Efficient sampling of polycyclic aromatic compounds for free energy predictions through active learning

The physical growth of Polycyclic Aromatic Compounds (PACs) to soot particles plays a significant role in understanding the chemistry of soot formation. Insights into the process can be gained from PACs’ free energy of dimerization landscape. However, because the infeasibly large space of possible PAC dimers cannot be exhaustively simulated, researchers must train machine learning models on a subset of data to impute the rest. To this end, we propose and assess an active learning approach to discovering the optimal PACs for training a machine learning model to predict PACs’ association and dissociation free energies. The comparison between active learning and random sampling showed that active learning has faster loss convergence, requiring fewer training samples to reach the same level of accuracy. The trained model accurately modeled unseen PACs and exhibited robustness against changes in the sampling space used to train the model. More broadly, this work shows how active learning can optimize the design and improve the understanding of more expensive models in specific domains. • Polycyclic Aromatic Compounds (PAC) growth to soot is key to understanding soot formation chemistry. • Machine learning models can predict PAC dimerization free energy from a limited dataset. • Active learning outperforms random sampling for PAC modeling, needing fewer samples to achieve high accuracy. • The trained model is robust and predicts unseen PACs, aiding in complex model optimization.