Machine Learning Excited State Potential Energy Surfaces of Solvated Nile Red with ESTEEM

Machine Learned Interatomic Potentials (MLIPs) offer a powerful combination of abilities for accelerating theoretical spectroscopy calculations utilising both ensemble sampling and trajectory post-processing for inclusion of vibronic effects, which can be very challenging for traditional ab initio MD approaches [1]. We demonstrate a workflow [2] that enables efficient generation of MLIPs for the solvatochromic dye nile red, in a variety of solvents [3]. We use iterative active learning techniques to make this process as efficient as possible in terms of number and size of DFT calculations [4]. Additionally, we compare the efficacy of various methodologies: generating distinct MLIPs for each adiabatic state, using one ground state MLIP in combination with delta-ML of excitation energies, and using a three-headed multiheaded ML model. To evaluate the validity of the resulting models, we compare predicted absorption and emission spectra to experimental spectra.

Refs:

1.) T. J. Zuehlsdorff, A. Montoya-Castillo, J. A. Napoli, T. E. Markland, and C. M. Isborn, J. Chem. Phys., 151, 074111, (2019).

2.) J. Eller and N. D. M. Hine, arXiv:2510.19088.

3.) N. Ghoneim, Spectrochim. Acta A, 56, 1003, (2000).

4.) E. Mosqueira-Rey, D. Alonso-Ríos, and A. Baamonde-Lozano, Procedia Comput. Sci., 192, 553, (2021).