018.02.02) LINK

more PIXELS … “Spectroscopy: The full spectrum” (2018.02.02) LINK

Process Control

Development of NIR-Spectroscopy-based Process Monitoring Methodology for Pharmaceutical Continuous Manufacturing … (2017.08.18) LINK


Nonlinear Regression with High-Dimensional Space Mapping for Blood Component Spectral Quantitative Analysis (2018.02.02) LINK


Where Agriculture and Blockchain Could Meet (2018.02.02) LINK

Food & Feed

Rapid Determination of Active Compounds and Antioxidant Activity of Okra Seeds Using Fourier Transform Near Infrare… (2018.03.03) LINK

Fascinating read: Using spectroscopy to detect if milk is really grass-fed. One way to validate NZ’s high-value food? The bes… (2018.02.08) LINK!

“How To Detect Coffee Fraud By Quantifying Robusta In Arabica Coffee Blends” – (2018.02.08) LINK

Measuring protein in semolina flour and durum wheat using Near Infrared Spectroscopy – Near Infrared Spectroscopy m… (2018.01.09) LINK


“Near-infrared spectroscopy detects age-related differences in skeletal muscle oxidative function: promising imp… (2018.02.08) LINK


These are the best countries and cities for attracting and developing talent | work (2018.02.14) LINK

ESA’s first launch of 2018 goes up tomorrow from China – it’s only the size of a cereal box but equipped with micro-propulsio… (2018.02.02) LINK!

Hi, I’m a chemistry prof who loves over-the-top makeup. I’m teaching spectroscopy today, so seemed appropriate. Colors… (2018.02.02) LINK!

Spectroscopy and Chemometrics News Weekly #41, 2016


Lipstick traces: FTIR calibration. cosmetics LINK

Using FT-Near-Infrared Spectroscopy to Predict the Mechanical Properties of Thermally Modified Southern Pine Wood LINK

Near Infrared

Fast Detection of Paprika Adulteration Using FT-NIR Spectroscopy – analytical techniques LINK

NIR spectroscopy to determine health of garlic cloves. vegetables LINK

Two-Dimensional MEMS Arrays Pave Way for Mobile Spectrometers. near-infrared (NIR) spectroscopy spectrometer LINK


Turning Raman into sound for Diagnostics – the Spectral Light Orchestra now here … LINK

Discrimination of Apple Liqueurs (Nalewka) Using a Voltammetric Electronic Tongue, UV-Vis and Raman Spectroscopy LINK


Perten NIR system approved for use in combustible dust environments – DA 7300 diode array LINK


New DISB spectrometer electronics with fast timing for instrument integrators OEM LINK

Screening system for MDMA in ecstasy tablets using a portable NIR spectrometer LINK

Food & Feed

Food scientists: We can detect much more food fraud – rawMaterials ingredients spectroscopic monitoring LINK

Food2030EU a platform for research and innovation shaping tomorrow’s sustainable food systems. FoodInnovation nutrit… LINK!

There’s a better way to detect food fraud – The fingerprint, or spectrum, can be compared to a validated fingerprint LINK

Spectroscopy and Chemometrics News Weekly #33, 2016


Quality assessment of refined oil blends during repeated deep frying monitored by SPME–GC–EIMS, GC and chemometrics LINK

Near Infrared

The use of portable near infrared spectroscopy in elite sport. PhD thesis, 2012 | Rio2016 spectroscopy LINK

Saphenous vein graft near-infrared spectroscopy imaging insights from the lipid core plaque association with… LINK

Corn Quality Variation Demonstrates Benefits of NIRS Analysis LINK


Raman-Test für Photovoltaik: Raman-Spektroskopie erlaubt kontaktfreie Analyse von Siliziumwafern. LINK

The new themed issue dedicated to SERS is now published! LINK

Spectral Imaging

Nondestructive inspection of insects in chocolate using near infrared multispectral imaging LINK


Machine Intelligence 2.0 in Charts and Graphs ArtificialIntelligence machineintelligence MachineLearning Swiss LINK


Raman spectroscopy could help identify life in Martian rocks | fossil LINK

Food & Feed

IR Spectroscopy Market Worth 1.26 Billion USD by 2022 – Biological, Pharmaceuticals, Chemicals, Food & Beverages LINK


XRF and Raman spectroscopy to identify pigments in early Irish manuscripts LINK

Laboratory Spectroscopy Assessments of Rainfed Paddy Soil Samples on Visible and Near-Infrared Spectroscopy LINK

Benefits of latest NIR developments – laboratory-based feed analysis LINK


“Companies don’t have ideas. Only people do.” LINK

NIRS Calibration Model Equation – Optimal Predictive Model Selection

To give you an insight what we do to find the optimal model, imagine a NIR data set, where a NIR specialist works hard for 4 hours in his chemometric software to try what he can with his chemometric-, NIR spectroscopic- and his product-knowledge to get a good model. During the 4 hours he finds 3 final candidate models for his application. With the RMSEP of 0.49 , 0.51 and 0.6. Now he has to choose one or to test all his three models on new measured NIR spectra.

That is common practice. But is this good practice?

And nobody asks, how long, how hard have you tried, how many trial have you done, if this really the best model that is possible from the data?
And imagine the cost of the data collection including the lab analytics!
And behind this costs, have you really tried hard enough to get the best out of your data? Was the calibration done quick and dirty on a Friday afternoon? Yes, time is limited and manually clicking around and wait in such kind of software is not really fun, so what are the consequences?

Now I come to the most important core point ever, if you own expensive NIR spectrometer system, or even many of them, and your company has collected a lot of NIR spectra and expensive Lab-reference data over years, do you spend just a few hours to develop and build that model, that will define the whole system’s measurement performance for the future? And ask yourself again (and your boss will ask you later), have you really tried hard enough, to get the best out of your data? really?

What else is possible? What does your competition do?

There is no measure (yet) what can be reached with a specific NIR data set.
And this is very interesting, because there are different beliefs if a secondary method like NIR or Raman can be more precise and accurate, as the primary method.

What we do different is, that our highly specialized software is capable of creating large amounts of useful calibrations to investigate this limits – what is possible. It’s done by permutation and combination of spectra-selection, wave-selection, pre-processing sequences and PC selections. If you are common with this, then you know that the possibilities are huge.

For a pre-screening, we create e.g. 42’000 useful calibrations for the mentioned data set. With useful we mean that the model is usable, e.g. R² is higher than 0.8, which shows a good correlation between the spectra and the constituent and it is well fitted (neither over-fitted nor under-fitted) because the PC selection for the calibration-set is estimated by the validation-set and the predictive performance of the test-set is used for model comparisons.

Here the sorted RMSEP values of the Test Set is shown for 42’000 calibrations.
You can immediately see that the manually found performance of 0.49 is just in the starting phase of our optimization. Interesting is the steep fall from 1.0 to 0.5 where manually optimization found it’s solutions. A range where ca. 2500 different useful calibrations exist. The following less steep fall from 0.5 to 0.2 contains a lot more useful models and between 0.2 to 0.08 the obvious high accurate models are around 2500 different ones. So the golden needle is not in the first 2500 models, it must be somewhere in the last 2500 models in the haystack.

Sorted RMSEP plot of 42'000 NIR Calibration Model Candidates

That allows us to pick the best calibration out of 42’000 models, depending on multiple statistical evaluation criteria, that is not just the R² or RPD, SEC, SEP or RMSEP, (or Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), Multivariate AIC  (MAIC) etc.) we do the model selection based on multiple statistical parameters.

Dengrogram plot of similar  NIR Calibration Models

To compare the calibration models by similarity it is best viewed with dendrogram plots like this (zoomed in), where the settings are shown versus the models overall performance similarity. In the settings you can see a lot of different permutations of pre-processings combined with different wave-selections.