Exploring Machine Learning in Chemistry through the Classification of Spectra: An Undergraduate Project

Abstract

Applications of machine learning in chemistry are many and varied, from prediction of structure–property relationships, to modeling of potential energy surfaces for large scale atomistic simulations. We describe a generalized approach for the application of machine learning to the classification of spectra which can be used as the basis for a wide variety of undergraduate projects. While our examples use FTIR and mass spectra, the approach could equally well be used with UV–visible, Raman, NMR, or indeed any other type of spectra. We summarize a number of different unsupervised and supervised machine learning algorithms that can be used to classify spectra into groups, and illustrate their application using data from three different projects carried out by fourth year chemistry undergraduates. The three projects investigated the ability of the various machine learning approaches to correctly classify spectra of a variety of fruits, whiskies, and teas, respectively. In all cases the algorithms were able to differentiate between the various samples used in each study, and the trained machine learning models could then be used to classify unknown samples with a high degree of accuracy (>98% in many cases). Depending on the extent to which students are expected to write their own code to perform the data analysis, the general model adopted in this work can be adapted for a variety of purposes, from short (one to two day) practical exercises and workshops, to much longer independent student projects.

Implementation of an R Shiny App for Instructors: An Automated Text Analysis Formative Assessment Tool for Evaluating Lewis Acid–Base Model Use

“…Technologies help facilitate learners’ access to and participation in learning resources that provide formative feedback . The development of this Shiny app based on our previous machine learning-based tool is a small start, adding to other machine learning-based resources to support the learning of chemistry topics. − We have made our R code freely available so that others might use our code to translate other assessment instruments and prompts into practical tools for educators more easily . We should note that other researchers have also begun to develop tools such as dashboards to provide students and instructors with automated feedback; , this is yet another example of how such technologies can be used to transform and promote learning.…”

Machine Learning for Infrared Spectral Classification of Polyvinyl butyrals with Identical Chemical Groups: An Example for Undergraduate Chemistry Classes

“…16,17 ML has demonstrated remarkable ability to differentiate spectra with exceptionally subtle differences, that traditional analytical methods struggle to achieve. 22,23 Although teaching examples of integrating ML and spectroscopic techniques have been documented, 11,20,24 they currently primarily focus on identifying small molecules or compounds with distinct functional groups or physiochemical attributes (Table LI-1 in the Instructor Note). 20,24 In principle, these examples can be distinguished by human experience using traditional analytical methods.…”

A Modern Twist on an Old Measurement: Using Laboratory Automation and Data Science to Determine the Solubility Product of Lead Iodide

“…Data science and laboratory automation are rapidly becoming essential tools in modern experimental chemistry. , As such, it is important that we teach these skills throughout the chemistry curriculum, but efforts to date have primarily been in upper-level courses. Recent articles in this Journal have discussed training machine learning for spectroscopy-related problems in physical and analytical chemistry. − High-throughput experimentation has been discussed in the context of second-year organic chemistry and upper-level biochemistry courses. − The closely related idea of autonomous experimentation  colloquially known as “self-driving labs”  has been discussed in the context instrumental analysis or advanced elective courses. − …”