Spectral features from specific regions in infrared spectra of organic molecules can consistently be attributed to certain functional groups. Artificial neural networks were employed as a pattern recognition tool to elucidate the relationships between functional groups and spectral features. The ability of these network models to predict the presence and absence of a variety of functional groups was evaluated. The sensitivity of the artificial neural network over the entire infrared spectral region was used to generate a spectral factor representation of the major information associated with each functional group. The resulting sensitivity factors were utilized in a much simpler model for functional group prediction. Ultimately, the presence of a functional group was predicted based on the dot product of an unknown spectrum with the corresponding sensitivity factor. A probability based on Bayes' theorem was assigned to each of the predictions. The prediction accuracies were greater than 90% for all 13 functional groups considered in the investigation.

Spectral features in Raman spectra of organic molecules can be attributed to certain functional groups. A library of 1222 Raman spectra was used to train an artificial neural network (ANN) for predicting the presence of 13 functional groups. Sensitivity analysis was applied to the ANN models to determine a sensitivity factor or feature spectrum for each functional group. The feature spectra could then be used to predict the presence of specific groups based on Bayes' theorem. Once a model is constructed for each functional group, it can be applied directly to measured spectra of structurally unknown molecules and provide real-time predictions. Prediction accuracies of greater than 90% were obtained for aromatic, alkene, aldehyde, ketone, ester, nitro, and nitrile linkages. Accuracies for alcohols and amines were in the 80% range.