Identification of chemical structures from infrared spectra by using neural networks

Structure identification of chemical substances from infrared spectra can be done with various approaches: a theoretical method using quantum chemistry calculations, an inductive method using standard spectral databases of known chemical substances, and an empirical method using rules between spectra and structures. For various reasons, it is difficult to definitively identify structures with these methods. The relationship between structures and infrared spectra is complicated and nonlinear, and for problems with such nonlinear relationships, neural networks are the most powerful tools. In this study, we have evaluated the performance of a neural network system that mimics the methods used by specialists to identify chemical structures from infrared spectra. Neural networks for identifying over 100 functional groups have been trained by using over 10000 infrared spectral data compiled in the integrated spectral database system (SDBS) constructed in our laboratory. Network structures and training methods have been optimized for a wide range of conditions. It has been demonstrated that with neural networks, various types of functional groups can be identified, but only with an average accuracy of about 80%. The reason that 100% identification accuracy has not been achieved is discussed.