Infrared spectrum analysis of organic molecules with neural networks using standard reference data sets in combination with real world data

In this study, we propose a neural network based approach to analyze IR spectra and detect the presence of functional groups. Our neural network architecture is based on the concept of learning split representations. We demonstrate that our method achieves favorable validation performance using the NIST dataset. Furthermore, by incorporating additional data from the open-access research data repository Chemotion, we show that our model improves the classification performance for nitriles and amides. We could reach an improved performance of our model referring to previous models with F1 scores for identifying 17 functional groups above 0.7.