Size-transferable prediction of excited state properties for molecular assemblies with machine-learned exciton model

Computational modeling of the excited states of molecular aggregates faces significant computational challenges and size heterogeneity. Current machine learning (ML) models, typically trained on specific-sized aggregates, struggle with scalability. We found that the exciton model Hamiltonian of large aggregates can be decomposed into dimer pairs, allowing an ML model trained on dimers to reconstruct Hamiltonians for aggregates of any size. We also systematically addressed the phase-correction problem by introducing coupling terms’ approximations. Our model accurately predicted the excitation energies of trimer and tetramer of perylene and tetracene and estimated S₁ oscillator strengths of perylene aggregates. Leveraging our ML model, the optical gaps of nanosized perylene aggregates with up to 50 monomers are analyzed, qualitatively revealing the role of different couplings on their size-dependency. Future work will explore transferability across different monomers to predict optical properties in heterogeneous assemblies.