Near infrared spectroscopic data handling and chemometric analysis with the R statistical programming language: A practical tutorial

Near infrared spectroscopy is widely used for compositional analysis of bulk materials because it is inexpensive, fast, and non-destructive. However, the chemometric techniques required to produce near infrared calibrations are varied and complex. While there are a number of commercial applications capable of implementing these techniques, there has also been a recent proliferation of R packages for chemometrics. The R programming language has greater capabilities for data processing, automation of multiple analyses, and user development of new techniques than many of the closed-source, graphical user interface-based commercial chemometrics applications do. The R project is thus a powerful, open-source option for generating and testing near infrared calibrations, albeit with a longer learning curve than many of the commercial chemometric applications. The calibration techniques available in R have been widely demonstrated in both the primary literature and introductory texts, but less so the steps between the acquisition of the data and the calibration. This tutorial seeks to bridge that gap by demonstrating a practical approach to data transfer and handling, using R and several packages available on the Comprehensive R Archive Network (https://cran.r-project.org/), and then illustrates the use of the resulting data framework in the generation of near infrared calibrations.