Work

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

Year: 2025

Type: article

Abstract: 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.

Source: Energy and AI

DOI: 10.1016/j.egyai.2025.100528

Authors: Mohammed I. Radaideh, Matt Raymond, Paolo Elvati, Jacob C. Saldinger, Majdi I. Radaideh, Angela Violi

Institution: University of Michigan

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,630

Funders: National Science Foundation, University of Michigan, Division of Chemical, Bioengineering, Environmental, and Transport Systems