Understanding the patterns that neural networks learn from chemical spectra

14 March 2023, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


Analysing spectra from experimental characterization of materials is often time consuming, susceptible to distortions in data, requires specific domain knowledge, and may be susceptible to biases in general heuristics under human analysis. Recent work has shown the potential of using machine learning methods to solve this task, and provide automated and unbiased spectral analysis on- the-fly . We present a simple 1D neural network model to classify infrared spectra from small organic molecules, according to their functional groups. Our model is within range of state-of-the-art performance while being significantly less complex than previous works. A smaller network reduces the risk of overfitting and enables exploring what the model has learned about the underlying physics behind the spectra. Using explainability techniques, we show that our model learns the characteristic group frequencies of functional groups, and additionally uses non-intuitive patterns to classify spectra. We argue for the development of smaller yet accurate models to carry out tasks where model transparency is as important as prediction accuracy


machine learning
deep learning
Infrared Spectra
Experimental Characterization
Spectral Analysis

Supplementary materials

Supplements for the paper


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.