Machine Learning Classification of Disrotatory IRC and Conrotatory Non-IRC Trajectory Motion for Cyclopropyl Radical Ring Opening

Transition-state features from trajectories were used for supervised machine learning analysis of the cyclopropyl radical ring opening reaction. Quantitative and qualitative assessment of features controlling disrotatory IRC versus conrotatory non-IRC motion and revealed that there are two key vibrational modes where their directional combination provides prediction of pathway motion.